Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
1155cf1233 | ||
|
|
5aef634115 | ||
|
|
b09cd2ef90 | ||
|
|
426f27c05a | ||
|
|
336e37724f | ||
|
|
7274017347 | ||
|
|
b94ab48ca4 | ||
|
|
ed3512d269 | ||
|
|
9ed91e64f8 | ||
|
|
c0db7374b7 |
@@ -17,6 +17,6 @@ jobs:
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Publish Custom Node
|
||||
uses: Comfy-Org/publish-node-action@main
|
||||
uses: Comfy-Org/publish-node-action@d2366e7abb6ab16f3bb03e3520ae25c8cf749bc9 # 1.0.1
|
||||
with:
|
||||
personal_access_token: ${{ secrets.REGISTRY_ACCESS_TOKEN }}
|
||||
|
||||
@@ -2,6 +2,11 @@
|
||||
|
||||
Condensed version-by-version index of DEVLOG.md (each line: version + one-line summary of what changed and why). Full rationale, code details, and "How to apply" lessons live in the excluded DEVLOG.md itself; this index exists so graphify can extract a queryable semantic node per release without feeding the full log to the local Ollama model. Regenerate with `python tools/generate_doc_index.py devlog` whenever DEVLOG.md changes.
|
||||
|
||||
- **v0.5.7** — 設定エクスポート/フルバックアップのドキュメント修正: v0.5.5のVideo Plan機能追加分の言及漏れ
|
||||
- **v0.5.6** — バグ修正: WD Taggerで不正確なタグが生成される問題を修正(GitHub Issue #1)
|
||||
- **v0.5.5** — Videoタブ全面刷新: Plan/Asset/Editバッチ生成 + Projectサブタブ + プレビュー2ペイン化 + Video Assets/Video Temp運用整理 + Galleryメタデータ消失バグ根本修正
|
||||
- **v0.5.4** — 機能追加: Video/GenerateUIタブのLTX-2.5・Wan2.2対応拡大 + AI Assistant設定のUnsloth対応・独立モーダル化・モデルアンロード機能
|
||||
- **v0.5.3** — バグ修正: Labタブのワークフロー切替時に前の内容が残留 + Galleryタブの読み込み高速化・root自動展開 + READMEスクリーンショット刷新
|
||||
- **v0.5.2** — 機能追加: GenerateUI/Labタブの動画ワークフロー対応 + VideoタブにFrame抽出/GIF変換機能 + データ管理監査とZIPフルバックアップ + Send to LI node統一
|
||||
- **v0.5.1** — 機能追加: mp4動画の埋め込みメタデータ対応(Gallery Prompt/JSON・Metadataサブタブ・サイドパネルIタブ)+ Gallery Infoタブに寸法/再生時間表示 + MiniMax H3等オールインワン動画ノードのプロンプト抽出バグ修正
|
||||
- **v0.5.0** — 機能追加: mp4動画Gallery対応 + Videoタブ新設(MiniMax H3専用) + バグ修正: Galleryのタグ/メモが再起動後に消える
|
||||
|
||||
@@ -2,6 +2,145 @@
|
||||
|
||||
---
|
||||
|
||||
## v0.5.7
|
||||
|
||||
### 設定エクスポート/フルバックアップのドキュメント修正: v0.5.5のVideo Plan機能追加分の言及漏れ
|
||||
|
||||
「Videoプランの追加で設定のエクスポート、バックアップ機能の更新が必要では」との確認依頼を受けて調査。v0.5.5で追加された`video_plan/`ディレクトリ(Plan JSON+インデックスPNG、`lab_plan/`と同構造)が、フルバックアップZIP機能の説明文言から漏れていないか確認した。実装(`_build_full_backup_zip`)自体は`DATA_DIR`配下のトップレベルエントリを汎用的に走査する設計(除外リスト`_FULL_BACKUP_EXCLUDE_NAMES`は`gmic_temp`/`thumb_cache`/`wildcard`の3つのみ)のため、`video_plan/`は既存コードの変更なしに自動的にバックアップ対象へ含まれていた——つまり機能的な欠陥は無かった。一方、ユーザー向け説明文(`fullBackupHint`/`helpSettings15`のi18n.js3言語、README.mdのFull Backup説明、`settings_routes.py`のコード内コメント)は「AI Skills、Lab Plans、Style presets」という列挙のままVideo Plan機能追加時に更新されておらず、実際にバックアップされるデータの説明として不正確になっていた。該当6箇所+READMEを「Video Plans」を含む形に修正。
|
||||
|
||||
### Video Plan (Planサブタブ) 中央パネルの設定項目レイアウト刷新 + MiniMax H3 Turbo/LTX-2.5 Prompt Enhance/Wan2.2 Turbo対応
|
||||
|
||||
「Duration・Noise SeedをMultipleの右隣に移動し、その下に新しい行でWidth/Height/MiniMaxのturbo_mode/strength/steps・LTX-2.5のprompt_enhance・Wan2.2のenable_turbo_mode(MiniMaxのturbo_modeと兼用)を追加したい」との要望。着手前にComfyUI_5環境の直近保存ワークフロー(`minimax_turbo.json`、LTX-2.5の`ltx_25_test`/`test2`/`test3`、Wan2.2の`wan22_test`/`test2`/`test3_i`)を実際にPythonでパースしてサブグラフの公開入力を調査し、対応可否を事前検証してから実装した。
|
||||
|
||||
調査で判明した構造: MiniMax H3は`turbo_mode`(BOOLEAN)/`turbo_model_strength`(FLOAT、LoRA強度)/`turbo_steps`(INT)をサブグラフの直接ウィジェットとして公開しており、これらがユーザーの言う「strength」「steps」に対応する。LTX-2.5は3バリアントとも`prompt_enhance`(BOOLEAN)を公開。Wan2.2は`enable_turbo_mode`(BOOLEAN)を公開しており、MiniMaxの`turbo_mode`と意味的に同一のためUI上は1つの「Turbo Mode」欄として兼用する設計にした。width/heightはMiniMax・LTX-2.5のText/Image版ではResolutionSelector経由(サブグラフ入力がリンク接続されている)だが、LTX-2.5のFirst & Last Frame版とWan2.2は全バリアントでResolutionSelectorを持たずサブグラフの直接ウィジェット値のまま——既存コードのコメント通りの構造を実データで確認できた。noise_seedは全ファミリーで`name="noise_seed"`に統一されている(LTX-2.5のText to Videoのみ`label="seed"`を持つため、ラベルではなくname直接一致で検索するヘルパーを新設)が、**Wan2.2のText to Videoだけサブグラフの公開入力に`noise_seed`が存在しない**(Image to Videoにはある)という非対称性を発見した。
|
||||
|
||||
実装は`video-workflow.js`の`locateVideoModelNodes()`を拡張し、上記7項目(width/height直接指定用インデックス、noise_seed、turbo_mode、turbo_strength、turbo_steps、prompt_enhance)のインデックスを検出して返すようにした(対応する入力が無ければ-1を返し、呼び出し側で無効化・非ハイライトの判断に使う)。既存のAspect Ratio/Megapixels/Multipleと全く同じ「ワークフローが対応する場合のみ入力可能+ラベルハイライト」の仕組みで新規7項目も統一し、新しい選択UIを作らず既存の`wfm-model-label-active`パターンを再利用した。noise_seedについては値の書き込みロジックをあえて追加しなかった——`comfyUI.generate()`がAPI変換後のワークフロー全体から`noise_seed`/`seed`キーを持つ全ノードを一括で上書きする既存の`applySeedToWorkflow()`が必ず後から実行されるため、`applyBlockToWorkflow()`側で書いても意味がなく、Plan全体のシード管理は引き続きそちらに一任する設計とした。
|
||||
|
||||
UI面ではDuration(元々ブロックごとの独立値)とNoise Seed(Plan全体で共有)を、機能的な性質は変えずにDOM位置だけtopbarのbasesettings行へ移動した。Durationはブロックエディタの`innerHTML`再生成に巻き込まれない固定要素にする必要があったため、change時のリスナー登録をブロック切替のたびに再アタッチする方式から、初期化時に一度だけ登録し値の同期のみブロック切替時に行う方式(`_initDurationControl()`新設)に変更した。新規7項目は`_plan.base_settings`に追加しPlan保存/読込(`_buildPlanData`/`_applyPlanData`)にも対応させた——Aspect Ratio等と同様Plan全体で共有する値とし、ブロックごとには持たせない設計とした。
|
||||
|
||||
実機検証はComfyUI_5(ユーザーが起動中のポート8189、8188に誤って重複起動してしまった分は作業後に停止)上でKaptureブラウザ操作により実施。MiniMax H3ワークフローで`Turbo Mode`/`Strength`/`Steps`が正しくハイライト・値反映され`Width`/`Height`は無効化されること、LTX-2.5 First & Last Frame版で`Width`/`Height`が有効化・ハイライトされること、Wan2.2 Text to Videoで`Noise Seed`のみ非ハイライト(disabled)になり`Turbo Mode`はハイライトされること、ブロック追加後にDurationがブロックごとに独立して保持される(1つ目=5秒のまま、2つ目=7秒に変更後も1つ目に戻ると5秒を維持)ことを、DOM要素のクラス・disabled状態を直接読み取って確認した。
|
||||
|
||||
ヘルプ文言は`helpVideo1`/`helpVideo2`/`helpVideo10`をindex.html・i18n.js(英日中3言語)・app.jsの`helpIdMap`の3点セットで更新——`helpIdMap`自体は既存のキーマッピングをそのまま流用でき変更不要だったが、`applyI18nToHtml`が起動時にi18n.jsの内容でDOM要素を上書きする一方でindex.html側の静的テキストが更新漏れになっていたため、ソース整合性のため合わせて修正した。README.mdのVideo Tabセクション(Plan/Edit subtabsの基本設定説明、Field highlight colorの対象フィールド一覧)も新規7項目を反映して更新した。
|
||||
|
||||
**検証**: `node --check`で変更した全JSファイルの構文確認。実機(ComfyUI_5、ポート8189)でMiniMax H3/LTX-2.5(First & Last Frame版)/Wan2.2(Text to Video版)の3ワークフローをKapture経由で実際にロードし、ハイライト・disabled状態・値反映・ブロックごとのDuration独立性をDOM評価で確認。開発元gitリポジトリと実行時`custom_nodes`フォルダは別実体のため([[project_dev_deploy_sync]]参照)、変更ファイル(`video-workflow.js`/`video-plan-tab.js`/`i18n.js`/`index.html`/`video-tab.css`)を都度両フォルダへ同期し`diff`で完全一致を確認。
|
||||
|
||||
**How to apply**: UIに新しい項目を追加する際、「ワークフローによって対応する場合のみ有効化・ハイライトする」という既存パターンが確立している画面では、新規に選択UIやトグルを作らず既存の仕組み(本プロジェクトでは`wfm-model-label-active`クラス+ラベルID登録)にそのまま乗せるのが一貫性を保ちやすい([[feedback_reuse_existing_ui_before_building_new]])。同系統に見えるモデルファミリー間でも、実際のワークフローJSONをパースして公開入力の有無を確認しないと「あるはず」の項目が無い非対称性(今回のWan2.2 Text to VideoのNoise Seed欠如)を見落とす——README/ヘルプ文言に「ワークフローXにはYが無い」という例外を書く前に、必ず実データで裏取りする。UI上は1つのフィールドとして統一表示しつつ、内部的には複数のワークフローファミリーそれぞれの異なる入力名(`turbo_mode`と`enable_turbo_mode`)にマッピングする「兼用フィールド」パターンは、意味が同じであることをコメントで明記した上でフォールバック演算子(`||`)で検出すればよく、UI側の分岐は不要になる。生成時に上流のAPI変換・送信処理(今回の`applySeedToWorkflow`)が特定のキーを一括で上書きする既存の仕組みがある場合、新規追加するフィールドの値が同じキーに書き込まれるなら、二重に値を設定するコードを書かず上流の処理に委ねる方が正確(後から上書きされる無駄なコードパスを残さない)。
|
||||
|
||||
関連: [[project_video_plan_asset_tab]], [[project_dev_deploy_sync]], [[feedback_reuse_existing_ui_before_building_new]]
|
||||
|
||||
---
|
||||
|
||||
## v0.5.6
|
||||
|
||||
### バグ修正: WD Taggerで不正確なタグが生成される問題を修正(GitHub Issue #1)
|
||||
|
||||
ユーザー(censor-ed氏)からのIssue報告: `wd-swinv2-tagger-v3`でタグ付けすると画像内容と一致しない不自然なタグが出力される。調査依頼者自身が原因を特定しており、`tagger_service.py`のONNX推論前処理がWD Tagger系モデルの学習時前処理と異なっていた(単純リサイズ+RGBのまま0.0〜1.0正規化)のに対し、WD Tagger系標準の前処理は「透過は白背景で合成→アスペクト比を維持したまま白背景で正方形にパディング→BICUBICリサイズ→RGB→BGR→0〜255のfloat32のまま(正規化なし)」であるとの具体的な指摘だった。`_predict_onnx()`をこの標準前処理に修正(本プラグインがサポートするONNXタガーはREADME記載の通りWD Tagger系のみのためパス全体を統一。DeepDanbooru用`_predict_dd()`は元々正しい前処理のため変更なし)。実機で`wd-eva02-large-tagger-v3`を使い、くまの着ぐるみパペットを持つ緑髪キャラクターのアニメ調画像でタグ付けを検証したところ、修正前は前処理が公式実装と異なる状態だったのに対し、修正後は`green_hair, bear_ears, bear_costume, paw_gloves, hoodie, animal_hood, animal_costume`など画像内容と高精度に一致する自然なタグが生成されることを確認した。
|
||||
|
||||
---
|
||||
|
||||
## v0.5.5
|
||||
|
||||
### Videoタブ全面刷新: Plan/Asset/Editバッチ生成 + Projectサブタブ + プレビュー2ペイン化 + Video Assets/Video Temp運用整理 + Galleryメタデータ消失バグ根本修正
|
||||
|
||||
「Videoタブにバッチ動画生成機能を追加したい。既存の生成UIタブのLab機能を動画生成用に整えたイメージ」との要望を起点に着手。従来のVideoタブ(単発生成フォーム)をPlan/Asset/Editの3タブ構成に再設計し、複数セッションにわたるユーザー実機確認・レイアウト調整・追加要望への対応、および調査の過程で発見した重大バグの根本修正までを1リリースにまとめた。
|
||||
|
||||
**1. Planタブ: タイムラインブロックによるバッチ動画生成**: 「基本設定→タイムラインをブロック分割→各ブロックにFirst/Last画像とプロンプトを設定→実行で順次バッチ生成」という要望を実装。LabタブがCheckpoint/LoRA/VAE/Prompt/Ksamplerそれぞれ独立したキーフレーム配列を持つ設計なのに対し、Video Planは「各ブロックが完結した1本の生成ジョブ」という単位でデータを持つ点が本質的に異なるため、Lab方式(`_buildWorkflowForIteration`によるキーフレーム解決)ではなく新規のデータモデル(`{id, color, duration, prompt, first_image_mode, first_image_filename, last_image_filename}`の配列)を設計した。First ImageはNone/画像を指定/前ブロックの最終フレームを使用の3択(`first_image_mode`)を持ち、chain_previous選択時は前ブロックに明示的なLast Imageがあればそれを直接使い(フレーム抽出不要)、無ければ前ブロックの生成動画から実際の最終フレームを`extractLastFrameBlob()`(Labのchain image機能で実績のある関数を再利用)でクライアント側抽出してアップロードする、という優先順位をユーザーと合意の上で実装した。Run/Pause/Cancelと進捗バーはLabタブの`_runLabBatch`と同じPromiseベースの一時停止機構を踏襲。ワークフロー操作(モデルファミリー自動判定・ノードへの値注入)はVideoタブの既存ロジックから`video-workflow.js`として抽出し、Plan/旧単発フォームの双方から呼べる純粋関数群にした。
|
||||
|
||||
**2. Plan永続化**: Labの`ws_labplan_`プレフィックス+PNGコンタクトシートへのiTXt埋め込み方式をそのまま踏襲し、`ws_videoplan_`プレフィックスでPlan JSON+インデックス画像を保存する仕組みを新規実装(`video_plan_service.py`はLabのサービスを複製、共通化はしない方針)。ブロックが1個のPlan=旧来の単発生成と等価になるよう設計し、「Load in Video」ボタンは常にブロック1個の新規Planを生成するようにした。
|
||||
|
||||
**3. Assetタブ: Galleryのグループ機能を再利用した素材管理**: 独自のフォルダブラウザを新規実装する代わりに、`feeder-tab.js`の「Galleryモード」(Gallery既存バックエンドをグループスコープで叩く軽量グリッド)と同じパターンを踏襲。当初は生成された動画を全て予約グループ`__VideoAssets__`へ自動追加する設計だったが、ユーザーからのフィードバックで用途を再定義:`__VideoAssets__`はユーザーがGalleryで手動キュレーションする「素材」グループとし、バッチ実行の自動追加先は新設の予約グループ`__vtemp__`(Planを保存していない生成物の一時置き場)に変更。Plan保存済みの場合は`VideoPlan:<name>`サブグループへ、未保存の場合は`__vtemp__`へ、という条件分岐にした。Assetタブのグループ選択には「All Video Assets」(`__VideoAssets__`+`__vtemp__`の合算、バックエンドに単一グループでの合算フィルタが無いため2回フェッチしてマージ)に加え、両グループの個別選択・Plan別サブグループ選択も追加。Galleryタブ側には`__vtemp__`用の🔒予約表示(`__Feeder__`と同様リネーム・削除不可)と、詳細パネルに`__vtemp__`をワンクリックでクリアする「VtC」ボタン(既存の`__Feeder__`用「FC」ボタンと同じ`groups/{name}/clear`APIを利用)を追加した。
|
||||
|
||||
**4. UIレイアウトの複数回反復**: 初回実装は左サイドバー(380px固定幅)にPlan/Asset/Editの3サブタブを縦積みする構成にしたが、実機確認で「Timeline+First/Last画像+Promptを横並びにしたい」という要望とレイアウト崩れの報告を受け、Planタブの中身を中央の広いプレビュー欄の下部に移動(ブロックエディタをFirst Image/Last Image/Prompt/Duration+colorスウォッチの横並び4カラムに再設計、実行系(Run/Pause/Cancel/進捗/Seed)とプラン管理系(Note/Save/Load)を「Run」「Plan」の2タブに整理)。続けて「これをPlanタブ化してEditタブを追加、左ペインのPlan/Editは削除」との指示で、中央パネルにPlan/Edit専用のタブナビを新設し、左サイドバーにはAssetのみを残した。この際、両タブナビが同じ`.wfm-video-subtab-btn`/`.wfm-video-subtab-panel`クラスを共有する実装だったため「Assetを選ぶと中央のPlan/Editも連動して消える」という不具合が発生 — 中央タブの切替処理を`.wfm-video-center-panel`スコープに限定したquerySelectorAllに変更し、サイドバーのAsset単独ボタンは独立したshow/hideトグルとして分離することで解消した。中央・右ペイン(プレビュー、Frame抽出/GIF変換/Video Source)はサブタブ切替と独立した常時表示パネルとして、レイアウト変更を通じて無改修のまま維持している。
|
||||
|
||||
**5. バグ修正: Galleryのグループ追加がジャンクションフォルダ環境で一覧に反映されない**: 「生成完了後に`__vtemp__`グループには入らない。Galleryで手動追加したコンテンツは表示される」との報告を受けた調査で発見。ユーザー環境の`ComfyUI_5\output`はStabilityMatrixの共有出力フォルダ機能によるWindowsジャンクション(実体は`StabilityMatrix\Images\Text2Img`)だった。`save_image_meta`(タグ/メモ保存)には既に「`get_image_metadata()`側はresolve()済みパスをキーにするため保存側も統一する」という同種バグの修正コメントがあったが、`add_to_group`/`remove_from_group`/`toggle_favorite`/`bulk_set_favorite`の4箇所には同じ修正が未適用のまま残っていた。そのためグループ追加自体はサーバー上で成功する(ジャンクション形式の未解決パスをキーに保存)が、一覧取得(`list_images`)はフォルダを`.resolve()`した実パスでスキャンするためキーが一致せず、「追加はされるが一覧に出てこない」というサイレント不具合になっていた。4箇所とも`save_image_meta`と同じresolve()統一パターンに修正。Video機能に限らずGallery全体(お気に入り・グループ機能)に影響していた既存バグで、今回の調査で偶然発見・修正できた。
|
||||
|
||||
**6. バグ修正: Galleryのグループフィルタがサブフォルダ内のファイルを見つけられない**: 5の修正後も「rootで`__VideoAssets__`フィルタ時は画像のみ、動画は表示されない」との報告。動画は`video/`サブフォルダに保存されるが、Galleryタブの`loadImages()`はグループフィルタの有無に関わらず常に非再帰スキャン(現在のフォルダ直下のみ)だったため、グループメンバーがサブフォルダにあると机上から漏れていた。グループフィルタが有効な時のみ`recursive=true`を付与するよう修正。
|
||||
|
||||
**7. バグ修正: チェイン画像が無関係な既存ファイルにすり替わる**: 「2ブロックのPlanで2つ目のFirst Imageを前ブロックの最終フレームに設定したが、生成された2つ目の動画は無関係な画像が使われている」との報告。調査の結果、`convertUiToApi()`(UI形式→API形式変換の共通処理)が持つ「COMBO項目の値がキャッシュ済み`/object_info`の選択肢に無い場合、無警告で選択肢の先頭に差し替える」というフォールバック機構(チェックポイント名の互換性対応が主目的で元々存在)が原因と判明。LoadImageノードの「image」もCOMBO型のため対象になり、バッチ実行中にアップロードした抽出フレーム画像のファイル名はその時点でキャッシュ済みの`/object_info`にまだ存在せず、無関係な既存ファイル(選択肢の先頭)に差し替えられていた。LabタブのchainImage機能がこの問題に遭遇しないのは、Labが既にAPI形式のワークフローを直接操作し`convertUiToApi()`を経由しないため。`comfyui-workflow.js`に`invalidateObjectInfoCache()`を新設し、チェイン用フレーム・ユーザーの手動画像アップロードの直後に呼んで次回変換時に最新の`/object_info`を再取得させるよう修正した。
|
||||
|
||||
**8. バグ修正: `__VideoAssets__`グループが再起動後に一覧・詳細パネルから消える**: 「再起動してギャラリーを確認したがグループに`__VideoAssets__`、`__vtemp__`が表示されなくなった」との報告。`gallery_metadata.json`を実データで直接確認したところ、`__vtemp__`はレジストリ・10件のメンバーシップとも正常だった一方、`__VideoAssets__`はグループレジストリ配列からも全画像のメンバーシップからも完全に消えていた(`delete_group()`はレジストリと全画像の`groups`配列を同時に消す実装で、症状と完全に一致)。原因は`__vtemp__`/`VideoPlan:<name>`と異なり、`__VideoAssets__`はバッチ実行側から`ensure_group`を呼ぶコードが一切無い設計だったこと — 3番で予約グループ保護(🔒表示・削除ボタン無効化)を追加する**前**の時点でManage Groupsから削除操作が可能だったため、その時点で削除され、以後`add_to_group`は個別画像への書き込みは成功してもレジストリを再登録しないため二度と一覧に出てこなくなっていた。`gallery-tab.js`に`ensureFeederGroup()`と同型の`ensureVideoGroup()`を新設し、VideoタブのAssetタブ初期化のたびに`__VideoAssets__`を確実に再登録するよう修正。削除時に失われた過去のメンバーシップ自体(開発中のテスト動画)はバックアップが無く復元不可能である旨をユーザーに報告した(このensure漏れが後に13番の伏線になる — `__VideoAssets__`側だけ直し`__vtemp__`側のensureが漏れていた)。
|
||||
|
||||
**9. Assetタブに保存済みPlan一覧を表示する「Project」サブタブを追加**: 「AssetタブにVideo Planを表示したい」との要望を起点に着手。何を指すか確認したところ「右ペインにプロジェクトタブを追加し、保存済み一覧、各動画のplan名表示としたい」との回答。調査の結果、バックエンドには`GET /api/wfm/video/plans`一覧APIと`/wfm_data/video_plan/{name}.png`サムネイル配信が2番のPlan永続化実装時から既に存在していたが、フロントエンドからは一度も呼ばれておらず丸ごと未使用のまま埋まっていたことが判明した。新規`video-project-tab.js`で保存済みPlan一覧(サムネイル・名前・ブロック数・更新日時)表示、クリックでのPlanエディタ読み込み(`video-plan-tab.js`に`openSavedVideoPlan()`をexport)、削除機能を実装し、Assetカードには生成元のPlan名をバッジ表示する機能(`img.groups`から`VideoPlan:<name>`グループを逆引き)も合わせて追加した。当初の指示通り右ペイン(Frame/GIFタブの隣)に実装したが、直後のフィードバックで「左ペインに変更したい」との指示を受け、左サイドバー(Assetタブの隣)へ丸ごと再配置した。この移動に伴い、左サイドバーのトグルロジックを「Assetボタン単体のshow/hide」から「クリックした方を開き他方を閉じる、同じボタンの再クリックで両方とも折りたたむ」という排他的トグルに拡張した。
|
||||
|
||||
**10. 中央下部のワークフロー名表示行を1行に統合**: 「Open Workflowボタン行を上段の現在読み込んでいるワークフロー名行と1行にしたい」との要望。`wfm-video-wf-name`(現在ロード中のワークフロー名)と`wfm-video-plan-workflow-row`(Planに記録されたワークフロー名+Open Workflowボタン)が縦に2行表示されていたのを、`.wfm-video-wf-row`という横並びflexコンテナでまとめ1行に統合した。
|
||||
|
||||
**11. ワークフロー設定可能項目ハイライト表示の復活**: 「以前の単発生成フォーム時の設定項目のハイライト表示を行いたい」との要望を受けて調査したところ、v0.5.4で一度実装されていた機能(`wfm-model-label-active`クラス、GenerateUI Modelタブと共通の設定色)が、4番のPlan/Asset/Edit再設計で単発フォームのコードごと失われ、ヘルプ文言だけが取り残されていたことが判明した。Planタブのブロックエディタ向けに`_updateFieldHighlights()`を再実装:Prompt/Duration/First Image/Last Image/Aspect Ratio/Megapixels/Multipleの各ラベルにIDを付与し、読み込んだワークフローが実際にそのフィールドをサポートしている場合のみハイライトする(Wan2.2のようにResolutionSelectorが無いワークフローではAspect Ratio/Megapixels/Multipleは非ハイライトのまま)。ワークフローロード時・Open Workflowボタン使用時・ブロック切り替え時(`_renderBlockEditor()`はブロック選択のたびにDOMを作り直すため都度再適用が必要)のいずれでも正しく再適用されるようにし、ハイライト色を注入するCSSセレクタ(`settings-tab.js`の`applyModelTabActiveColor()`)も旧レイアウトの`.wfm-video-form-panel`から新レイアウトの`.wfm-video-plan-content`に更新した(4番のレイアウト変更で参照先の無いセレクタになっていた)。この過程で、ヘルプ本文(`helpVideo8`)がHTML側とi18n.js側で別内容になっている既存の不整合(HTML側は旧ハイライト説明、i18n.js側はチェイン機能の説明で後者が実際に表示される)を発見し、ハイライト説明を新規`helpVideo10`として追加し直した。
|
||||
|
||||
**12. Video Assets/Video Tempグループの命名統一・自動登録の運用整理**: 「__vtempグループが消えてしまっている」という報告と、ユーザー自身による修正方針の提示(表示名をグループ名で統一、VideoPlan:自動登録を廃止し常にVideo Tempへ、VtCボタン名を「Clear __Video Temp__」に変更)を受けて実施。3番/8番で導入した`__VideoAssets__`/`__vtemp__`を`__Video Assets__`/`__Video Temp__`に改名し、Assetタブの表示名もグループ名からそのまま導出する形に統一(「Temporary (unsaved runs)」という独自表示名は廃止)。3番の「Plan保存済みなら`VideoPlan:<name>`サブグループへ」という自動振り分けは廃止し、Plan保存の有無に関わらず常に`__Video Temp__`へ登録するよう変更 — `__Video Assets__`への整理は完全にユーザー任意のタイミングに委ねる設計に転換した。対応してAssetタブの「VideoPlan:」動的取得・フィルタ表示ロジックと、9番で追加したAssetカードへのPlan名バッジ表示も、対応するグループ自体が無くなったため削除した。バックエンド予約グループリスト(`py/routes/gallery_routes.py`の`_RESERVED_GROUPS`)も新グループ名に追従させている。既存の`VideoPlan:`グループ自体はユーザー側で削除する前提で進めた。
|
||||
|
||||
**13. 重大バグ修正: `gallery_metadata.json`の非アトミック書き込みによるデータ消失(根本原因)**: 「再起動するとグループに登録した内容が消えます」との報告を受けた調査。まず8番の`ensureVideoGroup()`が実は`__VideoAssets__`(現`__Video Assets__`)しかensureしておらず`__vtemp__`(現`__Video Temp__`)はensureしていなかったという見落としを修正したが、実データ(`user/default/Workflow-Studio/gallery_metadata.json`、画像9,470件)を直接調べたところ、より深刻な問題が見つかった。`GalleryMetadataStore._save_to_disk()`が`open(path, "w")`による直接上書きの非アトミック書き込みで、バックグラウンドインデックス処理(`_bg_index_folder`、未キャッシュ画像10枚ごとに保存)が大量画像フォルダに対して極めて高頻度にこのファイルへ書き込み続けていた(実測でファイルサイズが0.5秒間隔で数百KB単位で変動し、外部プロセスから読むとタイミングによってJSONパースが失敗する状態だった)。この書き込みの最中にComfyUIプロセスが終了すると、ファイルが不完全なJSONのまま残り、次回起動時の`_load()`がパースに失敗して警告ログを出すだけで中身を空の`{"images": {}, "groups": []}`にリセットしてしまう — 以降1回でも保存が走ると、それまでの全グループ登録・タグ・メモが跡形もなく上書きされて消える、という構造だった。実際に確認したところ、グループの登録リスト自体(`__Feeder__`/`__Video Assets__`/`__Video Temp__`等)は残っていたが、動画がどのグループに属しているかという個々のメンバーシップ情報は失われていた。`_save_to_disk()`を一時ファイル書き込み+`Path.replace()`によるアトミックな置き換えに変更し、`_load()`がJSON破損を検出した場合は単に空データにするのではなく`.corrupt`ファイルとしてバックアップしてから起動するよう変更した(今後同様の事態が起きても手動復旧の余地を残す)。単体テスト(アトミック書き込み・破損時バックアップ・復旧後の再保存)で動作確認。今回失われた登録内容自体はバックアップが無く復元不可能である旨をユーザーに報告した。
|
||||
|
||||
**14. 中央プレビューの2ペイン化**: 手描きの構成図での要望「動画ソース・ファイルドロップエリアを左端に移動、プレビューを2つにして左はアセットの選択動画/ドロップされた動画のプレビュー兼用、右は生成された動画のプレビュー用」を実装。従来は単一のプレビュー(Video Sourceドロップの表示専用で、Assetタブの選択動画やPlan実行結果を自動表示する仕組み自体がそもそも存在しなかった)だったのを、3カラム構成(左: Video Sourceフォーム、中央: Asset選択/Sourceドロップ兼用プレビュー、右: 生成動画専用プレビュー、いずれも新規実装)に再構成した。`video-tab.js`・`video-asset-tab.js`(Asset選択)・`video-plan-tab.js`(バッチ実行結果)の3ファイルがプレビュー状態を共有する必要があったため、新規`video-preview.js`という共有モジュールに切り出した(video-tab.jsが既に他の2ファイルをimportしているため、逆方向のimportを追加すると循環参照になることを回避するため)。Frame/GIFツールは「直近にアクティブになった方のプレビュー」を対象に動作する設計にした。Asset選択時はGalleryの絶対パスをComfyUIのfilename/subfolder/type形式に変換する手間を避けるため、動画をBlobとしてfetchし「ローカルファイル」として扱うことで、GIF変換の既存アップロードロジックをそのまま流用できるようにした。Assetサイドバーの詳細パネルにあった動画プレビュー(`<video>`要素)は、中央プレビューに統合されたため削除した。
|
||||
|
||||
**15. ヘルプの整合性チェック**: リリース前の最終確認としてVideo Tabヘルプ全11項目(Title/Desc/1〜10)をHTML・i18n.js(3言語)・app.jsのhelpIdMapで突き合わせ、11番で発見した`helpVideo8`の不整合以外にも、`helpVideoDesc`(旧「Plan / Asset / Edit」の一括り記述が9番以降のサイドバー分離構造と食い違っていた)と`helpVideo1`/`helpVideo2`/`helpVideo3`(HTML側が旧単発フォーム時代の文言のまま放置され、実際に表示されるi18n.js側の内容と長年食い違っていた)を発見・修正した。README.mdのVideo Tabセクションも同様に、4番のPlan/Asset/Edit再設計自体が一切反映されないまま単発フォーム時代の説明で放置されていたことが判明し、9〜14番までの内容を反映して全面的に書き直した。
|
||||
|
||||
**16. `pyproject.toml`のlicense記述をComfy Registry仕様準拠の形式に修正**: リリース準備の一環で、`license = "MIT"`という単純文字列形式が、公式仕様(`license = {file = "LICENSE"}`または`{text = "..."}`のいずれか)に該当しない非推奨形式であり、`comfy env`実行時にcomfy-cliが警告を出していたことを確認した([[project_registry_flagged_versions]]で追跡しているv0.5.0〜v0.5.3の原因不明のFlagged/Pending状態の調査依頼を受けて着手)。合わせて、参照先の`LICENSE`ファイル自体がリポジトリに存在しなかった(README.mdの「MIT License」という一文のみ)ため新規作成し、`license = { file = "LICENSE" }`に修正した。調査の結果、Comfy Registryのセキュリティスキャンは主にAI+静的解析(Ruff)によるPythonコード内の危険なパターン検出(`eval`/`exec`/`subprocess`/`pickle.loads`/カスタムpip wheel等)が対象で、`pyproject.toml`のメタデータ自体(license記述含む)がスキャン対象になるという情報は見つからなかった — つまり今回の修正はComfy Registryの公式仕様に沿った改善ではあるが、Flagged/Banned問題の直接的な解決策である確証はない。一方で、他の開発者(GitHub issue経由)でも同様の原因不明なFlaggedステータスが複数報告されており、pyproject.tomlの記述とは無関係にRegistry側の自動スキャンが誤検知(false positive)を起こしている可能性が高いことが分かった。具体例として、外部バイナリをsubprocessで呼び出す正当なコード(GraphicsMagick連携)が誤検知された報告があり、本プロジェクトにも同種のパターン(`gmic_routes.py`の`subprocess.Popen`+Windows固有の`CREATE_NEW_CONSOLE`フラグ、`wildcard_service.py`の`["cmd", "/c", "mklink", ...]`)が存在するため、これらが誤検知の一因になっている可能性はあるが確証はない(いずれも正当な機能で、変更は行っていない)。
|
||||
|
||||
**検証**: 全JS/Pythonファイルを`node --check`/`python -m py_compile`で構文確認、`templates/index.html`はPythonの`html.parser`でタグ対応チェックとJinja2実レンダリングで検証。ジャンクションバグの調査・検証は、ユーザーが起動中のComfyUI_5(ポート8189で稼働)に対し`curl`でAPIを直接叩いて実施 — `os.path.realpath()`で実際にジャンクションであることを確認し、`groups/{name}/images`(生成成功)と`list_images`(グループフィルタで空)の食い違いを再現、修正版デプロイ後の再検証はユーザー自身の実機確認で完了。8番の`__VideoAssets__`消失バグは、実行中サーバーの`gallery_metadata.json`を直接読み込んで原因を特定した(読み取り中にサーバー側の`_save_to_disk()`と競合しJSONDecodeErrorになることがあったため、パース成功するまで数回リトライして実データを確認)。13番の根本原因調査では、同じファイルへの読み取りを連続実行してもファイルサイズと成否が毎回変わることを確認し、実データが継続的に高頻度書き込みされている実態そのものを証拠として特定に用いた。13番の修正自体は`tempfile`を使った独立テストスクリプトで正常保存・再ロード後のデータ保持・破損ファイル検出時のバックアップ・復旧後の再保存を単体検証(ComfyUI起動不要)。開発元gitリポジトリと実行時`custom_nodes`フォルダは別実体のため([[project_dev_deploy_sync]]参照)、変更・新規ファイルを都度両フォルダへ同期しCRLF/LF差異を除いた`diff`で完全一致を確認、Python変更(13番・12番の`gallery_routes.py`予約グループリスト)を含む回では実行時側の`__pycache__`もクリアした。各段階(レイアウト・Projectサブタブ追加・ハイライト復活・グループ運用整理・データ消失バグ・プレビュー2ペイン化・ヘルプ整合性)ともユーザー自身の実機確認・スクリーンショットや手描き構成図の提供を受けて次の修正に進む反復的な進め方で実施した。16番のRegistry仕様調査はWeb検索でComfy公式ドキュメント(`docs.comfy.org/registry/specifications`)とGitHub issue(Comfy-Org/ComfyUI-Manager #2927, #2997)を確認し、`pyproject.toml`の`license = { file = "LICENSE" }`変更後は`toml`パッケージでパース可能なことを確認した。
|
||||
|
||||
**How to apply**: 「◯◯機能では動くのに△△機能では動かない」という報告があった場合、両者の実行経路が本当に同じか(今回はLabがAPI形式を直接操作するのに対しVideoはUI形式から`convertUiToApi()`を経由する、という違い)を疑うと真因に早く到達できる。ComfyUIフロントエンドの`convertUiToApi()`のようなCOMBO値検証は「無警告でのフォールバック」を行う設計になっている場合があるため、実行時に動的アップロードした値をCOMBO項目に書き込む機能(画像チェイン等)を追加する際は、そのCOMBOの選択肢キャッシュが最新かどうかを必ず確認する必要がある。StabilityMatrixのような複数ComfyUIインスタンスでモデル/出力フォルダを共有するツールはジャンクション/シンボリックリンクを使うため、`Path.resolve()`をパスキーの一部に使うコードとファイルシステムスキャンで得たパスとの間に「解決する/しない」の不一致が生まれやすい — 同じ画像を指すパス文字列の保存/検索が全経路で一貫した規約(このプロジェクトでは「常にresolve()後の文字列で統一」)に従っているか、新しい書き込み経路を追加するたびに確認する価値がある。複数のタブ切替グループが同じCSSクラス/data属性を共有する実装は、後から片方だけ物理的に別の場所へ移動すると意図せず連動してしまうため、独立させたいグループは早い段階でクラス名やquerySelectorAllのスコープを分けておくとよい。予約グループ(`__Feeder__`のような「削除されると誰も自動で作り直さない」特別なグループ)を新設する際は、保護(削除禁止)の実装と同時に「常に存在することを保証する`ensure`呼び出し」もセットで用意しないと、保護を追加する前の空白期間や手違いで一度消えた場合に二度と復活しない — この2つは別々の対策であり、片方だけでは不十分。実行中サーバーが継続的に書き込んでいるJSONファイルを外部から直接読んで調査する際は、書き込みと衝突して不完全な内容を読んでしまうことがあるため、パースが安定して成功するまでリトライするのが安全。JSON等の設定/メタデータファイルへの永続化処理を新規実装・レビューする際は、単純な`open(path, "w")`による直接上書きになっていないか必ず確認する — 書き込み頻度が低いうちは問題が表面化しなくても、対象データ量が増えて書き込み回数が増えるほど「書き込み中のプロセス終了でファイルが壊れる」リスクが顕在化しやすく、かつ壊れたファイルのロード失敗を「空データにフォールバック」で処理していると、その後の1回の保存で過去の全データが消えるという最悪の組み合わせになる(一時ファイル+`Path.replace()`のアトミック置き換えと、破損検出時のバックアップ退避はセットで対策する)。UI再設計でコードごと削除した機能(今回のハイライト表示)は、対応するヘルプ文言だけが取り残されて「存在しない機能の説明」として残り続けることがあるため、大きめのUI再設計を行った際はヘルプ文言側の棚卸しも忘れずに行う。ユーザー向けドキュメント(README等)は実装が大きく変わった直後に更新を忘れると、次に触るまで長期間ズレたまま放置されやすい — 大規模なUI再設計コミットを作る際は、その場でREADMEの該当セクションも一緒に更新するのが安全(今回はPlan/Asset/Edit再設計そのものが数バージョン分READMEに未反映のまま残っていた)。
|
||||
|
||||
関連: [[project_v050_video_tab]], [[project_dev_deploy_sync]]
|
||||
|
||||
---
|
||||
|
||||
## v0.5.4
|
||||
|
||||
### 機能追加: Video/GenerateUIタブのLTX-2.5・Wan2.2対応拡大 + AI Assistant設定のUnsloth対応・独立モーダル化・モデルアンロード機能
|
||||
|
||||
複数セッションにまたがり実施された作業をまとめてリリース。Videoタブが従来MiniMax H3専用だった検出/生成ロジックをLTX-2.5・Wan2.2にも対応させ、続けて生成UIタブ側の解析ロジックにも同じ2ファミリーへの対応を追加した。並行してAI Assistant設定(Prompt/Tagger)をUnslothバックエンド対応・タブ別モーダル化・モデルアンロード機能へ刷新した。
|
||||
|
||||
**1. Videoタブ: LTX-2.5 / Wan2.2対応(ノード検出の汎用化)**: 従来MiniMax H3専用だったサブグラフ検出/フォーム反映ロジックを、サブグラフが公開する入力のlabel(無ければname)ベースで意味的にスロットを特定する方式に一般化した。MiniMax H3/LTX-2.5系は内部ノード型のプレフィックス(`LTXV*`等)で、Wan2.2は該当する固有ノード型を持たないためサブグラフ名自体("...(Wan2.2)"表記)で家系を判定する。これによりVideoタブの「Load in Video」からLTX-2.5のText/Image/First&Last-Frame to VideoワークフローとWan2.2のText to Videoワークフローも読み込み・生成できるようになった。同梱していない`minimax_test.json`の自動読み込みも廃止。
|
||||
|
||||
**2. バグ修正: convertUiToApi()のMultiTypeウィジェット脱落**: object_infoが複合型(例: `LTXVEmptyLatentAudio.frame_rate: "FLOAT,INT"`)を宣言している入力が、単純な完全一致判定(`upper === "INT" || ...`)に引っかからずウィジェット名/型リストから丸ごと脱落し、後続ウィジェットの値が1つずつずれる問題を発見・修正した。実際に`LTXVEmptyLatentAudio.batch_size`にframe_rateの値が誤って書き込まれ、動画生成が"Expected size 1 but got size 25"で失敗する原因になっていた。`_resolveWidgetType()`を新設し、カンマ区切りの型宣言から実際にウィジェットスロットを占める単一のスカラー型を解決するよう修正。
|
||||
|
||||
**3. 動画再生ボリュームの保存設定**: 動画を切り替えるたびに音量が最大へ戻ってしまう問題を解消するため、設定タブに音量設定を追加しVideo/Galleryタブの全プレーヤー間で保存・共有されるようにした。
|
||||
|
||||
**4. GenerateUIタブ: LTX-2.5 / Wan2.2対応(プロンプト検出・Latent Image・タイムアウト)**: Videoタブとは独立した解析経路(`analyzeWorkflow()`、フラット化済みAPI形式ワークフローを解析)側でも同じ2ファミリーの通常ワークフロー読み込みに対応させる作業。実機確認したところ、Model タブ(Checkpoint/VAE/Diffusion Model/Text Encoder/LoRA)は既存の`UNETLoader`/`CLIPLoader`/`VAELoader`ベースの汎用検出でWan2.2/LTX-2.5とも既に問題なく動作していたが、次の2点に不備を発見した。
|
||||
- **Positive/Negative Prompt検出(LTX-2.5)**: LTX-2.5は`LTXVDualCFGGuider`(positive/negativeが同一の`LTXVConditioning`ノードの別出力スロットを指す)+ `LTXVConditioning`(自身のpositive/negative入力を介して実際のプロンプトソースへ分岐)という専用ノード構成を使うため、既存の`CFGGuider`/`InstructPixToPixConditioning`向けロール伝播ロジックでは拾えず、Positive/Negative Promptが空欄のままSaveVideoノードへのフォールバック表示になっていた。`LTXVDualCFGGuider`をロール伝播の起点に、`LTXVConditioning`を`InstructPixToPixConditioning`と同型の分岐伝播ノードとして追加し解決した。
|
||||
- **Latent Image検出(Wan2.2・LTX-2.5共通)**: SettingsタブのLatent Imageセクションが`EmptyLatentImage`/`EmptySD3LatentImage`/`EmptyFlux2LatentImage`のみ対応しており、Wan2.2の`EmptyHunyuanLatentVideo`とLTX-2.5の`EmptyLTXVLatentVideo`が未対応で「No EmptyLatentImage node found」表示になっていた。両ノード型を追加し、動画特有の`length`(フレーム数)入力を編集するフィールドも新設した(Duration×FPSの数式ノードにリンクされ非リテラルなことが多いため、Width/Height同様「linked」表示にフォールバックする)。
|
||||
- あわせて`isVideoWorkflow()`(生成タイムアウトを30分に延長する判定)を、`SaveVideo`/`CreateVideo`ノードや動画用latentノードの存在でも判定できるよう拡張した。従来はMiniMax H3のようなオールインワン`*ToVideo`ノードの有無でしか判定できず、LTX-2.5/Wan2.2は通常の静止画と同じ短いタイムアウトで打ち切られる恐れがあった。
|
||||
|
||||
**5. Videoタブ左パネルのハイライト表示**: GenerateUIのModelタブが持つ「ワークフローに実際に該当する項目のラベルをハイライト」する仕組み(`wfm-model-label-active`クラス、設定タブでカスタマイズ可能な共通色)をVideoタブの左パネルにも適用した。Prompt/Durationは常時、First Frame/Last Frameはサブグラフがそのスロットを公開している場合のみ、Aspect Ratio/Megapixels/MultipleはResolutionSelectorノードが存在する場合のみハイライトする — Wan2.2のように該当ノードがなく操作不可(disabled)な項目は、既存の無効化表示と矛盾しないよう非ハイライトのままにした。
|
||||
|
||||
**6. バグ修正: 生成UIタブRAW JSON検索がヒット箇所にカーソルを当てて不意に編集させてしまう**: 検索でヒットした際に`editor.focus()` + `setSelectionRange()`でテキストエリアへフォーカス・選択範囲を作っていたため、検索直後にキー入力すると選択範囲が上書きされ意図せずJSONが書き換わってしまう問題があった。ハイライト表示(`<mark>`によるオーバーレイ)とスクロール追従は維持しつつ、フォーカス移動と選択状態の作成のみを取りやめ、編集はユーザーが明示的にエディタをクリックした場合のみに限定した。
|
||||
|
||||
**7. AI Assistant設定: Unsloth対応・Prompt/Tagger独立モーダル化・モデルアンロード機能**: Prompt AI(Prompt タブ)とTagger VLM(Taggerタブ)にUnslothバックエンドを追加した(サーバー側プロキシでAPIキーを付与)。Taggerタブは従来Ollama直呼び出しだった実装を、Ollama/LM Studio/Lemonade/Unslothの4バックエンド共通の`vlm_models`/`vlm_predict`エンドポイントに統一し、API URL直接入力欄を廃止した。中央Settingsタブにあった単一の「AI Assistant Settings」パネルを廃止し、Prompt/Tagger各タブに⚙設定ボタン+専用モーダル(`ai-settings-modal.js`、Backend/Connection/Model/Generation/Unload/Saveの共通UIコンポーネント)を新設、それぞれ独立した`localStorage`キーで設定を持つように変更した(PromptとTaggerで異なるバックエンド/モデルを使い分けられる)。Thinking mode / Max tokensの設定をPrompt/Tagger双方の生成呼び出しに反映(Tagger側はPython側の`vlm_predict`にも反映)。Ollama(`keep_alive:0`)/LM Studio(`/api/v1/models/unload`)/Lemonade(`/api/v1/unload`)向けのモデルアンロード機能を追加し、AI TOOLタブの設定にもUnloadボタンを追加した(Unslothは対応する公式APIが無いため非対応として明示)。
|
||||
|
||||
**8. CI: publish-node-actionのバージョンをSHA固定**: `Comfy-Org/publish-node-action@main`という可変ブランチ参照は、アクション側が更新された際に挙動が変わりうるサプライチェーンリスクのため、リリースタグ1.0.1のコミットSHAに固定するよう`.github/workflows/publish.yml`を修正した([[project_registry_flagged_versions]]で追跡している過去のRegistry Banned/Flagged原因調査の一環)。
|
||||
|
||||
**ヘルプ・README更新**: `project_v0336_conventions`の慣習(index.html + i18n.js 3言語 + app.jsのhelpIdMapの3点セット)に従い、GenerateUIタブ(LTX-2.5/Wan2.2対応・RAW JSON検索の挙動)とVideoタブ(ハイライト色機能)のヘルプ本文を英語・日本語・中国語の3言語で追加・更新した(Prompt/Settings/AI TOOL/Taggerタブのヘルプは7番の対応セッション内で既に更新済み)。README.mdはWorkflowタブ(Load in Video対象の拡大)、GenerateUIタブ(MultiTypeバグ修正・LTX-2.5/Wan2.2対応)、Videoタブ(対応ファミリー拡大・ハイライト色・音量設定・見出しバージョン範囲更新)、Settingsタブ(AI Assistant Settings廃止の案内・音量設定・ハイライト色の共有先追記)、Prompt/Taggerタブ(AI Assistant設定のモーダル化・マルチバックエンド化)、AI TOOLタブ(モデルアンロード機能)を更新した。
|
||||
|
||||
**検証**: 全JS/Pythonファイルを`node --check`/`ast.parse()`で構文確認。GenerateUIタブのLTX-2.5/Wan2.2対応は、実機ブラウザ(Kapture)でwan22_test.json / ltx_25_test.jsonの2ワークフローを実際に生成UIタブへ読み込み、Positive/Negative Promptの実文表示・Latent Image欄(Width/Height/Batch Size/Length)の表示・ハイライト色の点灯状態をスクリーンショットで確認した。RAW JSON検索のフォーカス修正は、検索実行後にキー入力してもtextareaの値が変化しないことを実機で確認した。開発元gitリポジトリと実行時`custom_nodes`フォルダは別実体のため([[project_dev_deploy_sync]]参照)、変更ファイルを都度両フォルダへ同期しCRLF/LF差異を除いた`diff`で完全一致を確認した。
|
||||
|
||||
**How to apply**: `analyzeWorkflow()`のような中央解析関数はワークフロー「ファミリー」が増えるたびに、既存パターン(KSampler系のロール伝播、EmptyLatentImage系のlatentノード検出)と同型の分岐を追加していく設計で拡張できる — 逆に言えば、新しいノード構成(今回のLTXVDualCFGGuider/LTXVConditioningのような「複数出力を持つ1ノードがpositive/negativeを兼ねる」パターン)は`InstructPixToPixConditioning`のような既存の同型ケースを探して倣うと実装が速い。同じワークフローファミリーへの対応が複数タブ(Video/GenerateUI)にまたがる場合、検出ロジック自体は各タブの解析経路(Video: サブグラフを直接歩く、GenerateUI: フラット化済みAPI形式を解析)が別実装なので、片方を直しても他方は直らない — 「Videoタブでは動くのにGenerateUIでは動かない」という状況は、まさにこの二重実装のズレが原因だった。テキストエリアへの自動フォーカス/selectionRangeは、検索・ハイライトのような「見せるだけ」の操作と「編集を許可する」操作を暗黙に混同させるため、ハイライト表示に徹する機能ではフォーカス移動自体を避けるのが安全。
|
||||
|
||||
関連: [[project_v050_video_tab]], [[project_dev_deploy_sync]], [[project_v0336_conventions]], [[project_registry_flagged_versions]]
|
||||
|
||||
---
|
||||
|
||||
## v0.5.3
|
||||
|
||||
### バグ修正: Labタブのワークフロー切替時に前の内容が残留 + Galleryタブの読み込み高速化・root自動展開 + READMEスクリーンショット刷新
|
||||
|
||||
ユーザーからの複数のバグ報告・改善要望を1セッションで順に対応した作業。
|
||||
|
||||
**1. バグ修正: Labタブで起動時デフォルトワークフロー読み込み後に別ワークフローを読み込むと前の内容が残る**: 「別のワークフローを読み込んだ。一部以前のワークフローの内容が残ったまま表示される(クリックするか他のタブから戻ると消える)」との報告。Labタブの「Setting 1」列(Checkpoint/LoRA/VAE/Prompt/KSampler)はGenerateUIの現在の読み込み内容をライブ反映する仕組みだが、その再描画(`refreshLabLiveDefaults()`)は「サブタブをLabに切り替えたとき」の一箇所(`generate-tab.js`のサブタブクリックハンドラ)でしかトリガーされていなかった。Labタブを既に開いた状態で別のワークフローを読み込んだ場合、`loadWorkflowIntoEditor()`側では再描画が一切呼ばれず、前のワークフローの表示がそのまま残っていた。「セルをクリックしたり他のタブから戻ると直る」という報告内容は、それらの操作がたまたま再描画をトリガーしていたことの裏返しだった。`loadWorkflowIntoEditor()`の末尾で、現在アクティブなサブタブがLabの場合は`refreshLabLiveDefaults()`を追加で呼ぶよう修正。
|
||||
|
||||
**2. 改善: Galleryタブの生成後の更新が遅い**: 「生成後の画像表示に更新して読み直すのに時間がかかる」との報告。実データ(Output先の`Text2Img`フォルダ、画像9,777枚)で`_scan_folder()`を実測したところ**7.5秒**かかっており、原因を切り分けたところ`entry.stat(follow_symlinks=True)`と、各ファイルごとに呼んでいた`Path(entry.path).resolve()`の2箇所がボトルネックと判明。特に`resolve()`の再解決が支配的で、これだけで1ファイルあたり約0.7ms×9,777件のファイルシステム往復が発生していた。`_scan_folder()`の呼び出し元(`list_images()`/`_bg_index_folder()`)は既にフォルダ自体を`Path(folder_path).resolve()`済みで渡しているため、`entry.path`は既に絶対パスであり、エントリ単位での再`resolve()`は不要だった。`entry.is_file()`/`entry.stat()`を`follow_symlinks=False`に変更し、パス生成も`entry.path.replace("\\", "/")`に簡略化(出力フォルダにシンボリックリンクの画像が置かれる想定はないため安全と判断)。同じ理由で`os.walk()`ベースだった`_scan_folder_recursive()`(ImagePrompt/Style Catalog用の再帰スキャン)も、`os.scandir()`を自前で再帰しDirEntryベースでstatする実装に書き換えた。実測で9,777枚のフォルダに対する`list_images()`全体が0.14秒(コールド)/0.08秒(フォルダキャッシュ温存時)まで短縮(約50倍高速化)。
|
||||
|
||||
**3. 改善: Galleryフォルダツリーのrootをデフォルト展開状態に**: 上記の高速化を受けて「rootフォルダはデフォルトで展開状態で表示したい」との要望。フォルダスキャンが軽くなったことでサブフォルダの内容もすぐ確認できるようになった一方、`renderTreeNode()`はrootも他のノードと同じく初期状態は折りたたみ(▶)だったため気付きにくかった。root(`isRoot`)の場合のみ、ツリー構築時に矢印を展開済み(▼)にし子ノードを即座にレンダリングするよう`gallery-tab.js`を修正。
|
||||
|
||||
**4. READMEスクリーンショット刷新**: 「以下のスクリーンショットは削除したい」との依頼でGenUI Feeder / GenUI LoRA Stack / Models Multi-select Menu / Tagger Tab / Customizeの5件をREADME.mdの表と`docs/`実ファイルの両方から削除(残った項目は2列レイアウトに詰め直し)。続けてVideo Tab・Lab Tab(2枚)・AI TOOL Tabの新規スクリーンショット計4枚をユーザーが`docs/`に配置し、READMEの表に追加した。
|
||||
|
||||
**検証**: JS/Pythonとも`node --check`/`ast.parse()`で構文確認。Gallery高速化は開発元リポジトリの`GalleryService`を実データ(実際の`Text2Img`フォルダ、9,777枚)に対してvenv Pythonから直接呼び出し、修正前後の`_scan_folder()`/`list_images()`の実行時間をベンチマークして改善を数値で確認(7.5秒→0.063秒、`list_images()`全体は0.14秒)。返却されるパス文字列が修正前と同じ絶対パス形式であることも確認済み。開発元gitリポジトリと実行時`custom_nodes`フォルダは別実体のため([[project_dev_deploy_sync]]参照)、変更・削除した全ファイル(`generate-tab.js`, `gallery_service.py`, `gallery-tab.js`, `README.md`, `docs/`配下の画像)を都度両フォルダへ同期し`diff`/存在確認で完全一致を確認、Pythonファイル変更のため`__pycache__`もクリア。全項目ともユーザー自身の実機確認で解消・反映を確認済み。
|
||||
|
||||
**How to apply**: あるタブ/サブタブの表示を「別の場所(GenerateUI本体など)の現在の状態をライブ反映する」設計にする場合、再描画のトリガーを「そのタブへの切替」1箇所だけに置くと、切替を経由しない別の更新経路(今回はワークフロー読み込み)で表示が古いまま取り残される。ライブ反映される値の更新元(今回は`loadWorkflowIntoEditor()`)側でも、現在表示中のタブを見て能動的に再描画を呼ぶ必要がある。パフォーマンス調査では「体感で重い処理」を分解して各行を実測するまで真犯人を決め打ちしない方がよい — 今回も当初`follow_symlinks=True`のstat呼び出しを主因と想定したが、実測すると`Path.resolve()`の方が支配的だった。Windows上で大量ファイルを扱う`os.scandir()`ループでは、`entry.path`が既に呼び出し元でresolve済みのフォルダ配下の絶対パスであることを踏まえ、エントリ単位での`resolve()`/`follow_symlinks=True`はファイル数に比例した無視できないコストになり得るため避ける。バックエンドの表示速度を改善した際は、それに応じてフロントエンドのデフォルトUI状態(今回は折りたたみ初期状態)も見直す価値がある — 「遅いから畳んでおく」という妥協がボトルネック解消後も残ったままになりがち。
|
||||
|
||||
関連: [[project_dev_deploy_sync]]
|
||||
|
||||
---
|
||||
|
||||
## v0.5.2
|
||||
|
||||
### 機能追加: GenerateUI/Labタブの動画ワークフロー対応 + VideoタブにFrame抽出/GIF変換機能 + データ管理監査とZIPフルバックアップ + Send to LI node統一
|
||||
|
||||
@@ -0,0 +1,21 @@
|
||||
MIT License
|
||||
|
||||
Copyright (c) 2026 ketle-man
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
@@ -26,7 +26,7 @@ A comprehensive workflow, asset management, and generation UI plugin for [ComfyU
|
||||
- Built-in AI tools (translation and more)
|
||||
|
||||

|
||||

|
||||

|
||||
|
||||
## Features (tab -> feature names)
|
||||
|
||||
@@ -49,7 +49,7 @@ Setting / Results / Plan JSON sub-panels, Per-column keyframes, Model column —
|
||||
3-column layout, AI chat assistant, Image attachment, Translation, Prompt presets, Preset Manager, Group management, Clipboard copy, GenUI Set, Wildcard/Style tab bar, Wildcard input toolbar, Wildcard file manager, Style manager, Form / Table toggle, Table view — Presets / Presets Group / Wildcards / Style
|
||||
|
||||
### Settings Tab
|
||||
2-column layout, Collapsible sections, Theme selection, Theme customization, Workflows directory, Gallery output directory, Eagle connection, Ollama connection, CivitAI Host, CivitAI API Key, Default workflow, Default Checkpoint, Data Management, Text Size, RAW JSON Colors, GenerateUI Model Tab Highlight, Wildcard Integration, G'MIC-Qt Integration, Language
|
||||
2-column layout, Collapsible sections, Theme selection, Theme customization, Workflows directory, Gallery output directory, Eagle connection, CivitAI Host, CivitAI API Key, Default workflow, Default Checkpoint, Video Playback Volume, Data Management, Text Size, RAW JSON Colors, GenerateUI Model Tab Highlight, Wildcard Integration, G'MIC-Qt Integration, Language
|
||||
|
||||
### Gallery Tab (v0.3.44)
|
||||
Output / ImagePrompt / Style_Catalog / Metadata sub-tabs, Image browser, Folder tree root label, Thumbnail / Table views, Folder management, File operations, Download, MP4 video support, MP4 embedded metadata, Info tab: dimensions & duration, Multi-select, Image Compare, Prompt search, Server-side filtering, Group management, Thumbnail F button, Favorites, Detail panel, Prompt tab, Workflow viewer, GenUI button, Image Edit button, Send GenUI Image button, Send to LI node button, Send CC button, Search clear (✕), Clear all filters (✕ Clear), Workflow auto-save, Output folder configurable, SVG file support, Performance
|
||||
@@ -70,16 +70,16 @@ Node Browser, Search & Filter, Package badges, Node detail panel, Node Sets, Rig
|
||||
Model Browser, Thumbnail / Table views, Table column sort, Search & Filter, User-defined badges, Side panel tabs, CivitAI integration, CivitAI panel — Info / Sample sub-tabs, CivitAI panel states, Batch CivitAI fetch, Detail modal, GenUI Model button, Group management, Table view memo, Preview images, Enable / Disable models, Multi-select & bulk operations, Search clear (✕), Clear all filters (✕ Clear)
|
||||
|
||||
### Tagger Tab (v0.3.38)
|
||||
3 sub-tabs, Model support, Threshold sliders, Ollama VLM, Single tab, Single output options, Batch tab, DB tab, Dependencies
|
||||
3 sub-tabs, Model support, Threshold sliders, VLM tagging, Single tab, Single output options, Batch tab, DB tab, Dependencies
|
||||
|
||||
### Image Edit Tab (v0.3.65)
|
||||
Layer-based image editor, Loading images, New button, Tools, Layer panel, Layer lock, Text quality, Export, Canvas navigation, Undo / Redo
|
||||
|
||||
### Video Tab (v0.5.0 – v0.5.2)
|
||||
Dedicated MiniMax H3 video generation UI, independent of GenerateUI, 3-pane layout, First Frame / Last Frame are both optional, Node lookup instead of hardcoded IDs, Load in Video, Preview frame + Video Source panel, Frame tab, GIF tab
|
||||
### Video Tab (v0.5.0 – v0.5.7)
|
||||
Dedicated video generation UI, independent of GenerateUI, Plan / Edit subtabs, Base settings row, Asset / Project subtabs, Two center previews, First Frame / Last Frame are both optional, Semantic node lookup, not hardcoded IDs, Field highlight color, Load in Video, Frame tab, GIF tab, Playback volume
|
||||
|
||||
### AI TOOL Tab (v0.3.14)
|
||||
4-pane layout, Translation pane, Chat pane, Chat pane — image generation via Tool Calling, Chat pane — generate_image extra parameters, TOOLS pane (VLM), TOOLS pane — shared Chat attachment, TOOLS pane (Wildcards), Chat pane — image-to-image (I2I), Chat pane — SVG generation, no ComfyUI workflow involved, Chat pane — Skills, Settings pane, Unsloth backend, Settings pane — Chat Image Generation, Settings pane — Chat I2I Generation, Settings pane — Generation, Settings shared, Backend support, URL security, Lemonade's other endpoints (not integrated)
|
||||
4-pane layout, Translation pane, Chat pane, Chat pane — image generation via Tool Calling, Chat pane — generate_image extra parameters, TOOLS pane (VLM), TOOLS pane — shared Chat attachment, TOOLS pane (Wildcards), Chat pane — image-to-image (I2I), Chat pane — SVG generation, no ComfyUI workflow involved, Chat pane — Skills, Settings pane, Unsloth backend, Settings pane — Chat Image Generation, Settings pane — Chat I2I Generation, Settings pane — Generation, Model unload, Settings shared, Backend support, URL security, Lemonade's other endpoints (not integrated)
|
||||
|
||||
### Workflow Studio Library (ComfyUI Side Panel) (v0.3.9)
|
||||
Tab layout (W / N / P / M / I / A), W — Workflows tab, N — Nodes tab, M — Models tab, P — Prompts tab, I — Information tab, A — AI TOOL tab, Drag & drop workflows, Drag & drop nodes, Drag & drop prompts, Send to Canvas, Copy prompts, Double-click, Search, ⚙ Theme settings
|
||||
|
||||
@@ -22,7 +22,7 @@ A comprehensive workflow, asset management, and generation UI plugin for [ComfyU
|
||||
- Built-in AI tools (translation and more)
|
||||
|
||||

|
||||

|
||||

|
||||
|
||||
## Screenshots
|
||||
|
||||
@@ -30,29 +30,25 @@ A comprehensive workflow, asset management, and generation UI plugin for [ComfyU
|
||||
| :-------------------------------------: | :---------------------------------: |
|
||||
|  |  |
|
||||
|
||||
| Prompt Input Assistance | Gen UI Feeder |
|
||||
| :----------------------------------------------------------: | :---------------------------------------: |
|
||||
|  |  |
|
||||
| Prompt Input Assistance | GenUI Batch |
|
||||
| :----------------------------------------------------------: | :-------------------------------------: |
|
||||
|  |  |
|
||||
|
||||
| GenUI LoRA Stack | GenUI Batch |
|
||||
| :---------------------------------------------: | :-------------------------------------: |
|
||||
|  |  |
|
||||
|
||||
| Models Multi-select Menu | Top Bar |
|
||||
| :-----------------------------------------------------------: | :---------------------------: |
|
||||
|  |  |
|
||||
| Top Bar | Image Edit Tab |
|
||||
| :----------------------------: | :--------------------------------------: |
|
||||
|  |  |
|
||||
|
||||
| WS Library | Library Information |
|
||||
| :----------------------------------: | :---------------------------------------------------: |
|
||||
|  |  |
|
||||
|
||||
| Tagger Tab | Image Edit Tab |
|
||||
| :-------------------------------: | :--------------------------------------: |
|
||||
|  |  |
|
||||
| Video Tab | AI TOOL Tab |
|
||||
| :----------------------------------: | :--------------------------------------: |
|
||||
|  |  |
|
||||
|
||||
| Customize | |
|
||||
| :--------------------------------: | :-: |
|
||||
|  | |
|
||||
| Lab Tab | Lab Index Image |
|
||||
| :--------------------------------: | :------------------------------------------: |
|
||||
|  |  |
|
||||
|
||||
---
|
||||
|
||||
@@ -69,7 +65,7 @@ A comprehensive workflow, asset management, and generation UI plugin for [ComfyU
|
||||
- **Badge management** — add, rename, delete badges with custom colors shared with the Models tab (⚙ Badge button)
|
||||
- **AI summary** — generate workflow descriptions using Ollama
|
||||
- **Import / Export** — import workflows from files or clipboard; **Send to Canvas** button sends the selected workflow directly to the ComfyUI canvas (UI and API formats both supported)
|
||||
- **Side panel toolbar buttons** (v0.5.0) — selecting a card shows three buttons in the top toolbar: **Load in GenerateUI**, **Load in Video** (new — loads a MiniMax H3 Image-to-Video workflow into the Video tab; shows an error toast for workflows that don't contain that node), and **Send to Canvas**; the detail modal's duplicate copies of these three buttons were removed in favor of this single toolbar location
|
||||
- **Side panel toolbar buttons** (v0.5.0) — selecting a card shows three buttons in the top toolbar: **Load in GenerateUI**, **Load in Video** (loads a MiniMax H3 Image-to-Video, LTX-2.5 (Text/Image/First&Last-Frame to Video), or Wan2.2 (Text to Video) workflow into the Video tab (LTX-2.5/Wan2.2 support: v0.5.4); shows an error toast for workflows that don't contain a supported node), and **Send to Canvas**; the detail modal's duplicate copies of these three buttons were removed in favor of this single toolbar location
|
||||
- **Default view setting** — persist your preferred view mode (Thumbnail / Table)
|
||||
- **Search clear (✕)** — inline ✕ button appears inside the search box whenever text is entered; click to clear immediately
|
||||
- **Clear all filters (✕ Clear)** — rightmost toolbar button; resets search text, group filter, and badge filter (ALL) in one click
|
||||
@@ -117,7 +113,9 @@ A comprehensive workflow, asset management, and generation UI plugin for [ComfyU
|
||||
- **Right pane (Batch Queue)** — 7 columns: Checkpoint / Lora / Prompt / Workflow / Sampler / Scheduler / **Style**; each column header has an enable checkbox (radio behavior: only one at a time); count shown per column; Style batch applies each selected style sequentially to a workflow copy
|
||||
- **Lora batch prompt sync** (v0.3.69) — for each selected LoRA, its syntax (`<lora:name:strength_model:strength_clip>`) and CivitAI trained words are automatically appended to the Positive prompt (rebuilt from the original prompt each time, not accumulated), then restored to the pre-batch state when the batch completes or is stopped; if a selected LoRA is not yet recognized by ComfyUI's model list, a warning toast suggests a Refresh or restart
|
||||
- **UI-to-API conversion** — automatic conversion supporting subgraphs (nested workflows), COMBO types, and display-only node exclusion; improved analysis covers SDXL multi-hop CONDITIONING chains, CLIPTextEncodeSDXL, SDXLPromptStyler, KSamplerAdvanced, and Guider-based "Advanced Sampling" workflows (`SamplerCustomAdvanced`/`SamplerCustom` + `CFGGuider`/`DualCFGGuider`/`BasicGuider` + `RandomNoise` + `KSamplerSelect` + `*Scheduler` — Flux.2 Klein, LongCat, Boogu, HiDream E1, etc.)
|
||||
- **MultiType widget-value bug fix** (v0.5.4) — a node input declaring a comma-joined MultiType (e.g. LTX-2.5's `LTXVEmptyLatentAudio.frame_rate: "FLOAT,INT"`) was silently dropped from the widget list instead of being recognized as a scalar widget, which shifted every subsequent widget's value onto the wrong input (surfaced as `LTXVEmptyLatentAudio.batch_size` receiving `frame_rate`'s value and video generation failing with "Expected size 1 but got size 25")
|
||||
- **Video workflow support** (v0.5.2) — loading a MiniMax H3 (or other all-in-one video-generation) workflow now works from GenerateUI too, not just the dedicated Video tab: the Input tab's Prompt field picks up its `prompt` widget, the Image tab picks up its LoadImage-based `first_frame` the same way any other I2I workflow does, and generation runs with a longer timeout since video generation takes much longer than a still image; the result preview shows the generated mp4 inline (`<video>`) instead of trying to render it as an image
|
||||
- **LTX-2.5 / Wan2.2 support** (v0.5.4) — these follow ComfyUI's regular node-graph pattern rather than an all-in-one node, so they needed their own detection: Positive/Negative Prompt now traces through LTX-2.5's `LTXVDualCFGGuider`/`LTXVConditioning` nodes to the actual prompt text, and the Settings tab's Latent Image section recognizes Wan2.2's `EmptyHunyuanLatentVideo` and LTX-2.5's `EmptyLTXVLatentVideo` (width/height/batch size, plus an added **Length (frames)** field) instead of showing "No EmptyLatentImage node found"; the extended generation timeout now also triggers off a `SaveVideo`/`CreateVideo` node anywhere in the graph, not just an all-in-one node
|
||||
- **Eagle integration** — auto-save generated images to [Eagle](https://eagle.cool/) with metadata
|
||||
|
||||
</details>
|
||||
@@ -184,7 +182,8 @@ An experimental batch generator: runs the workflow currently loaded in GenerateU
|
||||
<summary><h3>Prompt Tab</h3></summary>
|
||||
|
||||
- **3-column layout** — AI Assistant (left), Presets/Preset Manager tab-panel (center), Wildcard/Style support (right)
|
||||
- **AI chat assistant** — powered by [Ollama](https://ollama.com/), generate and refine prompts interactively
|
||||
- **AI chat assistant** — generate and refine prompts interactively using Ollama, LM Studio, Lemonade, or Unsloth (multi-backend: v0.5.4)
|
||||
- **⚙ Settings modal** (v0.5.4) — replaces the old central Settings-tab panel; opens a dedicated modal (Backend / Connection / Model / Generation / Unload / Save) scoped to this tab only, saved under its own `localStorage` key so it stays independent of the Tagger tab's VLM settings; **Thinking mode** and **Max tokens** apply to every chat request, and an **Unload** button frees the selected model from Ollama/LM Studio/Lemonade (Unsloth has no such API and is shown as unsupported)
|
||||
- **Image attachment** — attach reference images for vision-capable models
|
||||
- **Translation** — JA/EN/ZH translation buttons for multilingual prompt creation
|
||||
- **Prompt presets** — save/load reusable prompt templates (positive & negative) with category support
|
||||
@@ -225,16 +224,17 @@ An experimental batch generator: runs the workflow currently loaded in GenerateU
|
||||
- **Workflows directory** — configure which folder to scan for workflows
|
||||
- **Gallery output directory** — configure which output folder the Gallery tab scans for images
|
||||
- **Eagle connection** — set Eagle API endpoint for auto-save
|
||||
- **Ollama connection** — configure Ollama server URL
|
||||
- **CivitAI Host** — choose which site opens when clicking a model link: `civitai.com` (SFW only) or `civitai.red` (unrestricted); saved to `settings.json` and synced to `localStorage` for the Models tab to use without extra fetches
|
||||
- **CivitAI API Key** — optional Bearer token for authenticated CivitAI access; stored in `settings.json` (excluded from data exports); environment variable `CIVITAI_API_KEY` takes priority if set
|
||||
- **Default workflow** — set a workflow to auto-load on startup
|
||||
- **Default Checkpoint** (v0.3.73) — optional checkbox to force every checkpoint loader node's model to a chosen default whenever a workflow is loaded into GenerateUI; a safeguard against generation errors or garbled images from a stale/mismatched checkpoint saved in the workflow file
|
||||
- ~~AI Assistant Settings~~ (removed in v0.5.4) — the central Ollama backend/URL/model panel that used to live here was replaced by a ⚙ Settings button + modal directly in the Prompt tab and the Tagger tab, each with its own independent configuration (backend, URL, model, Thinking mode, Max tokens, and a model Unload button) — see those tabs below; the AI TOOL tab's own Settings pane is unaffected
|
||||
- **Video Playback Volume** (v0.5.4) — the video preview's volume is remembered here and shared across every video player in the plugin (Video tab, Gallery tab), instead of resetting to maximum whenever a different video is opened
|
||||
- **Data Management** — export core settings/metadata/prompts/CivitAI cache to a single JSON file; import to restore data (useful when migrating or reinstalling); API keys are excluded from exports for security
|
||||
- **Full Backup (ZIP)** (v0.5.2) — additionally covers what the JSON bundle can't represent: folder-based data (AI Skills, Lab Plans, Style presets) and the Tagger SQLite database; two opt-in checkboxes can also include ComfyUI's default workflows folder (`user/default/workflows`) and the Impact Pack's wildcard folder in the export — both of those are export-only and stored under an `_external/` prefix in the ZIP that Restore always skips, since auto-overwriting files a different plugin/ComfyUI core manages would be unsafe; copy them back by hand if needed. Restoring overwrites existing files; restart ComfyUI afterward for either restore path
|
||||
- **Full Backup (ZIP)** (v0.5.2) — additionally covers what the JSON bundle can't represent: folder-based data (AI Skills, Lab Plans, Video Plans, Style presets) and the Tagger SQLite database; two opt-in checkboxes can also include ComfyUI's default workflows folder (`user/default/workflows`) and the Impact Pack's wildcard folder in the export — both of those are export-only and stored under an `_external/` prefix in the ZIP that Restore always skips, since auto-overwriting files a different plugin/ComfyUI core manages would be unsafe; copy them back by hand if needed. Restoring overwrites existing files; restart ComfyUI afterward for either restore path
|
||||
- **Text Size** — one slider (10–28 px) adjusts font size for all prompt and chat textareas at once: Generate UI positive/negative prompts, AI Assistant chat input, Preset prompts, Wildcard prompt and file editor, and Metadata prompt full preview; takes effect immediately and saved with Save Settings
|
||||
- **RAW JSON Colors** — customize the 6 syntax highlight colors for the Raw JSON editor in Generate UI: Default Text (base), Name/Scheduler (yellow), Title (pink), Width/Height (green), Prompt/Text (cyan), Image/File (red); changes apply immediately on color pick; Reset Defaults restores the original scheme; saved to `localStorage` under `wfm_settings.jsonColors` and applied on startup
|
||||
- **GenerateUI Model Tab Highlight** (v0.3.98) — pick the color used to mark Checkpoint/VAE/Diffusion Model/Text Encoder/ControlNet/Hypernetwork labels and the LoRA column header in GenerateUI's Model tab when the loaded workflow actually contains that type of node; default bright green; changes apply immediately, Reset Defaults restores it; saved to `localStorage` under `wfm_settings.modelTabActiveColor`
|
||||
- **GenerateUI Model Tab Highlight** (v0.3.98) — pick the color used to mark Checkpoint/VAE/Diffusion Model/Text Encoder/ControlNet/Hypernetwork labels and the LoRA column header in GenerateUI's Model tab when the loaded workflow actually contains that type of node; default bright green; changes apply immediately, Reset Defaults restores it; saved to `localStorage` under `wfm_settings.modelTabActiveColor`; the same color and mechanism also drives the Video tab's field highlighting (v0.5.4, see above)
|
||||
- **Wildcard Integration** — link the WFS wildcard directory to ComfyUI-Impact-Pack's `wildcards/` directory (directory junction on Windows, symlink on other OS); existing WFS wildcard files are automatically migrated; requires [ComfyUI-Impact-Pack](https://github.com/ltdrdata/ComfyUI-Impact-Pack)
|
||||
- **G'MIC-Qt Integration** — set the path to `gmic_qt.exe` for the Image Edit Filter tool; download G'MIC-Qt Standalone from `gmic.eu/download.html` (Windows: `gmic_qt-win64.zip`), extract anywhere, then enter the full path to `gmic_qt.exe` and click Save
|
||||
- **Language** — English / Japanese / Chinese
|
||||
@@ -368,10 +368,11 @@ An experimental batch generator: runs the workflow currently loaded in GenerateU
|
||||
- **3 sub-tabs** — Single / Batch / DB for single-image tagging, folder batch processing, and tag database management
|
||||
- **Model support** — WD Tagger (ONNX, NCHW/NHWC auto-detect), SwinV2 (ONNX), DeepDanbooru (.h5, requires TensorFlow); place each model in its own subfolder under `ComfyUI/models/tagger/<model-name>/` containing the `.onnx` + `selected_tags.csv` (or `.h5` + label file)
|
||||
- **Threshold sliders** — General threshold (default 0.35) and Character threshold for `character:` prefix tags (default 0.85); sliders update the display value in real time
|
||||
- **Ollama VLM** — optional vision model alongside WD Tagger; set API URL and select model (↻ to refresh list); results from both models are merged into one comma-separated tag string
|
||||
- **VLM tagging** (v0.3.38, multi-backend: v0.5.4) — optional vision model alongside WD Tagger, running on Ollama, LM Studio, Lemonade, or Unsloth through the same unified backend used by the Prompt tab; results from both models are merged into one comma-separated tag string
|
||||
- **⚙ Settings modal** (v0.5.4) — a Settings button (Single and Batch tabs) opens the same modal component as the Prompt tab's AI Assistant (Backend / Connection / Model / Generation / Unload), but saved under its own `localStorage` key so Tagger's VLM backend/model choice is independent of the Prompt tab's; **Thinking mode** and **Max tokens** apply to VLM requests too, and the **Unload** button frees the selected model (Ollama/LM Studio/Lemonade; Unsloth unsupported) — replaces the old Tagger-only direct Ollama URL/model fields
|
||||
- **Single tab** — drag & drop an image onto the preview area or click Upload; Gallery detail panel **Tagger** button opens the selected image directly here
|
||||
- **Single output options** — (1) **GenUI:P** — appends tags to the GenerateUI tab's positive prompt and immediately applies to the loaded workflow; (2) **Send to Prompt** — appends tags to the Prompt tab's positive textarea; (3) **Save to Gallery** — saves tags to Gallery image metadata (requires image opened from Gallery); (4) **Write to File** — embeds tags into JPEG EXIF (`ImageDescription`) or PNG `tEXt` chunk (`Tags` key), other formats get a `.tags.json` sidecar; (5) **Save to DB** — stores in internal SQLite database
|
||||
- **Batch tab** — enter a folder path, configure WD Tagger and Ollama settings; output options: **Save to DB** (default on), **Write to File** (EXIF/PNG metadata), **Write .txt** (creates `<filename>.txt` alongside each image with all tags); real-time progress bar and log; Stop cancels after the current image
|
||||
- **Batch tab** — enter a folder path, configure WD Tagger thresholds and (via the same ⚙ Settings modal as Single) the VLM backend; output options: **Save to DB** (default on), **Write to File** (EXIF/PNG metadata), **Write .txt** (creates `<filename>.txt` alongside each image with all tags); real-time progress bar and log; Stop cancels after the current image
|
||||
- **DB tab** — searchable SQLite database of all tagged images; click a row to open the edit panel and modify WD Tags / VLM Tags; Save updates the record, Delete removes it; Export CSV downloads all records
|
||||
- **Dependencies** — install into ComfyUI's embedded Python: `python_embedded\python.exe -m pip install -r requirements.txt`; for GPU inference use `onnxruntime-gpu`; TensorFlow (DeepDanbooru) is optional and commented out in `requirements.txt`
|
||||
|
||||
@@ -403,16 +404,20 @@ An experimental batch generator: runs the workflow currently loaded in GenerateU
|
||||
</details>
|
||||
|
||||
<details>
|
||||
<summary><h3>Video Tab (v0.5.0 – v0.5.2)</h3></summary>
|
||||
<summary><h3>Video Tab (v0.5.0 – v0.5.7)</h3></summary>
|
||||
|
||||
- **Dedicated MiniMax H3 video generation UI, independent of GenerateUI** — a purpose-built tab for the MiniMax H3 (Image to Video) workflow; does not share state with the GenerateUI tab, and model selection (UNet/CLIP/VAE/Audio VAE) is fixed to the loaded workflow's own defaults rather than editable here
|
||||
- **3-pane layout** — left: form (First Frame / Last Frame / Prompt / Aspect Ratio / Megapixels / Multiple / Duration / Noise Seed / Generate); center: preview frame + Video Source panel, plus an Editing pane reserved for future video-editing tools; right: **Frame** / **GIF** property tabs (v0.5.2, see below)
|
||||
- **First Frame / Last Frame are both optional** — leaving First Frame empty runs the workflow text-only (the node is simply left unconnected — a "bypass"); workflows that don't even include a LoadImage node for First Frame are supported out of the box, and a LoadImage node is only injected into the graph on the fly if an image is actually supplied
|
||||
- **Node lookup instead of hardcoded IDs** — locates the MiniMax H3 subgraph instance, its linked Resolution Selector, and (if present) its linked LoadImage node by walking the workflow's subgraph definitions and links, so a workflow doesn't need to match the reference `minimax_test.json`'s exact node IDs
|
||||
- **Load in Video** (Workflow tab) — load any workflow containing a MiniMax H3 Image-to-Video node straight into this tab from the Workflow tab's side-panel toolbar (next to Load in GenerateUI); unsupported workflows show an error toast instead of loading
|
||||
- **Preview frame + Video Source panel** (v0.5.2, replaces the old Result panel) — the center pane's preview shows either a just-generated video or one loaded independently of generation; a **Video Source** drop zone next to it accepts any local video file (drag-and-drop or click to pick), with a **Clear** button to reset back to empty — the Frame/GIF tools below work on whatever is currently shown here, generated or not; generated results are still saved to Gallery metadata (embedded workflow JSON) automatically, so the Gallery tab's Workflow/Prompt panels work on generated videos the same way they do for images
|
||||
- **Frame tab** (v0.5.2) — captures the preview video's current playback position as a still frame: play/seek to the position you want, click **Capture Frame** (client-side canvas, no server round-trip), then **Save to Output** to write it as a PNG into ComfyUI's own Output folder (auto-numbered, same pattern as other generated images)
|
||||
- **GIF tab** (v0.5.2) — converts the preview video to an animated GIF; set Start/End (seconds), FPS, and an optional Max Width, then **Convert to GIF** — the server decodes the video (PyAV) and encodes an animated GIF (Pillow), both dependencies ComfyUI itself already requires, so no ffmpeg binary or extra install is needed; the result is saved into ComfyUI's Output folder and previewed inline
|
||||
- **Dedicated video generation UI, independent of GenerateUI** — a purpose-built tab for MiniMax H3 (Image to Video), LTX-2.5 (Text / Image / First & Last Frame to Video), and Wan2.2 (Text to Video) workflows (LTX-2.5/Wan2.2: v0.5.4); does not share state with the GenerateUI tab, and model selection (UNet/CLIP/VAE/Audio VAE) is fixed to the loaded workflow's own defaults rather than editable here
|
||||
- **Plan / Edit subtabs** (center panel, batch redesign in v0.5.5) — a **plan** is a sequence of timeline blocks, each a fully self-contained generation job with its own Prompt, Duration, and First/Last Image; split the timeline with **+ Split** / **+ Block** / **Delete**, then **Run** to generate every block in order (Pause/Cancel work mid-run) — a plan with a single block behaves exactly like the old one-shot form. First Image can be None, an explicit image, or "use previous block's last frame" (chaining — an explicit Last Image on the previous block always wins over extracting one from its generated output). Save / Save As / Clear a plan (`ws_videoplan_*.json`, with a PNG contact-sheet thumbnail that embeds the full plan data so dropping the image back on works too); Edit is reserved for future video-editing tools
|
||||
- **Base settings row** (topbar, v0.5.7) — Aspect Ratio / Megapixels / Multiple / Duration (seconds) / Noise Seed on one row — Duration always reflects the currently selected block (each block keeps its own value), the rest are plan-wide — plus a second row of model-specific fields: Width / Height (become directly editable for workflows with no Resolution Selector node, e.g. Wan2.2 and LTX-2.5's First & Last Frame to Video), Turbo Mode / Strength / Steps (MiniMax H3's turbo LoRA — Turbo Mode doubles as Wan2.2's own turbo toggle, sharing one field), and Prompt Enhance (LTX-2.5 only). Every field in both rows is enabled only when the loaded workflow actually has it — see Field highlight color below (one exception: Wan2.2's Text-to-Video variant doesn't expose Noise Seed at all, so it alone leaves that field disabled)
|
||||
- **Asset / Project subtabs** (sidebar, v0.5.5) — **Asset** browses generated videos through three groups: **Video Assets** (a manually-curated keeper group you organize yourself, on your own schedule), **Video Temp** (every plan run's output lands here automatically regardless of whether the plan itself was saved — a **Clear Video Temp** button in the Gallery tab's detail panel empties it in one click), and **All Video Assets** (the union of both); selecting a video shows it in the center panel's left preview and lets you tag/memo it or jump straight to the full Gallery tab. **Project** lists every saved plan file (thumbnail, block count, last updated) — click one to load it into the Plan editor, or delete it with the × button; either sidebar panel collapses back down when its own tab is clicked again
|
||||
- **Two center previews** (v0.5.5) — the left preview shows either the video currently selected in the Asset subtab or whatever's dropped/picked in the **Video Source** panel to its left (**Clear** resets it to empty); the right preview always shows the most recently generated clip. The Frame/GIF tools act on whichever preview was touched most recently
|
||||
- **First Frame / Last Frame are both optional** — leaving First Image empty runs the workflow text-only (the node is simply left unconnected — a "bypass"); workflows that don't even include a LoadImage node for First Frame are supported out of the box (Wan2.2's Text-to-Video graph has neither slot at all), and a LoadImage node is only injected into the graph on the fly if an image is actually supplied
|
||||
- **Semantic node lookup, not hardcoded IDs** (generalized in v0.5.4) — detects which of the three families is loaded from its subgraph's internal node types (or, for Wan2.2, the subgraph's own name — it has no distinctive internal node type), then locates its Resolution Selector and LoadImage node(s) by the subgraph's *public input label* (`prompt`, `duration`, `width`, `first_frame`, `last_frame`) rather than a fixed slot index — so it keeps working even though the three families expose those inputs under different internal names; a workflow no longer needs to match any bundled reference file's exact node IDs, and no fallback test workflow is auto-loaded on tab open
|
||||
- **Field highlight color** — Prompt / Duration / First Image / Last Image / Aspect Ratio / Megapixels / Multiple / Noise Seed / Width / Height / Turbo Mode / Strength / Steps / Prompt Enhance labels turn the same highlight color as the GenerateUI Model tab (shared setting, customizable in the Settings tab — see below) when the loaded workflow actually exposes that field; e.g. a Wan2.2 workflow (no Resolution Selector node) leaves Aspect Ratio / Megapixels / Multiple unhighlighted while Width / Height light up instead
|
||||
- **Load in Video** (Workflow tab) — load any workflow containing a MiniMax H3 Image-to-Video node, an LTX-2.5 Text/Image/First&Last-Frame-to-Video node, or a Wan2.2 Text-to-Video node straight into this tab from the Workflow tab's side-panel toolbar (next to Load in GenerateUI) — starts a fresh single-block plan seeded from the workflow's own current values; unsupported workflows show an error toast instead of loading
|
||||
- **Frame tab** (right panel) — captures the active preview's current playback position as a still frame: play/seek to the position you want, click **Capture Frame** (client-side canvas, no server round-trip), then **Save to Output** to write it as a PNG into ComfyUI's own Output folder (auto-numbered, same pattern as other generated images)
|
||||
- **GIF tab** (right panel) — converts the active preview to an animated GIF; set Start/End (seconds), FPS, and an optional Max Width, then **Convert to GIF** — the server decodes the video (PyAV) and encodes an animated GIF (Pillow), both dependencies ComfyUI itself already requires, so no ffmpeg binary or extra install is needed; the result is saved into ComfyUI's Output folder and previewed inline
|
||||
- **Playback volume** — the preview player's volume is saved to the Settings tab and shared across every video player in the plugin (Video tab, Gallery tab), so it no longer resets to maximum each time a different video is opened
|
||||
|
||||
</details>
|
||||
|
||||
@@ -436,6 +441,7 @@ An experimental batch generator: runs the workflow currently loaded in GenerateU
|
||||
- **Settings pane — Chat Image Generation** (v0.3.73) — "Use dedicated workflow" checkbox lets Chat-triggered image generation use a saved workflow of your choice instead of the one currently loaded in GenerateUI, without disturbing what's shown there (same pattern as Image Edit's Inpaint dedicated workflow)
|
||||
- **Settings pane — Chat I2I Generation** (v0.3.74) — same "Use dedicated workflow" pattern as above, but for image-to-image generation when an image is attached; independent of the text-to-image dedicated workflow setting
|
||||
- **Settings pane — Generation** (v0.3.98) — **Thinking mode** toggle (off by default; sends Ollama's `think` flag, and regardless of backend, any `<think>...</think>` block is stripped from the output when off so reasoning models don't clutter Translation/Chat/TOOLS results) and **Max tokens** (Ollama: `options.num_predict`; LM Studio/Lemonade/Unsloth: `max_tokens`; `0` = unlimited)
|
||||
- **Model unload** (v0.5.4) — an Unload button next to the model selector frees VRAM/memory by unloading the currently selected model from Ollama (`keep_alive:0` via `/api/generate`, the officially documented method — Ollama has no dedicated unload endpoint), LM Studio (`/api/v1/models/unload`), or Lemonade (`/api/v1/unload`); Unsloth exposes no equivalent API and the button is disabled for that backend
|
||||
- **Settings shared** — settings saved to `localStorage` under `wfm_ai_settings`; shared with the Library panel's AI TOOL tab so configuration is consistent across both interfaces
|
||||
- **Backend support** — Ollama (`/api/generate` for text, `/api/chat` for conversations, `/api/tags` for model list); LM Studio and Lemonade via the OpenAI-compatible API directly from the browser (`/v1/chat/completions`, `/v1/models`); Unsloth via the same OpenAI-compatible API but relayed through a server-side proxy that attaches the `Authorization: Bearer` header; VLM images sent as base64 (`images:[]` for Ollama, `image_url` content block for LM Studio/Lemonade/Unsloth)
|
||||
- **URL security** — backend URL validated via `new URL()` to enforce `http://` or `https://` scheme
|
||||
|
||||
|
Before Width: | Height: | Size: 16 KiB |
|
Before Width: | Height: | Size: 181 KiB |
|
After Width: | Height: | Size: 181 KiB |
|
After Width: | Height: | Size: 62 KiB |
|
After Width: | Height: | Size: 181 KiB |
|
After Width: | Height: | Size: 161 KiB |
|
Before Width: | Height: | Size: 278 KiB |
|
Before Width: | Height: | Size: 90 KiB |
|
Before Width: | Height: | Size: 48 KiB |
@@ -71,6 +71,7 @@ MODEL_METADATA_FILE = DATA_DIR / "model_metadata.json"
|
||||
WILDCARD_DIR = DATA_DIR / "wildcard"
|
||||
AI_SKILLS_DIR = DATA_DIR / "ai_skills"
|
||||
LAB_PLAN_DIR = DATA_DIR / "lab_plan"
|
||||
VIDEO_PLAN_DIR = DATA_DIR / "video_plan"
|
||||
|
||||
# Tagger
|
||||
TAGGER_DB_FILE = DATA_DIR / "tagger.db"
|
||||
|
||||
@@ -405,7 +405,7 @@ async def create_group(request: web.Request) -> web.Response:
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
|
||||
_RESERVED_GROUPS = {"__Feeder__"}
|
||||
_RESERVED_GROUPS = {"__Feeder__", "__Video Assets__", "__Video Temp__"}
|
||||
|
||||
|
||||
async def rename_group(request: web.Request) -> web.Response:
|
||||
|
||||
@@ -255,8 +255,8 @@ async def handle_import(request: web.Request) -> web.Response:
|
||||
|
||||
|
||||
# Full-backup (ZIP) export/import: unlike the flat _DATA_FILES JSON bundle above, this
|
||||
# covers the whole DATA_DIR — directory-shaped data (ai_skills/, lab_plan/, style/) and
|
||||
# the SQLite tagger.db that the JSON bundle can't represent. Excludes transient/cache
|
||||
# covers the whole DATA_DIR — directory-shaped data (ai_skills/, lab_plan/, video_plan/,
|
||||
# style/) and the SQLite tagger.db that the JSON bundle can't represent. Excludes transient/cache
|
||||
# dirs, and wildcard/ specifically because it's typically a symlink into a *different*
|
||||
# custom_node's folder (comfyui-impact-pack) rather than this plugin's own data.
|
||||
_FULL_BACKUP_EXCLUDE_NAMES = {"gmic_temp", "thumb_cache", "wildcard"}
|
||||
|
||||
@@ -18,8 +18,8 @@ _db = TaggerDbService(TAGGER_DB_FILE)
|
||||
def setup_routes(app: web.Application):
|
||||
app.router.add_get("/wfm/tagger/models", handle_models)
|
||||
app.router.add_post("/wfm/tagger/predict", handle_predict)
|
||||
app.router.add_get("/wfm/tagger/ollama/models", handle_ollama_models)
|
||||
app.router.add_post("/wfm/tagger/ollama/predict", handle_ollama_predict)
|
||||
app.router.add_get("/wfm/tagger/vlm/models", handle_vlm_models)
|
||||
app.router.add_post("/wfm/tagger/vlm/predict", handle_vlm_predict)
|
||||
app.router.add_post("/wfm/tagger/batch/start", handle_batch_start)
|
||||
app.router.add_get("/wfm/tagger/batch/status", handle_batch_status)
|
||||
app.router.add_post("/wfm/tagger/batch/stop", handle_batch_stop)
|
||||
@@ -61,25 +61,29 @@ async def handle_predict(request: web.Request) -> web.Response:
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
|
||||
async def handle_ollama_models(request: web.Request) -> web.Response:
|
||||
async def handle_vlm_models(request: web.Request) -> web.Response:
|
||||
backend = request.rel_url.query.get("backend", "ollama")
|
||||
api_url = request.rel_url.query.get("api_url", "http://127.0.0.1:11434")
|
||||
try:
|
||||
models = await asyncio.to_thread(_svc.ollama_models, api_url)
|
||||
models = await asyncio.to_thread(_svc.vlm_models, backend, api_url)
|
||||
return web.json_response({"models": models})
|
||||
except Exception as e:
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
|
||||
async def handle_ollama_predict(request: web.Request) -> web.Response:
|
||||
async def handle_vlm_predict(request: web.Request) -> web.Response:
|
||||
try:
|
||||
body = await request.json()
|
||||
result = await asyncio.to_thread(
|
||||
_svc.ollama_predict,
|
||||
_svc.vlm_predict,
|
||||
body.get("image_b64", ""),
|
||||
body.get("backend", "ollama"),
|
||||
body.get("api_url", "http://127.0.0.1:11434"),
|
||||
body.get("model", ""),
|
||||
body.get("prompt", ""),
|
||||
int(body.get("max_tags", 40)),
|
||||
bool(body.get("thinking_mode", False)),
|
||||
int(body.get("max_tokens", 0)),
|
||||
)
|
||||
return web.json_response(result)
|
||||
except Exception as e:
|
||||
@@ -96,7 +100,8 @@ async def handle_batch_start(request: web.Request) -> web.Response:
|
||||
float(body.get("threshold", 0.35)),
|
||||
float(body.get("char_threshold", 0.85)),
|
||||
bool(body.get("use_ollama", False)),
|
||||
body.get("ollama_api", "http://127.0.0.1:11434"),
|
||||
body.get("vlm_backend", "ollama"),
|
||||
body.get("vlm_api_url", "http://127.0.0.1:11434"),
|
||||
body.get("ollama_model", ""),
|
||||
body.get("ollama_prompt", ""),
|
||||
int(body.get("ollama_max_tags", 40)),
|
||||
@@ -104,6 +109,8 @@ async def handle_batch_start(request: web.Request) -> web.Response:
|
||||
bool(body.get("write_file", False)),
|
||||
bool(body.get("write_txt", False)),
|
||||
_db,
|
||||
bool(body.get("thinking_mode", False)),
|
||||
int(body.get("max_tokens", 0)),
|
||||
)
|
||||
return web.json_response(result)
|
||||
except Exception as e:
|
||||
|
||||
@@ -1,21 +1,31 @@
|
||||
"""Video tab utility API routes: last-frame capture, animated GIF conversion."""
|
||||
"""Video tab API routes: last-frame capture, animated GIF conversion, and
|
||||
Plan (batch timeline) file management."""
|
||||
|
||||
import asyncio
|
||||
import logging
|
||||
|
||||
from aiohttp import web
|
||||
|
||||
from ..config import VIDEO_PLAN_DIR
|
||||
from ..services.video_service import VideoService
|
||||
from ..services.video_plan_service import VideoPlanService
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
_service = VideoService()
|
||||
_plan_service = VideoPlanService(VIDEO_PLAN_DIR)
|
||||
|
||||
|
||||
def setup_routes(app: web.Application):
|
||||
app.router.add_post("/api/wfm/video/frame/save-to-output", handle_save_frame)
|
||||
app.router.add_post("/api/wfm/video/to-gif", handle_to_gif)
|
||||
|
||||
app.router.add_get("/api/wfm/video/plans", handle_list_plans)
|
||||
app.router.add_get("/api/wfm/video/plans/content", handle_get_plan_content)
|
||||
app.router.add_post("/api/wfm/video/plans/save", handle_save_plan)
|
||||
app.router.add_post("/api/wfm/video/plans/delete", handle_delete_plan)
|
||||
app.router.add_post("/api/wfm/video/index-image/save-to-output", handle_save_index_to_output)
|
||||
|
||||
|
||||
async def handle_save_frame(request: web.Request) -> web.Response:
|
||||
try:
|
||||
@@ -57,3 +67,67 @@ async def handle_to_gif(request: web.Request) -> web.Response:
|
||||
except Exception as e:
|
||||
logger.error("Error converting video to GIF: %s", e)
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
|
||||
async def handle_list_plans(request: web.Request) -> web.Response:
|
||||
try:
|
||||
result = await asyncio.to_thread(_plan_service.list_plans)
|
||||
return web.json_response(result)
|
||||
except Exception as e:
|
||||
logger.error("Error listing video plans: %s", e)
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
|
||||
async def handle_get_plan_content(request: web.Request) -> web.Response:
|
||||
filename = request.rel_url.query.get("filename", "")
|
||||
try:
|
||||
data = await asyncio.to_thread(_plan_service.get_plan, filename)
|
||||
return web.json_response({"data": data})
|
||||
except FileNotFoundError:
|
||||
return web.json_response({"error": "not found"}, status=404)
|
||||
except ValueError as e:
|
||||
return web.json_response({"error": str(e)}, status=400)
|
||||
except Exception as e:
|
||||
logger.error("Error getting video plan content: %s", e)
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
|
||||
async def handle_save_plan(request: web.Request) -> web.Response:
|
||||
try:
|
||||
body = await request.json()
|
||||
filename = body.get("filename", "")
|
||||
data = body.get("data", {})
|
||||
index_image_base64 = body.get("index_image_base64")
|
||||
result = await asyncio.to_thread(_plan_service.save_plan, filename, data, index_image_base64)
|
||||
return web.json_response({"status": "ok", **result})
|
||||
except ValueError as e:
|
||||
return web.json_response({"error": str(e)}, status=400)
|
||||
except Exception as e:
|
||||
logger.error("Error saving video plan: %s", e)
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
|
||||
async def handle_delete_plan(request: web.Request) -> web.Response:
|
||||
try:
|
||||
body = await request.json()
|
||||
filename = body.get("filename", "")
|
||||
await asyncio.to_thread(_plan_service.delete_plan, filename)
|
||||
return web.json_response({"status": "ok"})
|
||||
except ValueError as e:
|
||||
return web.json_response({"error": str(e)}, status=400)
|
||||
except Exception as e:
|
||||
logger.error("Error deleting video plan: %s", e)
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
|
||||
async def handle_save_index_to_output(request: web.Request) -> web.Response:
|
||||
try:
|
||||
body = await request.json()
|
||||
image_base64 = body.get("image_base64", "")
|
||||
if not image_base64:
|
||||
return web.json_response({"error": "image_base64 required"}, status=400)
|
||||
result = await asyncio.to_thread(_plan_service.save_index_image_to_output, image_base64)
|
||||
return web.json_response({"status": "ok", **result})
|
||||
except Exception as e:
|
||||
logger.error("Error saving video index image to output: %s", e)
|
||||
return web.json_response({"error": str(e)}, status=500)
|
||||
|
||||
@@ -53,13 +53,35 @@ class GalleryMetadataStore:
|
||||
}
|
||||
except Exception as e:
|
||||
logger.warning("GalleryMetadataStore: load error: %s", e)
|
||||
# 破損ファイルをリネームしてバックアップしておく。ここでリネームせずに
|
||||
# 空の self._data のまま次の save() が走ると、破損直前までの全メタデータ
|
||||
# (タグ/メモ/グループ登録)が跡形もなく上書きされ、二度と復元できなくなる
|
||||
# (実際に発生した不具合: _save_to_disk が非アトミック書き込みだったため、
|
||||
# 大量画像フォルダのBGインデックス処理中の頻繁な保存とComfyUIの終了タイミング
|
||||
# が重なるとファイルが不完全な状態のまま残ることがあった — _save_to_disk側は
|
||||
# os.replace()によるアトミック書き込みに修正済みだが、過去に壊れたファイルや
|
||||
# 他要因による破損に備えてここでも保護しておく)。
|
||||
try:
|
||||
backup_path = self.file_path.with_name(self.file_path.name + ".corrupt")
|
||||
self.file_path.replace(backup_path)
|
||||
logger.warning("GalleryMetadataStore: corrupt file backed up to %s", backup_path)
|
||||
except Exception as backup_err:
|
||||
logger.warning("GalleryMetadataStore: failed to back up corrupt file: %s", backup_err)
|
||||
|
||||
def _save_to_disk(self):
|
||||
# 呼び出し元(save/create_group等)が既にself._lockを保持している前提の内部メソッド
|
||||
# 呼び出し元(save/create_group等)が既にself._lockを保持している前提の内部メソッド。
|
||||
# 一時ファイルに書き出してから置き換える(os.replace相当のPath.replace)ことで書き込みを
|
||||
# アトミックにする。素朴な open(path, "w") での直接上書きだと、書き込み完了前に他プロセス
|
||||
# が読むと不完全なJSONを掴む(torn read)うえ、書き込み中にComfyUIプロセスが終了すると
|
||||
# ファイルが壊れたまま残る — 大量画像フォルダのBGインデックス処理(10枚ごとに保存)で
|
||||
# 書き込み頻度が高い環境ほど発生しやすく、次回起動時のロード失敗→空データでの
|
||||
# 全上書きという形でユーザーの登録済みグループ/タグ/メモが消失する原因になっていた。
|
||||
try:
|
||||
self.file_path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(self.file_path, "w", encoding="utf-8") as f:
|
||||
tmp_path = self.file_path.with_name(self.file_path.name + ".tmp")
|
||||
with open(tmp_path, "w", encoding="utf-8") as f:
|
||||
json.dump(self._data, f, ensure_ascii=False, indent=2)
|
||||
tmp_path.replace(self.file_path)
|
||||
return True
|
||||
except Exception as e:
|
||||
logger.error("GalleryMetadataStore: save error: %s", e)
|
||||
|
||||
@@ -312,15 +312,22 @@ class GalleryService:
|
||||
try:
|
||||
with os.scandir(folder) as it:
|
||||
for entry in it:
|
||||
if not entry.is_file(follow_symlinks=True):
|
||||
# follow_symlinks=True forces stat() to make an extra syscall per file
|
||||
# to resolve the link target even for plain files. Output folders don't
|
||||
# contain symlinked images, so False is safe and much cheaper.
|
||||
if not entry.is_file(follow_symlinks=False):
|
||||
continue
|
||||
if Path(entry.name).suffix.lower() not in IMAGE_EXTENSIONS:
|
||||
continue
|
||||
try:
|
||||
st = entry.stat(follow_symlinks=True)
|
||||
st = entry.stat(follow_symlinks=False)
|
||||
# entry.path is already absolute+resolved because callers always
|
||||
# pass in an already-resolved `folder`. Re-resolving it here via
|
||||
# Path(entry.path).resolve() costs an extra filesystem round-trip
|
||||
# per file — on a 9786-file folder that alone was 6.7s vs 0.07s.
|
||||
entries.append((
|
||||
entry.name,
|
||||
str(Path(entry.path).resolve()).replace("\\", "/"),
|
||||
entry.path.replace("\\", "/"),
|
||||
st.st_size,
|
||||
st.st_mtime,
|
||||
))
|
||||
@@ -333,30 +340,45 @@ class GalleryService:
|
||||
return entries
|
||||
|
||||
def _scan_folder_recursive(self, folder: Path) -> list[tuple[str, str, int, float]]:
|
||||
"""os.walk() でフォルダ配下を再帰的に列挙する(サブフォルダの画像も含む)。
|
||||
"""フォルダ配下を再帰的に列挙する(サブフォルダの画像も含む)。
|
||||
ImagePrompt/Style Catalogギャラリーのように深い階層に画像が置かれるケース用。
|
||||
キャッシュはしない(フォルダ数が少なく、都度スキャンしても軽い想定)。
|
||||
os.walk()はDirEntryを介さずPath.stat()(follow_symlinks=True相当)を呼ぶため、
|
||||
_scan_folder()と同じ理由でフォルダ内ファイル数に対して極端に遅くなる。
|
||||
os.scandir()を自前で再帰し、follow_symlinks=Falseでstatする。
|
||||
"""
|
||||
entries = []
|
||||
try:
|
||||
for root, dirs, files in os.walk(folder):
|
||||
dirs[:] = [d for d in dirs if not d.startswith(".")]
|
||||
for name in files:
|
||||
if Path(name).suffix.lower() not in IMAGE_EXTENSIONS:
|
||||
continue
|
||||
full = Path(root) / name
|
||||
try:
|
||||
st = full.stat()
|
||||
entries.append((
|
||||
name,
|
||||
str(full.resolve()).replace("\\", "/"),
|
||||
st.st_size,
|
||||
st.st_mtime,
|
||||
))
|
||||
except OSError:
|
||||
continue
|
||||
except PermissionError:
|
||||
pass
|
||||
|
||||
def _walk(d):
|
||||
try:
|
||||
with os.scandir(d) as it:
|
||||
dir_entries = list(it)
|
||||
except (PermissionError, OSError):
|
||||
return
|
||||
for entry in dir_entries:
|
||||
if entry.is_dir(follow_symlinks=False):
|
||||
if not entry.name.startswith("."):
|
||||
_walk(entry.path)
|
||||
continue
|
||||
if not entry.is_file(follow_symlinks=False):
|
||||
continue
|
||||
if Path(entry.name).suffix.lower() not in IMAGE_EXTENSIONS:
|
||||
continue
|
||||
try:
|
||||
st = entry.stat(follow_symlinks=False)
|
||||
# entry.path is already absolute since the top-level `folder` passed
|
||||
# in by callers is always pre-resolved — see _scan_folder() for why
|
||||
# re-resolving per file here would be costly.
|
||||
entries.append((
|
||||
entry.name,
|
||||
entry.path.replace("\\", "/"),
|
||||
st.st_size,
|
||||
st.st_mtime,
|
||||
))
|
||||
except OSError:
|
||||
continue
|
||||
|
||||
_walk(folder)
|
||||
return entries
|
||||
|
||||
def list_images(
|
||||
@@ -789,21 +811,27 @@ class GalleryService:
|
||||
return self.metadata_store.save(str(resolved), data)
|
||||
|
||||
def toggle_favorite(self, image_path: str) -> bool:
|
||||
if not self._check_path_allowed(Path(image_path).resolve()):
|
||||
resolved = Path(image_path).resolve()
|
||||
if not self._check_path_allowed(resolved):
|
||||
return False
|
||||
meta = self.metadata_store.get(image_path)
|
||||
# get_image_metadata()/list_images() 側はresolve()済みパスをキーにして取得する
|
||||
# ため、ここでも統一する(save_image_metaと同じ理由。キー不一致による
|
||||
# 「保存はできるが表示されない」というサイレントな食い違いを防ぐ)。
|
||||
resolved_str = str(resolved)
|
||||
meta = self.metadata_store.get(resolved_str)
|
||||
new_val = not meta.get("favorite", False)
|
||||
self.metadata_store.save(image_path, {"favorite": new_val})
|
||||
self.metadata_store.save(resolved_str, {"favorite": new_val})
|
||||
return new_val
|
||||
|
||||
def bulk_set_favorite(self, paths: list[str], value: bool) -> dict:
|
||||
"""複数画像のお気に入りを一括設定する"""
|
||||
ok = fail = 0
|
||||
for p in paths:
|
||||
if not self._check_path_allowed(Path(p).resolve()):
|
||||
resolved = Path(p).resolve()
|
||||
if not self._check_path_allowed(resolved):
|
||||
fail += 1
|
||||
continue
|
||||
if self.metadata_store.save(p, {"favorite": value}):
|
||||
if self.metadata_store.save(str(resolved), {"favorite": value}):
|
||||
ok += 1
|
||||
else:
|
||||
fail += 1
|
||||
@@ -837,21 +865,28 @@ class GalleryService:
|
||||
return self.metadata_store.delete_group(name)
|
||||
|
||||
def add_to_group(self, image_path: str, group_name: str) -> bool:
|
||||
if not self._check_path_allowed(Path(image_path).resolve()):
|
||||
resolved = Path(image_path).resolve()
|
||||
if not self._check_path_allowed(resolved):
|
||||
return False
|
||||
meta = self.metadata_store.get(image_path)
|
||||
# get_image_metadata()/list_images() 側はresolve()済みパスをキーにして取得する
|
||||
# ため、ここでも統一する(save_image_metaと同じ理由。キー不一致による
|
||||
# 「グループに追加はできるが一覧に反映されない」というサイレントな食い違いを防ぐ)。
|
||||
resolved_str = str(resolved)
|
||||
meta = self.metadata_store.get(resolved_str)
|
||||
groups = meta.get("groups", [])
|
||||
if group_name not in groups:
|
||||
groups.append(group_name)
|
||||
return self.metadata_store.save(image_path, {"groups": groups})
|
||||
return self.metadata_store.save(resolved_str, {"groups": groups})
|
||||
return True
|
||||
|
||||
def remove_from_group(self, image_path: str, group_name: str) -> bool:
|
||||
if not self._check_path_allowed(Path(image_path).resolve()):
|
||||
resolved = Path(image_path).resolve()
|
||||
if not self._check_path_allowed(resolved):
|
||||
return False
|
||||
meta = self.metadata_store.get(image_path)
|
||||
resolved_str = str(resolved)
|
||||
meta = self.metadata_store.get(resolved_str)
|
||||
groups = [g for g in meta.get("groups", []) if g != group_name]
|
||||
return self.metadata_store.save(image_path, {"groups": groups})
|
||||
return self.metadata_store.save(resolved_str, {"groups": groups})
|
||||
|
||||
def list_images_in_group(self, group_name: str) -> list[str]:
|
||||
all_paths = self.metadata_store.list_images_in_group(group_name)
|
||||
|
||||
@@ -5,6 +5,8 @@ import csv
|
||||
import io
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import tempfile
|
||||
import threading
|
||||
import urllib.request
|
||||
@@ -185,19 +187,33 @@ class TaggerService:
|
||||
def _predict_onnx(self, img: Image.Image, data: dict, thr: float, char_thr: float) -> list:
|
||||
shape = data["input_shape"]
|
||||
fmt = "NHWC"
|
||||
size = (224, 224)
|
||||
size = 224
|
||||
if len(shape) == 4:
|
||||
if shape[1] == 3 and isinstance(shape[2], int) and shape[2] > 0:
|
||||
fmt = "NCHW"
|
||||
size = (int(shape[3]), int(shape[2]))
|
||||
size = int(shape[2])
|
||||
elif shape[3] == 3 and isinstance(shape[1], int) and shape[1] > 0:
|
||||
fmt = "NHWC"
|
||||
size = (int(shape[2]), int(shape[1]))
|
||||
size = int(shape[1])
|
||||
|
||||
img = ImageOps.exif_transpose(img)
|
||||
if img.mode != "RGB":
|
||||
img = img.convert("RGB")
|
||||
arr = np.array(img.resize(size, Image.Resampling.LANCZOS), dtype=np.float32) / 255.0
|
||||
# WD Tagger系標準の前処理: 透過は白背景で合成 → アスペクト比を維持したまま
|
||||
# 白背景で正方形にパディング → リサイズ → RGB→BGR → 0-255のfloat32のまま(NHWC)
|
||||
if img.mode != "RGBA":
|
||||
img = img.convert("RGBA")
|
||||
canvas = Image.new("RGBA", img.size, (255, 255, 255))
|
||||
canvas.paste(img, mask=img)
|
||||
img = canvas.convert("RGB")
|
||||
|
||||
w, h = img.size
|
||||
max_dim = max(w, h)
|
||||
padded = Image.new("RGB", (max_dim, max_dim), (255, 255, 255))
|
||||
padded.paste(img, ((max_dim - w) // 2, (max_dim - h) // 2))
|
||||
if max_dim != size:
|
||||
padded = padded.resize((size, size), Image.Resampling.BICUBIC)
|
||||
|
||||
arr = np.array(padded, dtype=np.float32)
|
||||
arr = np.ascontiguousarray(arr[:, :, ::-1]) # RGB -> BGR
|
||||
if fmt == "NCHW":
|
||||
arr = arr.transpose((2, 0, 1))
|
||||
arr = np.expand_dims(arr, 0)
|
||||
@@ -223,39 +239,107 @@ class TaggerService:
|
||||
tags.append(label.replace("character:", ""))
|
||||
return tags
|
||||
|
||||
# ── Ollama VLM ────────────────────────────────────────────
|
||||
# ── VLM Tagging (Ollama / LM Studio / Lemonade / Unsloth) ──
|
||||
|
||||
def ollama_models(self, api_url: str) -> list:
|
||||
@staticmethod
|
||||
def _unsloth_api_key() -> Optional[str]:
|
||||
"""UNSLOTH_API_KEY を環境変数(.env)から取得。Unslothはローカルでも常に必須。"""
|
||||
return os.environ.get("UNSLOTH_API_KEY", "").strip() or None
|
||||
|
||||
@staticmethod
|
||||
def _strip_thinking_tags(text: str) -> str:
|
||||
text = re.sub(r"<think>[\s\S]*?</think>", "", text, flags=re.IGNORECASE)
|
||||
text = re.sub(r"<thinking>[\s\S]*?</thinking>", "", text, flags=re.IGNORECASE)
|
||||
return text.strip()
|
||||
|
||||
def vlm_models(self, backend: str, api_url: str) -> list:
|
||||
backend = (backend or "ollama").lower()
|
||||
try:
|
||||
req = urllib.request.Request(api_url.rstrip("/") + "/api/tags")
|
||||
if backend == "ollama":
|
||||
req = urllib.request.Request(api_url.rstrip("/") + "/api/tags")
|
||||
with urllib.request.urlopen(req, timeout=5) as resp:
|
||||
data = json.loads(resp.read().decode("utf-8"))
|
||||
return sorted(m["name"] for m in data.get("models", []))
|
||||
|
||||
headers = {}
|
||||
if backend == "unsloth":
|
||||
key = self._unsloth_api_key()
|
||||
if not key:
|
||||
logger.error("vlm_models: UNSLOTH_API_KEY is not set")
|
||||
return []
|
||||
headers["Authorization"] = f"Bearer {key}"
|
||||
req = urllib.request.Request(api_url.rstrip("/") + "/v1/models", headers=headers)
|
||||
with urllib.request.urlopen(req, timeout=5) as resp:
|
||||
data = json.loads(resp.read().decode("utf-8"))
|
||||
return sorted(m["name"] for m in data.get("models", []))
|
||||
return sorted(m["id"] for m in data.get("data", []))
|
||||
except Exception as e:
|
||||
logger.error("ollama_models: %s", e)
|
||||
logger.error("vlm_models: %s", e)
|
||||
return []
|
||||
|
||||
def ollama_predict(self, image_b64: str, api_url: str, model: str, prompt: str, max_tags: int = 40) -> dict:
|
||||
payload = json.dumps({
|
||||
"model": model,
|
||||
"messages": [{"role": "user", "content": prompt, "images": [image_b64]}],
|
||||
"stream": False,
|
||||
"options": {"temperature": 0.7, "num_ctx": 4096},
|
||||
}).encode("utf-8")
|
||||
def vlm_predict(self, image_b64: str, backend: str, api_url: str, model: str, prompt: str, max_tags: int = 40,
|
||||
thinking_mode: bool = False, max_tokens: int = 0) -> dict:
|
||||
backend = (backend or "ollama").lower()
|
||||
try:
|
||||
req = urllib.request.Request(
|
||||
api_url.rstrip("/") + "/api/chat",
|
||||
data=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
method="POST",
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=180) as resp:
|
||||
data = json.loads(resp.read().decode("utf-8"))
|
||||
content = data.get("message", {}).get("content", "")
|
||||
if backend == "ollama":
|
||||
body = {
|
||||
"model": model,
|
||||
"messages": [{"role": "user", "content": prompt, "images": [image_b64]}],
|
||||
"stream": False,
|
||||
"think": bool(thinking_mode),
|
||||
"options": {"temperature": 0.7, "num_ctx": 4096},
|
||||
}
|
||||
if max_tokens > 0:
|
||||
body["options"]["num_predict"] = max_tokens
|
||||
payload = json.dumps(body).encode("utf-8")
|
||||
req = urllib.request.Request(
|
||||
api_url.rstrip("/") + "/api/chat",
|
||||
data=payload,
|
||||
headers={"Content-Type": "application/json"},
|
||||
method="POST",
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=180) as resp:
|
||||
data = json.loads(resp.read().decode("utf-8"))
|
||||
content = data.get("message", {}).get("content", "")
|
||||
else:
|
||||
headers = {"Content-Type": "application/json"}
|
||||
if backend == "unsloth":
|
||||
key = self._unsloth_api_key()
|
||||
if not key:
|
||||
return {"error": "UNSLOTH_API_KEY is not set. Copy .env.example to .env in the "
|
||||
"plugin folder, fill in the key, and restart ComfyUI."}
|
||||
headers["Authorization"] = f"Bearer {key}"
|
||||
body = {
|
||||
"model": model,
|
||||
"messages": [{"role": "user", "content": [
|
||||
{"type": "text", "text": prompt},
|
||||
{"type": "image_url", "image_url": {"url": f"data:image/jpeg;base64,{image_b64}"}},
|
||||
]}],
|
||||
"stream": False,
|
||||
}
|
||||
if max_tokens > 0:
|
||||
body["max_tokens"] = max_tokens
|
||||
payload = json.dumps(body).encode("utf-8")
|
||||
req = urllib.request.Request(
|
||||
api_url.rstrip("/") + "/v1/chat/completions",
|
||||
data=payload,
|
||||
headers=headers,
|
||||
method="POST",
|
||||
)
|
||||
with urllib.request.urlopen(req, timeout=180) as resp:
|
||||
data = json.loads(resp.read().decode("utf-8"))
|
||||
message = data.get("choices", [{}])[0].get("message", {})
|
||||
content = message.get("content", "")
|
||||
# Unslothはreasoningを別フィールドで返すため<think>タグに畳んで統一的に扱う
|
||||
reasoning = message.get("reasoning_content")
|
||||
if reasoning:
|
||||
content = f"<think>{reasoning}</think>{content}"
|
||||
|
||||
if not thinking_mode:
|
||||
content = self._strip_thinking_tags(content)
|
||||
tags = [t.strip() for t in content.split(",") if t.strip()][:max_tags]
|
||||
return {"tags": ", ".join(tags), "count": len(tags)}
|
||||
except Exception as e:
|
||||
logger.error("ollama_predict: %s", e)
|
||||
logger.error("vlm_predict: %s", e)
|
||||
return {"error": str(e)}
|
||||
|
||||
# ── ファイルメタデータ書込 ────────────────────────────────
|
||||
@@ -334,8 +418,9 @@ class TaggerService:
|
||||
self._batch_state["stop"] = True
|
||||
|
||||
def batch_start(self, folder: str, model_name: str, threshold: float, char_threshold: float,
|
||||
use_ollama: bool, ollama_api: str, ollama_model: str, ollama_prompt: str,
|
||||
ollama_max_tags: int, save_db: bool, write_file: bool, write_txt: bool, db_service) -> dict:
|
||||
use_ollama: bool, vlm_backend: str, vlm_api_url: str, ollama_model: str, ollama_prompt: str,
|
||||
ollama_max_tags: int, save_db: bool, write_file: bool, write_txt: bool, db_service,
|
||||
thinking_mode: bool = False, max_tokens: int = 0) -> dict:
|
||||
if self._batch_state["running"]:
|
||||
return {"error": "Batch already running"}
|
||||
folder_path = Path(folder)
|
||||
@@ -370,7 +455,8 @@ class TaggerService:
|
||||
|
||||
vlm_tags = ""
|
||||
if use_ollama and ollama_model:
|
||||
res2 = self.ollama_predict(b64, ollama_api, ollama_model, ollama_prompt, ollama_max_tags)
|
||||
res2 = self.vlm_predict(b64, vlm_backend, vlm_api_url, ollama_model, ollama_prompt, ollama_max_tags,
|
||||
thinking_mode, max_tokens)
|
||||
vlm_tags = res2.get("tags", "")
|
||||
|
||||
all_tags = ", ".join(filter(None, [interrogator_tags, vlm_tags]))
|
||||
|
||||
@@ -0,0 +1,143 @@
|
||||
"""Video tab plan file management service (JSON plan + optional PNG index thumbnail).
|
||||
|
||||
Duplicated from LabPlanService rather than shared — the two plan formats are
|
||||
unrelated (batch keyframe columns vs. sequential timeline blocks) and would
|
||||
gain nothing from a forced common base beyond coincidental line-count savings.
|
||||
"""
|
||||
|
||||
import base64
|
||||
import json
|
||||
import logging
|
||||
from datetime import datetime, timezone
|
||||
from pathlib import Path
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
class VideoPlanService:
|
||||
def __init__(self, plan_dir: Path):
|
||||
self.plan_dir = plan_dir
|
||||
self.plan_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# Path safety
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def _safe_path(self, filename: str, ext: str = ".json") -> Path | None:
|
||||
if not filename or not filename.strip():
|
||||
return None
|
||||
name = filename.strip()
|
||||
if not name.endswith(ext):
|
||||
name = name + ext
|
||||
if "/" in name or "\\" in name or name in (".", "..") or "\x00" in name:
|
||||
return None
|
||||
resolved = (self.plan_dir / name).resolve()
|
||||
plan_dir_resolved = self.plan_dir.resolve()
|
||||
if resolved != plan_dir_resolved and not str(resolved).startswith(str(plan_dir_resolved) + "\\") and not str(resolved).startswith(str(plan_dir_resolved) + "/"):
|
||||
return None
|
||||
return resolved
|
||||
|
||||
def _now_iso(self) -> str:
|
||||
return datetime.now(timezone.utc).isoformat().replace("+00:00", "Z")
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# CRUD
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
def list_plans(self) -> list[dict]:
|
||||
if not self.plan_dir.is_dir():
|
||||
return []
|
||||
result = []
|
||||
for path in sorted(self.plan_dir.glob("*.json")):
|
||||
try:
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
data = json.load(f)
|
||||
except Exception as e:
|
||||
logger.warning("Skipping unreadable video plan %s: %s", path.name, e)
|
||||
continue
|
||||
|
||||
stem = path.stem
|
||||
thumbnail = None
|
||||
thumb_path = self.plan_dir / f"{stem}.png"
|
||||
if thumb_path.is_file():
|
||||
thumbnail = f"/wfm_data/video_plan/{stem}.png"
|
||||
|
||||
result.append({
|
||||
"filename": path.name,
|
||||
"name": data.get("name", stem),
|
||||
"note": data.get("note", ""),
|
||||
"block_count": len(data.get("blocks", [])),
|
||||
"updated_at": data.get("updated_at", ""),
|
||||
"thumbnail": thumbnail,
|
||||
})
|
||||
result.sort(key=lambda p: p.get("updated_at", ""), reverse=True)
|
||||
return result
|
||||
|
||||
def get_plan(self, filename: str) -> dict:
|
||||
path = self._safe_path(filename)
|
||||
if path is None:
|
||||
raise ValueError(f"Invalid filename: {filename}")
|
||||
if not path.is_file():
|
||||
raise FileNotFoundError(f"Plan not found: {filename}")
|
||||
with open(path, "r", encoding="utf-8") as f:
|
||||
return json.load(f)
|
||||
|
||||
def save_plan(self, filename: str, data: dict, index_image_base64: str | None = None) -> dict:
|
||||
path = self._safe_path(filename)
|
||||
if path is None:
|
||||
raise ValueError(f"Invalid filename: {filename}")
|
||||
|
||||
data = dict(data)
|
||||
data["updated_at"] = self._now_iso()
|
||||
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
with open(path, "w", encoding="utf-8") as f:
|
||||
json.dump(data, f, ensure_ascii=False, indent=2)
|
||||
|
||||
if index_image_base64:
|
||||
self.save_index_image(filename, index_image_base64)
|
||||
|
||||
return {"filename": path.name, "updated_at": data["updated_at"]}
|
||||
|
||||
def save_index_image(self, filename: str, image_base64: str) -> None:
|
||||
path = self._safe_path(filename)
|
||||
if path is None:
|
||||
raise ValueError(f"Invalid filename: {filename}")
|
||||
stem = path.stem
|
||||
thumb_path = self.plan_dir / f"{stem}.png"
|
||||
|
||||
# Accept both raw base64 and data: URL forms
|
||||
b64 = image_base64
|
||||
if "," in b64 and b64.strip().lower().startswith("data:"):
|
||||
b64 = b64.split(",", 1)[1]
|
||||
|
||||
image_bytes = base64.b64decode(b64)
|
||||
with open(thumb_path, "wb") as f:
|
||||
f.write(image_bytes)
|
||||
|
||||
def save_index_image_to_output(self, image_base64: str, filename_prefix: str = "Video_index") -> dict:
|
||||
"""Saves the contact-sheet index image into ComfyUI's own output folder,
|
||||
alongside the videos generated during the run (unlike save_index_image,
|
||||
which saves it next to the plan file in plan_dir)."""
|
||||
b64 = image_base64
|
||||
if "," in b64 and b64.strip().lower().startswith("data:"):
|
||||
b64 = b64.split(",", 1)[1]
|
||||
image_bytes = base64.b64decode(b64)
|
||||
|
||||
import folder_paths # type: ignore
|
||||
output_dir = folder_paths.get_output_directory()
|
||||
full_output_folder, filename, counter, subfolder, _ = folder_paths.get_save_image_path(filename_prefix, output_dir)
|
||||
save_name = f"{filename}_{counter:05}_.png"
|
||||
save_path = Path(full_output_folder) / save_name
|
||||
save_path.write_bytes(image_bytes)
|
||||
return {"filename": save_name, "subfolder": subfolder}
|
||||
|
||||
def delete_plan(self, filename: str) -> None:
|
||||
path = self._safe_path(filename)
|
||||
if path is None:
|
||||
raise ValueError(f"Invalid filename: {filename}")
|
||||
if path.is_file():
|
||||
path.unlink()
|
||||
thumb_path = self.plan_dir / f"{path.stem}.png"
|
||||
if thumb_path.is_file():
|
||||
thumb_path.unlink()
|
||||
@@ -4,7 +4,7 @@ import jinja2
|
||||
from aiohttp import web
|
||||
from pathlib import Path
|
||||
|
||||
from .config import TEMPLATES_DIR, STATIC_DIR, DATA_DIR, WORKFLOWS_DIR, LAB_PLAN_DIR
|
||||
from .config import TEMPLATES_DIR, STATIC_DIR, DATA_DIR, WORKFLOWS_DIR, LAB_PLAN_DIR, VIDEO_PLAN_DIR
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
@@ -57,6 +57,22 @@ async def serve_lab_plan_file(request: web.Request) -> web.Response:
|
||||
})
|
||||
|
||||
|
||||
async def serve_video_plan_file(request: web.Request) -> web.Response:
|
||||
"""Serve files (index thumbnails) from the Video plan directory."""
|
||||
filename = request.match_info.get("filename", "")
|
||||
if not filename or ".." in filename or "/" in filename or "\\" in filename:
|
||||
return web.Response(status=404)
|
||||
|
||||
file_path = VIDEO_PLAN_DIR / filename
|
||||
if not file_path.is_file():
|
||||
return web.Response(status=404)
|
||||
|
||||
content_type, _ = mimetypes.guess_type(str(file_path))
|
||||
return web.FileResponse(file_path, headers={
|
||||
"Content-Type": content_type or "application/octet-stream",
|
||||
})
|
||||
|
||||
|
||||
class WorkflowStudio:
|
||||
"""Main entry point for Workflow Studio plugin."""
|
||||
|
||||
@@ -76,6 +92,9 @@ class WorkflowStudio:
|
||||
# Dynamic Lab plan file serving (index thumbnails)
|
||||
app.router.add_get("/wfm_data/lab_plan/{filename}", serve_lab_plan_file)
|
||||
|
||||
# Dynamic Video plan file serving (index thumbnails)
|
||||
app.router.add_get("/wfm_data/video_plan/{filename}", serve_video_plan_file)
|
||||
|
||||
# Main page
|
||||
app.router.add_get("/wfm", serve_index_page)
|
||||
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
[project]
|
||||
name = "comfyui-workflow-studio"
|
||||
description = "A comprehensive workflow, asset management, and generation UI plugin for ComfyUI. Manage workflows, models, images, and prompts; batch generation and Image Feeder in the GenerateUI tab; library side panel with canvas drag & drop and AI tools."
|
||||
version = "0.5.2"
|
||||
license = "MIT"
|
||||
version = "0.5.7"
|
||||
license = { file = "LICENSE" }
|
||||
requires-python = ">= 3.10"
|
||||
dependencies = ["jinja2"]
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
/* =============================================
|
||||
Video Tab (MiniMax H3専用・GenerateUIタブとは独立)
|
||||
3ペイン構成: 左=フォーム / 中央=プレビュー+編集 / 右=プロパティ
|
||||
Video Tab (MiniMax H3 / LTX-2.5 / Wan2.2対応・GenerateUIタブとは独立)
|
||||
3ペイン構成: 左=Plan/Asset/Editサブタブ / 中央=プレビュー+Video Source / 右=プロパティ
|
||||
中央・右ペインは左のサブタブ切替と無関係に常時表示される。
|
||||
各ペインは独立したカラムとして高さ100%を占め、内部でスクロールする。
|
||||
中央ペインのコンテンツ量(生成結果の有無・動画の縦横比)が変わっても
|
||||
左右のペインの位置が動かないよう、意図的に高さを共有させない構造にしている。
|
||||
@@ -37,44 +38,324 @@
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
|
||||
.wfm-video-header {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 2px;
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
|
||||
.wfm-video-header h3 {
|
||||
margin: 0;
|
||||
}
|
||||
|
||||
.wfm-video-wf-name {
|
||||
color: var(--wfm-text-secondary);
|
||||
font-size: 13px;
|
||||
}
|
||||
|
||||
.wfm-video-frame-slots {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr 1fr;
|
||||
gap: 12px;
|
||||
/* ── Plan/Asset/Edit サブタブナビ(Lab/Galleryと同型) ── */
|
||||
.wfm-video-subtab-nav {
|
||||
display: flex;
|
||||
border-bottom: 1px solid var(--wfm-border);
|
||||
flex-shrink: 0;
|
||||
margin: -16px -16px 12px;
|
||||
padding: 0 16px;
|
||||
}
|
||||
|
||||
.wfm-video-frame-slot {
|
||||
.wfm-video-subtab-btn {
|
||||
padding: 6px 16px;
|
||||
font-size: 12px;
|
||||
background: transparent;
|
||||
border: none;
|
||||
color: var(--wfm-text-secondary);
|
||||
cursor: pointer;
|
||||
border-bottom: 2px solid transparent;
|
||||
margin-bottom: -1px;
|
||||
transition: color 0.15s;
|
||||
}
|
||||
|
||||
.wfm-video-subtab-btn:hover { color: var(--wfm-text-primary); }
|
||||
.wfm-video-subtab-btn.active { color: var(--wfm-primary); border-bottom-color: var(--wfm-primary); }
|
||||
|
||||
/* 中央ペイン用のタブナビ: プレビュー行の"下"に来るため、サイドバー版と違って
|
||||
上マージンは潰さない(プレビュー行と重ならないようにする)。左右のみ潰して
|
||||
center-panelのpadding分フルブリードにする。 */
|
||||
.wfm-video-center-subtab-nav {
|
||||
margin: 0 -16px 12px;
|
||||
}
|
||||
|
||||
.wfm-video-subtab-panel {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 10px;
|
||||
}
|
||||
|
||||
/* ── Plan: タイムライン(各ブロックのdurationに応じてflex-growで幅配分) ── */
|
||||
.wfm-video-timeline-wrap {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 6px;
|
||||
}
|
||||
|
||||
.wfm-video-timeline-track {
|
||||
display: flex;
|
||||
height: 40px;
|
||||
border-radius: 4px;
|
||||
overflow: hidden;
|
||||
border: 1px solid var(--wfm-border);
|
||||
}
|
||||
|
||||
.wfm-video-timeline-block {
|
||||
flex-basis: 0;
|
||||
min-width: 24px;
|
||||
cursor: pointer;
|
||||
border-right: 1px solid rgba(0, 0, 0, 0.3);
|
||||
transition: outline 0.1s;
|
||||
}
|
||||
|
||||
.wfm-video-timeline-block:last-child { border-right: none; }
|
||||
.wfm-video-timeline-block.selected { outline: 2px solid var(--wfm-primary); outline-offset: -2px; }
|
||||
|
||||
.wfm-video-timeline-toolbar {
|
||||
display: flex;
|
||||
gap: 6px;
|
||||
}
|
||||
|
||||
/* ── Plan: 中央下部に配置されるコンテンツ全体(Planサブタブ選択時のみ表示) ── */
|
||||
.wfm-video-plan-topbar {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 8px;
|
||||
}
|
||||
|
||||
/* 現在ロード中のワークフロー名 + Planに記録されたワークフローのOpen Workflow行を
|
||||
同じ1行にまとめる(以前は縦に2行だった)。 */
|
||||
.wfm-video-wf-row {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 10px;
|
||||
flex-wrap: wrap;
|
||||
}
|
||||
|
||||
.wfm-video-wf-row .wfm-lab-plan-workflow-row { margin-top: 0; }
|
||||
|
||||
.wfm-video-plan-basesettings {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(5, 150px);
|
||||
gap: 10px;
|
||||
}
|
||||
|
||||
/* ── Plan: 2行目の追加設定(Width/Height/Turbo Mode/Strength/Steps/Prompt Enhance)。
|
||||
basesettingsと同じ見た目だが、ワークフローによって対応する項目が変わる可変集合の
|
||||
ため別クラスに分けている ── */
|
||||
.wfm-video-plan-extrasettings {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(6, 130px);
|
||||
gap: 10px;
|
||||
}
|
||||
|
||||
.wfm-video-plan-basesettings label,
|
||||
.wfm-video-plan-extrasettings label {
|
||||
display: block;
|
||||
font-size: 12px;
|
||||
color: var(--wfm-text-secondary);
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
|
||||
/* Noise Seed欄: 数値入力とRandomizeチェックボックスを1セル内で横並びにする */
|
||||
.wfm-video-seed-inline {
|
||||
display: flex;
|
||||
gap: 6px;
|
||||
align-items: center;
|
||||
}
|
||||
|
||||
.wfm-video-seed-inline .wfm-input { flex: 1; min-width: 0; }
|
||||
|
||||
.wfm-video-seed-randomize-inline {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 3px;
|
||||
font-size: 11px;
|
||||
white-space: nowrap;
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
/* Turbo Mode / Prompt Enhance欄: ラベル行の下にチェックボックスを1つだけ置く
|
||||
(他のnumber/select欄と縦位置を揃えるため、input要素の高さを合わせる) */
|
||||
.wfm-video-checkbox-inline {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
gap: 4px;
|
||||
height: 30px;
|
||||
font-size: 12px;
|
||||
margin-bottom: 0;
|
||||
}
|
||||
|
||||
/* タイムラインの下: ブロックエディタ(左、横並びの3カラム) + Run/Planタブ(右) */
|
||||
.wfm-video-plan-main-row {
|
||||
display: flex;
|
||||
gap: 16px;
|
||||
align-items: flex-start;
|
||||
}
|
||||
|
||||
/* ── Plan: ブロックエディタ(選択中ブロックのFirst/Last Image・Prompt。Durationはtopbarの
|
||||
basesettings行に移動済み。中央の広いエリアに配置されるため横並びの3カラムで表示する) ── */
|
||||
.wfm-video-block-editor {
|
||||
flex: 1;
|
||||
min-width: 0;
|
||||
display: flex;
|
||||
gap: 16px;
|
||||
}
|
||||
|
||||
.wfm-video-block-col label {
|
||||
display: block;
|
||||
font-size: 12px;
|
||||
color: var(--wfm-text-secondary);
|
||||
margin-bottom: 4px;
|
||||
}
|
||||
|
||||
.wfm-video-block-first-col,
|
||||
.wfm-video-block-last-col {
|
||||
width: 190px;
|
||||
flex: none;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
.wfm-video-resolution-row {
|
||||
display: grid;
|
||||
grid-template-columns: 1fr 1fr 1fr;
|
||||
gap: 10px;
|
||||
align-items: end;
|
||||
.wfm-video-block-prompt-col {
|
||||
flex: 1;
|
||||
min-width: 220px;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
.wfm-video-seed-randomize-wrap {
|
||||
.wfm-video-block-prompt-col textarea {
|
||||
flex: 1;
|
||||
resize: none;
|
||||
}
|
||||
|
||||
.wfm-video-block-color-row {
|
||||
display: flex;
|
||||
align-items: center;
|
||||
padding-bottom: 6px;
|
||||
gap: 6px;
|
||||
font-size: 11px;
|
||||
color: var(--wfm-text-secondary);
|
||||
margin-bottom: 6px;
|
||||
}
|
||||
|
||||
.wfm-video-color-swatch {
|
||||
display: inline-block;
|
||||
width: 14px;
|
||||
height: 14px;
|
||||
border-radius: 3px;
|
||||
border: 1px solid var(--wfm-border);
|
||||
}
|
||||
|
||||
/* ── Plan: Run/Planタブ(実行系・プラン管理系を切替表示するコンパクトなウィジェット) ── */
|
||||
.wfm-video-runplan-panel {
|
||||
width: 260px;
|
||||
flex: none;
|
||||
}
|
||||
|
||||
.wfm-video-runplan-tabnav {
|
||||
display: flex;
|
||||
gap: 4px;
|
||||
margin-bottom: 10px;
|
||||
border-bottom: 1px solid var(--wfm-border);
|
||||
}
|
||||
|
||||
.wfm-video-runplan-tab {
|
||||
flex: 1;
|
||||
background: none;
|
||||
border: none;
|
||||
padding: 6px 4px;
|
||||
cursor: pointer;
|
||||
color: var(--wfm-text-secondary);
|
||||
border-bottom: 2px solid transparent;
|
||||
font-size: 13px;
|
||||
}
|
||||
|
||||
.wfm-video-runplan-tab.active {
|
||||
color: var(--wfm-text);
|
||||
border-bottom-color: var(--wfm-primary);
|
||||
}
|
||||
|
||||
.wfm-video-runplan-content {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
}
|
||||
|
||||
/* ── Asset: 素材グリッド・詳細パネル ── */
|
||||
.wfm-video-asset-grid {
|
||||
display: grid;
|
||||
grid-template-columns: repeat(2, 1fr);
|
||||
gap: 8px;
|
||||
max-height: 320px;
|
||||
overflow-y: auto;
|
||||
}
|
||||
|
||||
.wfm-video-asset-card {
|
||||
cursor: pointer;
|
||||
border: 1px solid var(--wfm-border);
|
||||
border-radius: 4px;
|
||||
overflow: hidden;
|
||||
transition: outline 0.1s;
|
||||
}
|
||||
|
||||
.wfm-video-asset-card.selected { outline: 2px solid var(--wfm-primary); outline-offset: -2px; }
|
||||
|
||||
.wfm-video-asset-card-img {
|
||||
width: 100%;
|
||||
aspect-ratio: 1;
|
||||
object-fit: cover;
|
||||
display: block;
|
||||
background: var(--wfm-bg-hover, #111);
|
||||
}
|
||||
|
||||
.wfm-video-asset-card-name {
|
||||
font-size: 10px;
|
||||
padding: 2px 4px;
|
||||
overflow: hidden;
|
||||
text-overflow: ellipsis;
|
||||
white-space: nowrap;
|
||||
color: var(--wfm-text-secondary);
|
||||
}
|
||||
|
||||
.wfm-video-asset-detail {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 6px;
|
||||
border-top: 1px solid var(--wfm-border);
|
||||
padding-top: 10px;
|
||||
}
|
||||
|
||||
.wfm-video-asset-detail label {
|
||||
font-size: 12px;
|
||||
color: var(--wfm-text-secondary);
|
||||
}
|
||||
|
||||
.wfm-video-asset-name {
|
||||
font-size: 12px;
|
||||
font-weight: 600;
|
||||
overflow: hidden;
|
||||
text-overflow: ellipsis;
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.wfm-video-asset-tags {
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
gap: 4px;
|
||||
}
|
||||
|
||||
.wfm-video-asset-tag {
|
||||
display: inline-flex;
|
||||
align-items: center;
|
||||
gap: 2px;
|
||||
background: var(--wfm-bg-secondary);
|
||||
border: 1px solid var(--wfm-border);
|
||||
border-radius: 10px;
|
||||
padding: 1px 8px;
|
||||
font-size: 11px;
|
||||
}
|
||||
|
||||
.wfm-video-asset-tag button {
|
||||
background: none;
|
||||
border: none;
|
||||
color: var(--wfm-text-secondary);
|
||||
cursor: pointer;
|
||||
padding: 0;
|
||||
font-size: 11px;
|
||||
}
|
||||
|
||||
/* ── 中央ペイン: プレビュー + 編集 ── */
|
||||
@@ -89,8 +370,9 @@
|
||||
border-right: 1px solid var(--wfm-border);
|
||||
}
|
||||
|
||||
/* 生成結果 or ソース選択エリアで読み込んだ動画を横並びで表示する行。
|
||||
プレビュー枠が主役、ソースパネルは選択UIのみの固定幅。 */
|
||||
/* 3カラム構成: 左=Video Source選択UI(固定幅) / 中央=Asset選択・Sourceドロップ兼用
|
||||
プレビュー / 右=生成結果専用プレビュー。.wfm-video-preview-frameは共通クラスなので
|
||||
両プレビュー枠とも自動的にflex:1で均等幅になる。 */
|
||||
.wfm-video-preview-row {
|
||||
flex: none;
|
||||
display: flex;
|
||||
@@ -108,6 +390,7 @@
|
||||
border: 1px dashed var(--wfm-border);
|
||||
border-radius: 6px;
|
||||
background: var(--wfm-bg-hover, #111);
|
||||
text-align: center;
|
||||
}
|
||||
|
||||
.wfm-video-preview-el {
|
||||
@@ -183,3 +466,70 @@
|
||||
flex-direction: column;
|
||||
gap: 6px;
|
||||
}
|
||||
|
||||
/* ── 左ペイン Project サブタブ: 保存済みPlan一覧 ── */
|
||||
.wfm-video-project-list {
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 6px;
|
||||
max-height: 60vh;
|
||||
overflow-y: auto;
|
||||
}
|
||||
|
||||
.wfm-video-project-item {
|
||||
display: flex;
|
||||
gap: 8px;
|
||||
align-items: center;
|
||||
border: 1px solid var(--wfm-border);
|
||||
border-radius: 4px;
|
||||
padding: 6px;
|
||||
cursor: pointer;
|
||||
}
|
||||
|
||||
.wfm-video-project-item:hover { border-color: var(--wfm-primary); }
|
||||
.wfm-video-project-item.active { outline: 2px solid var(--wfm-primary); outline-offset: -2px; }
|
||||
|
||||
.wfm-video-project-item-thumb {
|
||||
width: 40px;
|
||||
height: 40px;
|
||||
flex: none;
|
||||
object-fit: cover;
|
||||
border-radius: 3px;
|
||||
background: var(--wfm-bg-hover, #111);
|
||||
}
|
||||
|
||||
.wfm-video-project-item-info {
|
||||
flex: 1;
|
||||
min-width: 0;
|
||||
display: flex;
|
||||
flex-direction: column;
|
||||
gap: 2px;
|
||||
}
|
||||
|
||||
.wfm-video-project-item-name {
|
||||
font-size: 12px;
|
||||
font-weight: 600;
|
||||
overflow: hidden;
|
||||
text-overflow: ellipsis;
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.wfm-video-project-item-meta {
|
||||
font-size: 10px;
|
||||
color: var(--wfm-text-secondary);
|
||||
overflow: hidden;
|
||||
text-overflow: ellipsis;
|
||||
white-space: nowrap;
|
||||
}
|
||||
|
||||
.wfm-video-project-item-delete {
|
||||
flex: none;
|
||||
background: none;
|
||||
border: none;
|
||||
color: var(--wfm-text-secondary);
|
||||
cursor: pointer;
|
||||
font-size: 14px;
|
||||
padding: 2px 6px;
|
||||
}
|
||||
|
||||
.wfm-video-project-item-delete:hover { color: var(--wfm-danger); }
|
||||
|
||||
@@ -0,0 +1,205 @@
|
||||
/**
|
||||
* Shared AI backend settings modal (Backend / Connection / Model / Generation / Unload / Save).
|
||||
* Used by the Prompt tab and Tagger tab, each with its own localStorage key so their
|
||||
* settings stay independent — mirrors the AI TOOL tab's own settings pane (ai-tab.js).
|
||||
*/
|
||||
|
||||
import { openModal, closeModal, showToast } from "./app.js";
|
||||
import { t } from "./i18n.js";
|
||||
import { readJsonStorage, getAiBackendDefaultUrl, unslothProxy, unloadAiModel } from "./util.js";
|
||||
|
||||
function loadCfg(storageKey) {
|
||||
return readJsonStorage(storageKey);
|
||||
}
|
||||
|
||||
function saveCfg(storageKey, patch) {
|
||||
const data = { ...loadCfg(storageKey), ...patch };
|
||||
localStorage.setItem(storageKey, JSON.stringify(data));
|
||||
return data;
|
||||
}
|
||||
|
||||
// 保存済み設定を {backend, url, model, thinkingMode, maxTokens} の形で返す
|
||||
export function getAiBackendConfig(storageKey) {
|
||||
const s = loadCfg(storageKey);
|
||||
const backend = s.backend || "ollama";
|
||||
const url = (s.backendUrl || getAiBackendDefaultUrl(backend)).replace(/\/$/, "");
|
||||
return {
|
||||
backend,
|
||||
url,
|
||||
model: s.model || "",
|
||||
thinkingMode: !!s.thinkingMode,
|
||||
maxTokens: Math.max(0, parseInt(s.maxTokens, 10) || 0),
|
||||
};
|
||||
}
|
||||
|
||||
function isValidBackendUrl(url) {
|
||||
try {
|
||||
const u = new URL(url);
|
||||
return u.protocol === "http:" || u.protocol === "https:";
|
||||
} catch {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
|
||||
async function fetchBackendModels(url, backend) {
|
||||
if (backend === "ollama") {
|
||||
const res = await fetch(`${url}/api/tags`);
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
return (await res.json()).models?.map(m => m.name) || [];
|
||||
} else if (backend === "unsloth") {
|
||||
const data = await unslothProxy(url, "/v1/models", "GET");
|
||||
return (data.data || []).map(m => m.id);
|
||||
} else {
|
||||
const res = await fetch(`${url}/v1/models`);
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
return ((await res.json()).data || []).map(m => m.id);
|
||||
}
|
||||
}
|
||||
|
||||
/**
|
||||
* @param {string} storageKey localStorage key holding {backend, backendUrl, model, thinkingMode, maxTokens}
|
||||
* @param {string} title modal title
|
||||
* @param {() => void} [onSaved] called after Save persists the config (e.g. to refresh a status label)
|
||||
*/
|
||||
export function openAiBackendSettingsModal(storageKey, title, onSaved) {
|
||||
const saved = loadCfg(storageKey);
|
||||
const backend = saved.backend || "ollama";
|
||||
|
||||
const html = `
|
||||
<div class="wfm-ai-settings-container">
|
||||
<div class="wfm-ai-settings-section">
|
||||
<div class="wfm-ai-settings-title">${t("aiSettingsBackend")}</div>
|
||||
<div class="wfm-ai-backend-row">
|
||||
${[["ollama", "Ollama"], ["lmstudio", "LM Studio"], ["lemonade", "Lemonade"], ["unsloth", "Unsloth"]].map(([v, label]) => `
|
||||
<label class="wfm-ai-radio-label">
|
||||
<input type="radio" name="wfm-aism-backend" value="${v}" ${v === backend ? "checked" : ""}> ${label}
|
||||
</label>`).join("")}
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-ai-settings-section">
|
||||
<div class="wfm-ai-settings-title">${t("aiSettingsConnection")}</div>
|
||||
<div class="wfm-ai-settings-row">
|
||||
<label class="wfm-ai-label">URL</label>
|
||||
<input type="text" id="wfm-aism-url" class="wfm-input wfm-ai-url-input" value="${saved.backendUrl || getAiBackendDefaultUrl(backend)}">
|
||||
</div>
|
||||
<div class="wfm-ai-settings-row">
|
||||
<button id="wfm-aism-test-btn" class="wfm-btn">${t("aiSettingsTestBtn")}</button>
|
||||
<button id="wfm-aism-unload-btn" class="wfm-btn">${t("aiUnloadModel")}</button>
|
||||
</div>
|
||||
<div class="wfm-ai-settings-row">
|
||||
<span id="wfm-aism-test-result" class="wfm-ai-test-result"></span>
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-ai-settings-section">
|
||||
<div class="wfm-ai-settings-title">${t("aiSettingsModelSection")}</div>
|
||||
<div class="wfm-ai-settings-row">
|
||||
<select id="wfm-aism-model" class="wfm-select wfm-ai-model-select">
|
||||
<option value="">${t("selectModel")}</option>
|
||||
</select>
|
||||
<button id="wfm-aism-refresh-btn" class="wfm-btn">${t("aiSettingsRefreshBtn")}</button>
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-ai-settings-section">
|
||||
<div class="wfm-ai-settings-title">${t("aiSettingsGenerationTitle")}</div>
|
||||
<div class="wfm-ai-settings-row">
|
||||
<label class="wfm-ai-label" style="display:flex;align-items:center;gap:6px;cursor:pointer;">
|
||||
<input type="checkbox" id="wfm-aism-thinking"> ${t("aiSettingsThinkingMode")}
|
||||
</label>
|
||||
</div>
|
||||
<div class="wfm-ai-settings-row">
|
||||
<label class="wfm-ai-label">${t("aiSettingsMaxTokens")}</label>
|
||||
<input type="number" id="wfm-aism-max-tokens" class="wfm-input" min="0" step="1" placeholder="${t("aiSettingsMaxTokensPlaceholder")}">
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-ai-settings-section">
|
||||
<button id="wfm-aism-save-btn" class="wfm-btn wfm-btn-primary">${t("aiSettingsSaveBtn")}</button>
|
||||
</div>
|
||||
</div>`;
|
||||
|
||||
openModal(title, html);
|
||||
|
||||
const urlInput = document.getElementById("wfm-aism-url");
|
||||
const modelSelect = document.getElementById("wfm-aism-model");
|
||||
const thinkingCheckbox = document.getElementById("wfm-aism-thinking");
|
||||
const maxTokensInput = document.getElementById("wfm-aism-max-tokens");
|
||||
const testResultEl = document.getElementById("wfm-aism-test-result");
|
||||
|
||||
thinkingCheckbox.checked = !!saved.thinkingMode;
|
||||
if (saved.maxTokens) maxTokensInput.value = saved.maxTokens;
|
||||
|
||||
function currentBackend() {
|
||||
return document.querySelector("input[name='wfm-aism-backend']:checked")?.value || "ollama";
|
||||
}
|
||||
|
||||
async function populateModels(selectedModel) {
|
||||
const url = urlInput.value.trim();
|
||||
try {
|
||||
const models = await fetchBackendModels(url, currentBackend());
|
||||
modelSelect.innerHTML = models.length
|
||||
? models.map(name => `<option value="${name}" ${name === selectedModel ? "selected" : ""}>${name}</option>`).join("")
|
||||
: `<option value="">${t("noModelsFound")}</option>`;
|
||||
} catch {
|
||||
modelSelect.innerHTML = `<option value="">${t("noModelsFound")}</option>`;
|
||||
}
|
||||
}
|
||||
populateModels(saved.model || "");
|
||||
|
||||
document.querySelectorAll("input[name='wfm-aism-backend']").forEach(r => {
|
||||
r.addEventListener("change", () => {
|
||||
urlInput.value = getAiBackendDefaultUrl(r.value);
|
||||
testResultEl.textContent = "";
|
||||
});
|
||||
});
|
||||
|
||||
document.getElementById("wfm-aism-refresh-btn")?.addEventListener("click", () => populateModels(modelSelect.value));
|
||||
|
||||
document.getElementById("wfm-aism-test-btn")?.addEventListener("click", async () => {
|
||||
const url = urlInput.value.trim();
|
||||
if (!isValidBackendUrl(url)) {
|
||||
testResultEl.textContent = t("aiToastInvalidUrlInput");
|
||||
testResultEl.className = "wfm-ai-test-result wfm-ai-status-error";
|
||||
return;
|
||||
}
|
||||
testResultEl.textContent = t("aiStatusConnecting");
|
||||
testResultEl.className = "wfm-ai-test-result wfm-ai-status-working";
|
||||
try {
|
||||
const models = await fetchBackendModels(url, currentBackend());
|
||||
testResultEl.textContent = `${t("aiStatusConnectOk")} (${models.length} ${t("aiModels")})`;
|
||||
testResultEl.className = "wfm-ai-test-result wfm-ai-status-ok";
|
||||
await populateModels(modelSelect.value);
|
||||
} catch (err) {
|
||||
testResultEl.textContent = `${t("aiStatusConnectFail")}${err.message}`;
|
||||
testResultEl.className = "wfm-ai-test-result wfm-ai-status-error";
|
||||
}
|
||||
});
|
||||
|
||||
document.getElementById("wfm-aism-unload-btn")?.addEventListener("click", async () => {
|
||||
const url = urlInput.value.trim();
|
||||
const model = modelSelect.value;
|
||||
if (!model) { showToast(t("aiUnloadNoModel"), "error"); return; }
|
||||
try {
|
||||
await unloadAiModel(url, currentBackend(), model);
|
||||
showToast(t("aiUnloadDone"), "success");
|
||||
} catch (err) {
|
||||
showToast(err.message === "UNSUPPORTED" ? t("aiUnloadUnsupported") : t("aiUnloadFailed") + err.message, "error");
|
||||
}
|
||||
});
|
||||
|
||||
document.getElementById("wfm-aism-save-btn")?.addEventListener("click", () => {
|
||||
const url = urlInput.value.trim();
|
||||
if (url && !isValidBackendUrl(url)) {
|
||||
showToast(t("aiToastInvalidUrl"), "error");
|
||||
return;
|
||||
}
|
||||
saveCfg(storageKey, {
|
||||
backend: currentBackend(),
|
||||
backendUrl: url,
|
||||
model: modelSelect.value,
|
||||
thinkingMode: !!thinkingCheckbox.checked,
|
||||
maxTokens: Math.max(0, parseInt(maxTokensInput.value, 10) || 0),
|
||||
});
|
||||
showToast(t("aiToastSettingsSaved"), "success");
|
||||
closeModal();
|
||||
if (onSaved) onSaved();
|
||||
});
|
||||
}
|
||||
@@ -5,7 +5,7 @@
|
||||
|
||||
import { showToast } from "./app.js";
|
||||
import { t } from "./i18n.js";
|
||||
import { readJsonStorage, getAiBackendDefaultUrl, escapeHtml } from "./util.js";
|
||||
import { readJsonStorage, getAiBackendDefaultUrl, escapeHtml, unloadAiModel } from "./util.js";
|
||||
import { comfyUI } from "./comfyui-client.js";
|
||||
import { comfyEditor } from "./comfyui-editor.js";
|
||||
import { comfyWorkflow } from "./comfyui-workflow.js";
|
||||
@@ -456,6 +456,20 @@ function initSettingsTab() {
|
||||
}
|
||||
});
|
||||
|
||||
// Unload model
|
||||
document.getElementById("wfm-ai-unload-btn")?.addEventListener("click", async () => {
|
||||
const backend = document.querySelector("input[name='wfm-ai-backend']:checked")?.value || "ollama";
|
||||
const url = urlInput?.value?.trim() || "";
|
||||
const model = document.getElementById("wfm-ai-model-select")?.value || "";
|
||||
if (!model) { showToast(t("aiUnloadNoModel"), "error"); return; }
|
||||
try {
|
||||
await unloadAiModel(url, backend, model);
|
||||
showToast(t("aiUnloadDone"), "success");
|
||||
} catch (err) {
|
||||
showToast(err.message === "UNSUPPORTED" ? t("aiUnloadUnsupported") : t("aiUnloadFailed") + err.message, "error");
|
||||
}
|
||||
});
|
||||
|
||||
// Model refresh
|
||||
document.getElementById("wfm-ai-model-refresh-btn")?.addEventListener("click", () => refreshModels());
|
||||
|
||||
|
||||
@@ -319,10 +319,8 @@ function applyI18nToHtml() {
|
||||
if (assistantHeader) assistantHeader.textContent = t("assistantSubtab");
|
||||
const presetsHeader = document.querySelector(".wfm-prompt-split-right .wfm-prompt-split-header");
|
||||
if (presetsHeader) presetsHeader.textContent = t("presetsSubtab");
|
||||
const ollamaRefreshBtn = document.getElementById("wfm-ollama-refresh-btn");
|
||||
if (ollamaRefreshBtn) ollamaRefreshBtn.textContent = t("refresh");
|
||||
const ollamaTestBtn = document.getElementById("wfm-ollama-test-btn");
|
||||
if (ollamaTestBtn) ollamaTestBtn.textContent = t("test");
|
||||
const ollamaSettingsBtn = document.getElementById("wfm-ollama-settings-btn");
|
||||
if (ollamaSettingsBtn) ollamaSettingsBtn.title = t("settings");
|
||||
const ollamaAttachBtn = document.getElementById("wfm-ollama-attach-btn");
|
||||
if (ollamaAttachBtn) ollamaAttachBtn.textContent = t("attachImage");
|
||||
const ollamaClearBtn = document.getElementById("wfm-ollama-clear-btn");
|
||||
@@ -487,6 +485,7 @@ function applyI18nToHtml() {
|
||||
"wfm-help-gen-28": "helpGen28",
|
||||
"wfm-help-gen-29": "helpGen29",
|
||||
"wfm-help-gen-30": "helpGen30",
|
||||
"wfm-help-gen-31": "helpGen31",
|
||||
"wfm-help-feeder-title": "helpFeederTitle",
|
||||
"wfm-help-feeder-desc": "helpFeederDesc",
|
||||
"wfm-help-feeder-imgloop-title": "helpFeederImgloopTitle",
|
||||
@@ -736,7 +735,8 @@ function applyI18nToHtml() {
|
||||
"wfm-help-video-1": "helpVideo1", "wfm-help-video-2": "helpVideo2",
|
||||
"wfm-help-video-3": "helpVideo3", "wfm-help-video-4": "helpVideo4",
|
||||
"wfm-help-video-5": "helpVideo5", "wfm-help-video-6": "helpVideo6",
|
||||
"wfm-help-video-7": "helpVideo7",
|
||||
"wfm-help-video-7": "helpVideo7", "wfm-help-video-8": "helpVideo8",
|
||||
"wfm-help-video-9": "helpVideo9", "wfm-help-video-10": "helpVideo10",
|
||||
};
|
||||
for (const [id, key] of Object.entries(helpIdMap)) {
|
||||
const el = document.getElementById(id);
|
||||
|
||||
@@ -1446,6 +1446,12 @@ export const comfyEditor = {
|
||||
<label>Batch Size</label>
|
||||
<input type="number" class="wfm-input" id="wfm-settings-batch" value="${latent.batch_size ?? 1}" min="1" max="64">
|
||||
</div>
|
||||
${latent.isVideoLatent ? `
|
||||
<div class="wfm-form-group">
|
||||
<label>Length (frames)</label>
|
||||
<input type="number" class="wfm-input" id="wfm-settings-latent-length" value="${latent.length ?? ""}" placeholder="${latent.length === undefined ? "linked" : ""}" step="1" min="1">
|
||||
</div>
|
||||
` : ""}
|
||||
<button class="wfm-btn wfm-btn-sm" id="wfm-settings-latent-apply">Apply</button>
|
||||
${latent.width === undefined || latent.height === undefined ? `<p class="wfm-placeholder" style="margin-top:6px;">Width/Height is linked to another node (e.g. auto-follows the input image) — leave blank to keep it linked.</p>` : ""}
|
||||
<div style="margin-top:10px;border-top:1px solid var(--wfm-border);padding-top:10px;">
|
||||
@@ -1502,6 +1508,8 @@ export const comfyEditor = {
|
||||
if (wEl?.value !== "") inputs.width = parseInt(wEl.value) || 512;
|
||||
if (hEl?.value !== "") inputs.height = parseInt(hEl.value) || 512;
|
||||
inputs.batch_size = parseInt(document.getElementById("wfm-settings-batch")?.value) || 1;
|
||||
const lenEl = document.getElementById("wfm-settings-latent-length");
|
||||
if (lenEl && lenEl.value !== "") inputs.length = parseInt(lenEl.value) || 1;
|
||||
_syncRawJson();
|
||||
});
|
||||
|
||||
|
||||
@@ -75,6 +75,35 @@ async function _loadObjectInfo() {
|
||||
* Get ordered widget (non-link) input names for a node class from object_info.
|
||||
* These correspond to widgets_values in UI-format nodes.
|
||||
*/
|
||||
// Scalar widget types object_info can declare for a required/optional input.
|
||||
const _WIDGET_TYPE_SET = new Set(["INT", "FLOAT", "STRING", "BOOLEAN", "COMBO", "COMFY_DYNAMICCOMBO_V3"]);
|
||||
|
||||
/**
|
||||
* Resolve a possibly-compound object_info type spec (e.g. LTXVEmptyLatentAudio's frame_rate:
|
||||
* "FLOAT,INT", a MultiType declaration meaning "widget defaults to FLOAT but also accepts an INT
|
||||
* link") down to the single scalar widget type it actually occupies a widgets_values slot as.
|
||||
* Preferring the explicit widgetType hint some MultiType specs carry, else the first comma-
|
||||
* separated segment. Returns null for link-only types (MODEL, CLIP, LATENT, etc.) or arrays that
|
||||
* aren't combo option lists.
|
||||
*
|
||||
* Without this, a plain `upper === "INT" || ...` exact-match check silently drops any
|
||||
* comma-joined MultiType widget from the name/type lists entirely — which corrupts every widget
|
||||
* declared after it in the node's schema order in _simulateWidgetValues (see its own docstring),
|
||||
* exactly the class of bug that produced e.g. LTXVEmptyLatentAudio's batch_size reading
|
||||
* frame_rate's stale value instead of its own.
|
||||
*/
|
||||
function _resolveWidgetType(type, spec) {
|
||||
if (Array.isArray(type)) return "COMBO";
|
||||
if (typeof type !== "string") return null;
|
||||
const explicit = spec?.[1]?.widgetType;
|
||||
if (typeof explicit === "string" && _WIDGET_TYPE_SET.has(explicit.toUpperCase())) return explicit.toUpperCase();
|
||||
for (const part of type.split(",")) {
|
||||
const upper = part.trim().toUpperCase();
|
||||
if (_WIDGET_TYPE_SET.has(upper)) return upper;
|
||||
}
|
||||
return null;
|
||||
}
|
||||
|
||||
function _getWidgetInputNames(objectInfo, classType) {
|
||||
const info = objectInfo[classType];
|
||||
if (!info) return [];
|
||||
@@ -89,31 +118,16 @@ function _getWidgetInputNames(objectInfo, classType) {
|
||||
// (e.g. CLIPTextEncodeEditPlus's text1/text2). Never has a widgets_values entry.
|
||||
if (Array.isArray(spec) && spec[1]?.forceInput) continue;
|
||||
// Link types are strings like "MODEL", "CLIP", "CONDITIONING", "LATENT", "IMAGE", etc.
|
||||
// Widget types are: "INT", "FLOAT", "STRING", "BOOLEAN", or an array of choices
|
||||
if (Array.isArray(type)) {
|
||||
// Combo/enum widget
|
||||
names.push(name);
|
||||
} else if (typeof type === "string") {
|
||||
const upper = type.toUpperCase();
|
||||
if (upper === "INT" || upper === "FLOAT" || upper === "STRING" || upper === "BOOLEAN" || upper === "COMBO" || upper === "COMFY_DYNAMICCOMBO_V3") {
|
||||
names.push(name);
|
||||
}
|
||||
// Other uppercase types (MODEL, CLIP, etc.) are link inputs, skip
|
||||
}
|
||||
// Widget types are: "INT", "FLOAT", "STRING", "BOOLEAN", an array of choices, or a
|
||||
// comma-joined MultiType union of those (e.g. "FLOAT,INT") — see _resolveWidgetType.
|
||||
if (_resolveWidgetType(type, spec)) names.push(name);
|
||||
}
|
||||
|
||||
// Optional inputs that are widgets
|
||||
for (const [name, spec] of Object.entries(optional)) {
|
||||
const type = Array.isArray(spec) ? spec[0] : spec;
|
||||
if (Array.isArray(spec) && spec[1]?.forceInput) continue;
|
||||
if (Array.isArray(type)) {
|
||||
names.push(name);
|
||||
} else if (typeof type === "string") {
|
||||
const upper = type.toUpperCase();
|
||||
if (upper === "INT" || upper === "FLOAT" || upper === "STRING" || upper === "BOOLEAN" || upper === "COMFY_DYNAMICCOMBO_V3") {
|
||||
names.push(name);
|
||||
}
|
||||
}
|
||||
if (_resolveWidgetType(type, spec)) names.push(name);
|
||||
}
|
||||
|
||||
return names;
|
||||
@@ -133,26 +147,14 @@ function _getWidgetInputTypes(objectInfo, classType) {
|
||||
for (const [name, spec] of Object.entries(required)) {
|
||||
const type = Array.isArray(spec) ? spec[0] : spec;
|
||||
if (Array.isArray(spec) && spec[1]?.forceInput) continue;
|
||||
if (Array.isArray(type)) {
|
||||
types.push("COMBO");
|
||||
} else if (typeof type === "string") {
|
||||
const upper = type.toUpperCase();
|
||||
if (upper === "INT" || upper === "FLOAT" || upper === "STRING" || upper === "BOOLEAN" || upper === "COMBO" || upper === "COMFY_DYNAMICCOMBO_V3") {
|
||||
types.push(upper);
|
||||
}
|
||||
}
|
||||
const resolved = _resolveWidgetType(type, spec);
|
||||
if (resolved) types.push(resolved);
|
||||
}
|
||||
for (const [name, spec] of Object.entries(optional)) {
|
||||
const type = Array.isArray(spec) ? spec[0] : spec;
|
||||
if (Array.isArray(spec) && spec[1]?.forceInput) continue;
|
||||
if (Array.isArray(type)) {
|
||||
types.push("COMBO");
|
||||
} else if (typeof type === "string") {
|
||||
const upper = type.toUpperCase();
|
||||
if (upper === "INT" || upper === "FLOAT" || upper === "STRING" || upper === "BOOLEAN" || upper === "COMBO" || upper === "COMFY_DYNAMICCOMBO_V3") {
|
||||
types.push(upper);
|
||||
}
|
||||
}
|
||||
const resolved = _resolveWidgetType(type, spec);
|
||||
if (resolved) types.push(resolved);
|
||||
}
|
||||
return types;
|
||||
}
|
||||
@@ -614,6 +616,18 @@ export const comfyWorkflow = {
|
||||
return _lastMutedNodes;
|
||||
},
|
||||
|
||||
// Forces the next convertUiToApi() call to refetch /object_info instead of
|
||||
// reusing the cached snapshot. Needed whenever a file gets uploaded mid-session
|
||||
// after the cache was already populated (e.g. Video Plan's block-chaining
|
||||
// uploads an extracted frame between batch iterations) — a stale cache's
|
||||
// LoadImage "image" COMBO choices wouldn't include the just-uploaded filename
|
||||
// yet, so the COMBO-mismatch fallback a few lines below (silently substituting
|
||||
// choices[0] when a value isn't in the known list — see the file-level comment
|
||||
// at the top) would replace it with an unrelated pre-existing file instead.
|
||||
invalidateObjectInfoCache() {
|
||||
_objectInfoCache = null;
|
||||
},
|
||||
|
||||
async convertUiToApi(workflow) {
|
||||
_lastCheckpointSubstitutions = [];
|
||||
_lastBypassedNodes = [];
|
||||
@@ -962,6 +976,14 @@ export const comfyWorkflow = {
|
||||
if (Array.isArray(inputs.positive)) samplerPositiveRef[inputs.positive[0]] = true;
|
||||
if (Array.isArray(inputs.negative)) samplerNegativeRef[inputs.negative[0]] = true;
|
||||
}
|
||||
// LTXVDualCFGGuider (LTX-2.5's video+audio guider) — positive/negative both
|
||||
// commonly point at the *same* LTXVConditioning node (different output slots),
|
||||
// so this only seeds the role on that node; LTXVConditioning below splits it
|
||||
// back out per-slot onto its own positive/negative inputs.
|
||||
if (ct === "LTXVDualCFGGuider") {
|
||||
if (Array.isArray(inputs.positive)) samplerPositiveRef[inputs.positive[0]] = true;
|
||||
if (Array.isArray(inputs.negative)) samplerNegativeRef[inputs.negative[0]] = true;
|
||||
}
|
||||
}
|
||||
|
||||
// === Pass 1b: Expand refs through CONDITIONING graph (BFS, 5 iterations) ===
|
||||
@@ -1038,6 +1060,13 @@ export const comfyWorkflow = {
|
||||
if (isPos && Array.isArray(inputs.positive)) samplerPositiveRef[inputs.positive[0]] = true;
|
||||
if (isNeg && Array.isArray(inputs.negative)) samplerNegativeRef[inputs.negative[0]] = true;
|
||||
}
|
||||
// LTXVConditioning (LTX-2.5) — same shape as InstructPixToPixConditioning:
|
||||
// separate positive/negative inputs feeding separate outputs consumed by
|
||||
// LTXVDualCFGGuider, so each role must route only to its own input.
|
||||
if (ct === "LTXVConditioning") {
|
||||
if (isPos && Array.isArray(inputs.positive)) samplerPositiveRef[inputs.positive[0]] = true;
|
||||
if (isNeg && Array.isArray(inputs.negative)) samplerNegativeRef[inputs.negative[0]] = true;
|
||||
}
|
||||
// ComfySwitchNode ("If/Else Switch", on_false/on_true/switch) — used by Ernie
|
||||
// Image's prompt-enhancement toggle to pick between the raw PrimitiveStringMultiline
|
||||
// text and an LLM-generated (TextGenerate) rewrite. The rewrite can't be known
|
||||
@@ -1363,6 +1392,21 @@ export const comfyWorkflow = {
|
||||
});
|
||||
}
|
||||
|
||||
// Video latent nodes (Wan2.2's EmptyHunyuanLatentVideo, LTX-2.5's
|
||||
// EmptyLTXVLatentVideo) — same width/height/batch_size shape as EmptyLatentImage
|
||||
// plus a frame-count "length" input, usually linked to a duration*fps expression
|
||||
// (see video-tab.js's own Wan2.2/LTX-2.5 handling) rather than a literal number —
|
||||
// left undefined in that case so the settings-tab UI shows "linked".
|
||||
if (ct === "EmptyHunyuanLatentVideo" || ct === "EmptyLTXVLatentVideo") {
|
||||
result.latent_nodes.push({
|
||||
id, type: ct, title, isVideoLatent: true,
|
||||
width: typeof inputs.width === "number" ? inputs.width : undefined,
|
||||
height: typeof inputs.height === "number" ? inputs.height : undefined,
|
||||
batch_size: inputs.batch_size,
|
||||
length: typeof inputs.length === "number" ? inputs.length : undefined,
|
||||
});
|
||||
}
|
||||
|
||||
// ResolutionSelector (ComfyUI core, comfy_extras.nodes_resolution): typically
|
||||
// feeds an EmptyLatentImage's width/height rather than being a latent node
|
||||
// itself. aspect_ratio is a fixed-choice COMBO (e.g. "3:2 (Photo)") — its exact
|
||||
@@ -1537,7 +1581,12 @@ export const comfyWorkflow = {
|
||||
// generation timeout (video generation runs far longer than a still image) — see
|
||||
// generate-tab.js _coreGenerate and lab-tab.js _runLabBatch.
|
||||
isVideoWorkflow(analysis) {
|
||||
return (analysis?.prompt_nodes || []).some((n) => /ImageToVideo|TextToVideo/.test(n.type));
|
||||
if ((analysis?.prompt_nodes || []).some((n) => /ImageToVideo|TextToVideo/.test(n.type))) return true;
|
||||
// LTX-2.5/Wan2.2: no all-in-one *ToVideo node — detected instead via their
|
||||
// EmptyHunyuanLatentVideo/EmptyLTXVLatentVideo latent node (see analyzeWorkflow)
|
||||
// or a SaveVideo/CreateVideo node anywhere in the flattened graph.
|
||||
if ((analysis?.latent_nodes || []).some((n) => n.isVideoLatent)) return true;
|
||||
return (analysis?.all_nodes || []).some((n) => n.type === "SaveVideo" || n.type === "CreateVideo");
|
||||
},
|
||||
|
||||
applyParams(workflow, params) {
|
||||
|
||||
@@ -14,6 +14,7 @@ import { comfyEditor } from "./comfyui-editor.js";
|
||||
import { callLLM, loadAiSettings, isValidBackendUrl } from "./ai-tab.js";
|
||||
import { initImagePromptTab, activateImagePromptTab } from "./image-prompt-tab.js";
|
||||
import { initStyleCatalogTab, activateStyleCatalogTab } from "./style-catalog-tab.js";
|
||||
import { applyStoredVideoVolume } from "./settings-tab.js";
|
||||
|
||||
// ── 定数 ─────────────────────────────────────────────────────
|
||||
|
||||
@@ -45,6 +46,16 @@ const API = {
|
||||
};
|
||||
|
||||
export const FEEDER_GROUP = "__Feeder__";
|
||||
export const VIDEO_GROUP = "__Video Assets__";
|
||||
// Video Planを実行するたびに生成された動画が自動的に追加される作業用グループ
|
||||
// (Plan保存の有無に関わらず常にここへ入る)。__Video Assets__(ユーザーが手動で
|
||||
// キュレーションする素材グループ)への整理はユーザー任意のタイミングで行う。
|
||||
export const VTEMP_GROUP = "__Video Temp__";
|
||||
|
||||
const _RESERVED_GROUPS = [FEEDER_GROUP, VIDEO_GROUP, VTEMP_GROUP];
|
||||
function _isReservedGroup(name) {
|
||||
return _RESERVED_GROUPS.includes(name);
|
||||
}
|
||||
|
||||
// 拡張子から動画ファイル(mp4)かどうかを判定する。
|
||||
// 一覧アイテムは path/filename、詳細メタ(get_image_metadata)は ext フィールドを持つため両対応。
|
||||
@@ -467,6 +478,16 @@ function renderTreeNode(node, container, depth, isRoot) {
|
||||
|
||||
container.appendChild(item);
|
||||
container.appendChild(childContainer);
|
||||
|
||||
// root フォルダはデフォルトで展開状態にする(フォルダスキャン高速化により
|
||||
// サブフォルダの内容もすぐ確認できるようになったため、折りたたみ初期状態だと
|
||||
// 気付きにくい)
|
||||
if (isRoot) {
|
||||
arrow.dataset.expanded = "true";
|
||||
arrow.textContent = "▼";
|
||||
childContainer.style.display = "";
|
||||
node.children.forEach(child => renderTreeNode(child, childContainer, depth + 1, false));
|
||||
}
|
||||
} else {
|
||||
container.appendChild(item);
|
||||
}
|
||||
@@ -488,8 +509,14 @@ async function loadImages() {
|
||||
if (state.favoriteOnly) params.favorite = "true";
|
||||
if (state.tagFilter) params.tag = state.tagFilter;
|
||||
|
||||
// グループフィルタはサーバーサイドで処理
|
||||
if (state.groupFilter) params.group = state.groupFilter;
|
||||
// グループフィルタはサーバーサイドで処理。グループのメンバーは現在のフォルダの
|
||||
// サブフォルダに散らばっている可能性がある(例: 動画は"video"サブフォルダ配下)ため、
|
||||
// 通常のフォルダ単位ブラウズ(非再帰)とは異なり、フィルタ時はフォルダ配下を再帰的に
|
||||
// 検索する。
|
||||
if (state.groupFilter) {
|
||||
params.group = state.groupFilter;
|
||||
params.recursive = "true";
|
||||
}
|
||||
|
||||
try {
|
||||
const images = (await apiFetch(API.images(params))).images || [];
|
||||
@@ -910,7 +937,9 @@ async function loadImageDetail(img) {
|
||||
${mediaHtml}
|
||||
</div>
|
||||
`;
|
||||
preview.querySelector(isVideo ? "video" : "img").addEventListener("dblclick", () => openLightbox(img));
|
||||
const previewMediaEl = preview.querySelector(isVideo ? "video" : "img");
|
||||
previewMediaEl.addEventListener("dblclick", () => openLightbox(img));
|
||||
if (isVideo) applyStoredVideoVolume(previewMediaEl);
|
||||
|
||||
// ファイル名
|
||||
document.getElementById("wfm-gallery-detail-filename").textContent = img.filename;
|
||||
@@ -1122,6 +1151,33 @@ export async function ensureFeederGroup() {
|
||||
}
|
||||
}
|
||||
|
||||
/** __Video Assets__ と __Video Temp__ の両方が存在しない場合に作成する。add_to_groupは
|
||||
* 対象グループがレジストリに登録されているかを確認せず画像側にグループ名を書き込むだけの
|
||||
* ため、一度レジストリから消える(例: 予約保護が効く前の版で削除された)と、以後の手動追加は
|
||||
* 画像には記録されてもグループ一覧・フィルタには一切出てこなくなる。VideoタブのAsset
|
||||
* タブ初期化時に呼び、レジストリを確実に存在させる。
|
||||
* (__Video Temp__側もここでensureする — 以前はensureVideoGroupがVIDEO_GROUPしか
|
||||
* 保証しておらず、__Video Temp__のレジストリが何らかの理由で消えると誰も復活させられない
|
||||
* バグがあった。バッチRun開始時のensure(video-plan-tab.jsの_ensureVideoAssetGroups)は
|
||||
* Runするまで呼ばれないため、それだけでは不十分。) */
|
||||
export async function ensureVideoGroup() {
|
||||
try {
|
||||
await fetch(API.groupEnsure, {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ name: VIDEO_GROUP }),
|
||||
});
|
||||
await fetch(API.groupEnsure, {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ name: VTEMP_GROUP }),
|
||||
});
|
||||
await loadGroups();
|
||||
} catch (e) {
|
||||
console.warn("[Gallery] ensureVideoGroup error:", e);
|
||||
}
|
||||
}
|
||||
|
||||
/** Feederグループ内の全画像を除外する(FC ボタン) */
|
||||
async function clearFeederGroup() {
|
||||
try {
|
||||
@@ -1136,6 +1192,19 @@ async function clearFeederGroup() {
|
||||
}
|
||||
}
|
||||
|
||||
/** __Video Temp__グループ内の全画像を除外する(詳細パネルの「Clear __Video Temp__」ボタン) */
|
||||
async function clearVtempGroup() {
|
||||
try {
|
||||
await fetch(API.groupClear(VTEMP_GROUP), { method: "POST" });
|
||||
showToast(t("vtempGroupCleared"), "success");
|
||||
if (state.groupFilter === VTEMP_GROUP) {
|
||||
await loadImages();
|
||||
}
|
||||
} catch (e) {
|
||||
showToast(t("errorWithMsg", e.message), "error");
|
||||
}
|
||||
}
|
||||
|
||||
/** ツールバーのグループフィルタと一括バーのセレクトを更新 */
|
||||
function _updateGroupSelects() {
|
||||
// ツールバー: グループフィルタ
|
||||
@@ -1215,15 +1284,16 @@ function renderDetailGroup(img) {
|
||||
${allGroups.length === 0
|
||||
? `<option value="">${t("modelsNoGroupAvailable")}</option>`
|
||||
: allGroups.map(g => {
|
||||
const label = g === FEEDER_GROUP ? `🔒 ${escapeHtml(g)}` : escapeHtml(g);
|
||||
const label = _isReservedGroup(g) ? `🔒 ${escapeHtml(g)}` : escapeHtml(g);
|
||||
return `<option value="${escapeHtml(g)}">${label}</option>`;
|
||||
}).join("")}
|
||||
</select>
|
||||
<button class="wfm-btn wfm-btn-sm" id="wfm-gallery-grp-rename-btn"
|
||||
${allGroups.length === 0 || allGroups[0] === FEEDER_GROUP ? "disabled" : ""} title="${t("modelsRename")}">✎</button>
|
||||
${allGroups.length === 0 || _isReservedGroup(allGroups[0]) ? "disabled" : ""} title="${t("modelsRename")}">✎</button>
|
||||
<button class="wfm-btn wfm-btn-sm wfm-btn-danger" id="wfm-gallery-grp-delete-btn"
|
||||
${allGroups.length === 0 || allGroups[0] === FEEDER_GROUP ? "disabled" : ""} title="${t("modelsDelete")}">×</button>
|
||||
${allGroups.length === 0 || _isReservedGroup(allGroups[0]) ? "disabled" : ""} title="${t("modelsDelete")}">×</button>
|
||||
</div>
|
||||
<button class="wfm-btn wfm-btn-sm" id="wfm-gallery-vtemp-clear-btn" style="width:100%;margin-top:6px;" title="${t("vtempClearBtnTitle")}">${t("vtempClearBtnLabel")}</button>
|
||||
</div>
|
||||
</div>
|
||||
`;
|
||||
@@ -1302,15 +1372,18 @@ function renderDetailGroup(img) {
|
||||
}
|
||||
});
|
||||
|
||||
// 管理セレクト変更時: __Feeder__ は rename/delete を無効化
|
||||
// 管理セレクト変更時: 予約グループ(__Feeder__/__Video Assets__/__Video Temp__)は rename/delete を無効化
|
||||
el.querySelector("#wfm-gallery-grp-manage-sel")?.addEventListener("change", (e) => {
|
||||
const isReserved = e.target.value === FEEDER_GROUP;
|
||||
const isReserved = _isReservedGroup(e.target.value);
|
||||
const renameBtn = el.querySelector("#wfm-gallery-grp-rename-btn");
|
||||
const deleteBtn = el.querySelector("#wfm-gallery-grp-delete-btn");
|
||||
if (renameBtn) renameBtn.disabled = isReserved;
|
||||
if (deleteBtn) deleteBtn.disabled = isReserved;
|
||||
});
|
||||
|
||||
// Clear __Video Temp__ ボタン: __Video Temp__ グループをクリア(Video Plan実行時に自動登録される生成物置き場)
|
||||
el.querySelector("#wfm-gallery-vtemp-clear-btn")?.addEventListener("click", clearVtempGroup);
|
||||
|
||||
// グループ名変更
|
||||
el.querySelector("#wfm-gallery-grp-rename-btn")?.addEventListener("click", async () => {
|
||||
const sel = el.querySelector("#wfm-gallery-grp-manage-sel");
|
||||
@@ -1647,6 +1720,7 @@ function openLightbox(img) {
|
||||
}
|
||||
});
|
||||
document.body.appendChild(overlay);
|
||||
if (isVideoFile(img)) applyStoredVideoVolume(overlay.querySelector("video"));
|
||||
}
|
||||
|
||||
// ── 画像比較ライトボックス ─────────────────────────────────────
|
||||
@@ -1682,6 +1756,7 @@ function openCompare(paths) {
|
||||
}
|
||||
});
|
||||
document.body.appendChild(overlay);
|
||||
overlay.querySelectorAll("video").forEach(applyStoredVideoVolume);
|
||||
}
|
||||
|
||||
// ── outputパス取得 ────────────────────────────────────────────
|
||||
|
||||
@@ -293,6 +293,13 @@ export async function loadWorkflowIntoEditor(workflow, filename) {
|
||||
|
||||
refreshFeederNodeList();
|
||||
|
||||
// Lab subtab may already be the active one (e.g. it was active when this workflow
|
||||
// was loaded) — the subtab-click handler that normally triggers this refresh never
|
||||
// fires in that case, leaving Setting 1's live-reflected cells showing the previous
|
||||
// workflow until the user clicks a cell or revisits the subtab.
|
||||
const activeSubtab = document.querySelector(".wfm-gen-subtab-btn.active")?.dataset.subtab;
|
||||
if (activeSubtab === "lab") refreshLabLiveDefaults();
|
||||
|
||||
if (ckptWarning) {
|
||||
showToast(ckptWarning, "error");
|
||||
} else {
|
||||
@@ -2284,10 +2291,11 @@ export async function initGenerateTab() {
|
||||
});
|
||||
searchOverlay.innerHTML = html + "\n";
|
||||
|
||||
// Scroll editor to current match
|
||||
// Scroll editor to current match. フォーカス/selectionRangeは意図的に設定しない
|
||||
// (テキストエリアにカーソルが当たった状態になり、検索直後のキー入力が選択範囲を
|
||||
// 上書きして不意にJSONを編集してしまうため)。ハイライトはsearchOverlayの<mark>
|
||||
// 表示のみで行い、編集はユーザーが明示的にエディタをクリックした場合に限る。
|
||||
const pos = matchPositions[currentMatchIndex];
|
||||
editor.focus();
|
||||
editor.setSelectionRange(pos, pos + term.length);
|
||||
const lineNum = (text.slice(0, pos).match(/\n/g) || []).length;
|
||||
const lineH = parseFloat(getComputedStyle(editor).lineHeight) || 18;
|
||||
editor.scrollTop = Math.max(0, lineH * lineNum - editor.clientHeight / 2);
|
||||
|
||||
@@ -186,6 +186,9 @@ const LANGUAGES = {
|
||||
feederGalNoNode: "No WFS_GalleryFeeder node selected",
|
||||
feederGalEmptyGroup: "No images in the selected group",
|
||||
feederGroupCleared: "Feeder group cleared",
|
||||
vtempGroupCleared: "__Video Temp__ group cleared",
|
||||
vtempClearBtnLabel: "Clear __Video Temp__",
|
||||
vtempClearBtnTitle: "Clear the __Video Temp__ group (video generations land here automatically; organize keepers into __Video Assets__ manually anytime)",
|
||||
addedToFeeder: "Added to Feeder",
|
||||
removedFromFeeder: "Removed from Feeder",
|
||||
appliedToWorkflow: "Applied to workflow",
|
||||
@@ -329,6 +332,8 @@ const LANGUAGES = {
|
||||
textSizeLabel: "Text Size",
|
||||
textSizeTextarea: "Prompt / Chat Textarea",
|
||||
textSizeHint: "Applies to: Generate UI prompts, AI Assistant chat, Preset prompts, Wildcard textarea, Metadata prompt preview",
|
||||
videoVolumeLabel: "Video Volume",
|
||||
videoVolumeHint: "Applies to: Video tab preview, Gallery detail/lightbox/compare video players — the level you set here (or adjust via any video's own controls) carries over to the next video opened anywhere in the app.",
|
||||
jsonColorsSection: "RAW JSON Colors",
|
||||
jsonColorBase: "Base text",
|
||||
jsonColorYellow: "Names / Scheduler",
|
||||
@@ -646,7 +651,7 @@ const LANGUAGES = {
|
||||
taggerThreshold: "Threshold",
|
||||
taggerCharThreshold: "Char Thr.",
|
||||
taggerGenerateTags: "Generate Tags",
|
||||
taggerOllamaEnable: "Ollama VLM",
|
||||
taggerOllamaEnable: "VLM Tagging",
|
||||
taggerOllamaUrl: "API URL",
|
||||
taggerOllamaModel: "Model",
|
||||
taggerOllamaPrompt: "Prompt",
|
||||
@@ -715,6 +720,12 @@ const LANGUAGES = {
|
||||
aiSettingsInputLang: "Input",
|
||||
aiSettingsOutputLang: "Output",
|
||||
aiSettingsSaveBtn: "Save Settings",
|
||||
aiUnloadModel: "Unload Model",
|
||||
aiUnloading: "Unloading...",
|
||||
aiUnloadDone: "Model unloaded",
|
||||
aiUnloadFailed: "Unload failed: ",
|
||||
aiUnloadUnsupported: "This backend does not support unloading via API",
|
||||
aiUnloadNoModel: "Select a model first",
|
||||
aiToastNoText: "Please enter text",
|
||||
aiToastNoModel: "Please select a model in the Settings tab",
|
||||
aiToastInvalidUrl: "URL must start with http:// or https://",
|
||||
@@ -785,7 +796,8 @@ const LANGUAGES = {
|
||||
helpGen5: "Model tab: Checkpoint, VAE, Diffusion Model (UNETLoader / UnetLoaderGGUF / LoaderGGUF), Text Encoder (CLIPLoader / DualCLIPLoader / ClipLoaderGGUF / DualClipLoaderGGUF — type and device selectors; DualCLIP shows two clip selectors) are always shown; ControlNet and Hypernetwork (with Strength field) are collapsed by default since they're used less often — click their header to expand; LoRA (Single/Stack tabs) has its own column to the right; all selectors have a filter; LoRA Stack — Apply writes all active LoRAs to the target node and simultaneously inserts LoRA syntax and CivitAI trigger words into the Positive prompt; re-applying updates the prompt by removing inactive LoRAs and re-adding active ones",
|
||||
helpGen28: "Model tab — Highlight color: the label of each model type (Checkpoint, VAE, Diffusion Model, Text Encoder, ControlNet, Hypernetwork) and the LoRA column header turn a distinct color (default bright green) when the loaded workflow actually contains that type of node; this stays visible even while ControlNet/Hypernetwork are collapsed, so you can tell at a glance whether they're in use without expanding them; the color is customizable in the Settings tab",
|
||||
helpGen6: "Settings tab: KSampler and Latent Image side by side, each at 50% width",
|
||||
helpGen7: "Raw JSON always visible in the right column of each tab — edit directly and Apply to reload the workflow; if the loaded workflow has Bypass or Mute nodes, a note listing them appears above the search bar (Bypass nodes are excluded with their wires reconnected around them; Mute nodes are excluded with no reconnection, matching ComfyUI itself)",
|
||||
helpGen31: "LTX-2.5 and Wan2.2 video workflows also work when loaded as regular workflows in this tab (not just the dedicated Video tab): Positive/Negative Prompt detection follows LTX-2.5's LTXVDualCFGGuider / LTXVConditioning nodes to find the actual prompt text, and the Settings tab's Latent Image section recognizes Wan2.2's EmptyHunyuanLatentVideo and LTX-2.5's EmptyLTXVLatentVideo nodes (with an added Length (frames) field) instead of showing \"No EmptyLatentImage node found\"; generating from these workflows also gets the same extended timeout as MiniMax H3 video generations",
|
||||
helpGen7: "Raw JSON always visible in the right column of each tab — edit directly and Apply to reload the workflow; if the loaded workflow has Bypass or Mute nodes, a note listing them appears above the search bar (Bypass nodes are excluded with their wires reconnected around them; Mute nodes are excluded with no reconnection, matching ComfyUI itself); the search bar highlights matches and scrolls to them without moving the cursor into the editor, so typing right after a search can't accidentally overwrite the JSON — click into the editor first to actually edit",
|
||||
helpGen8: "Seed control: random, fixed, increment, decrement",
|
||||
helpGen9: "Generate, progress display, stop, and view results",
|
||||
helpGen10: "Eagle integration: auto-save generated images to Eagle (SVG output supported too — both the standard SaveSVGNode and comfyui-tosvg's Save SVG String node)",
|
||||
@@ -867,7 +879,7 @@ const LANGUAGES = {
|
||||
helpLabResults3: "Loading a saved plan restores its Results grid from the image list recorded in the plan file",
|
||||
|
||||
helpSearchPlaceholder: "Search help...",
|
||||
helpPrompt1: "AI assistant (Ollama / LM Studio / Lemonade): model selection, chat for prompt consultation, image attachment (vision models); backend and URL configured in Settings tab",
|
||||
helpPrompt1: "AI assistant (Ollama / LM Studio / Lemonade / Unsloth): chat for prompt consultation, image attachment (vision models); click the ⚙ Settings button to choose backend, connection URL, model, Thinking mode, Max tokens, and unload the loaded model — settings are independent from the AI TOOL and Tagger tabs",
|
||||
helpPrompt2: "Apply AI responses to GenerateUI prompts",
|
||||
helpPrompt3: "Translation: JA\u2194EN, ZH\u2194EN",
|
||||
helpPrompt4: "Preset management: create, edit, positive/negative prompt clipboard copy (PP/NP)",
|
||||
@@ -897,11 +909,11 @@ const LANGUAGES = {
|
||||
helpSettings2: "Theme selection (13 presets) with customization: color overrides, background patterns (stripes, polka dot, checkerboard, SVG tiling), and font selection (16 Google Fonts including Japanese display fonts)",
|
||||
helpSettings3: "Workflow data folder path",
|
||||
helpSettings4: "ComfyUI connection URL and test",
|
||||
helpSettings5: "AI Assistant (Prompt Tab): backend (Ollama / LM Studio / Lemonade), API URL, default model, and connection test",
|
||||
helpSettings5: "AI Assistant settings have moved out of this tab — the Prompt tab, Tagger tab, and AI TOOL tab each have their own ⚙ Settings button (backend, URL, model, Thinking mode, Max tokens, unload model), saved independently",
|
||||
helpSettings6: "Default workflow setting",
|
||||
helpSettings7: "Eagle integration URL and auto-save toggle",
|
||||
helpSettings8: "Data Management: export core settings, metadata, and prompts to a JSON file, or import to restore. After importing, restart ComfyUI.",
|
||||
helpSettings15: "Full Backup (ZIP): unlike the JSON export above, also includes folder-based data (AI Skills, Lab Plans, Style presets) and the Tagger database — everything the JSON export can't represent. Restoring overwrites existing files; restart ComfyUI afterward.",
|
||||
helpSettings15: "Full Backup (ZIP): unlike the JSON export above, also includes folder-based data (AI Skills, Lab Plans, Video Plans, Style presets) and the Tagger database — everything the JSON export can't represent. Restoring overwrites existing files; restart ComfyUI afterward.",
|
||||
helpSettings16: "Two opt-in checkboxes above the Full Backup buttons additionally include ComfyUI's default workflows folder and the Impact Pack's wildcard folder in the export — both export-only, never restored automatically; copy the ZIP's _external/ folder back by hand if you want them.",
|
||||
helpSettings9: "All sections are collapsible accordion panels",
|
||||
helpSettings10: "Wildcard Integration: link WFS wildcard dir to ComfyUI-Impact-Pack wildcards (directory junction on Windows / symlink on other OS); existing files migrated automatically",
|
||||
@@ -959,13 +971,13 @@ const LANGUAGES = {
|
||||
|
||||
// -- Tagger Tab --
|
||||
helpTaggerTitle: "Tagger Tab",
|
||||
helpTagger1: "Automatic image tagging using WD Tagger (ONNX), SwinV2, DeepDanbooru (.h5), and Ollama VLM — 3 sub-tabs: Single / Batch / DB",
|
||||
helpTagger1: "Automatic image tagging using WD Tagger (ONNX), SwinV2, DeepDanbooru (.h5), and VLM (Ollama / LM Studio / Lemonade / Unsloth) — 3 sub-tabs: Single / Batch / DB",
|
||||
helpTagger2: "Model placement: put each model in its own subfolder under ComfyUI/models/tagger/<model-name>/; the folder must contain a .onnx file + selected_tags.csv (or .h5 + label file for DeepDanbooru)",
|
||||
helpTagger3: "Single tab: drag & drop an image onto the preview area, or click Upload to pick a file; the Tagger button in the Gallery detail panel opens the selected image directly here",
|
||||
helpTagger4: "Threshold slider: minimum confidence score for general tags (default 0.35); Character Threshold: separate threshold for character: prefix tags (default 0.85)",
|
||||
helpTagger5: "Ollama VLM: enable the checkbox to run a vision model alongside WD Tagger; set API URL, select model (click ↻ to refresh), and customize the prompt; results from both models are merged",
|
||||
helpTagger5: "VLM Tagging: enable the checkbox to run a vision model alongside WD Tagger; click the ⚙ Settings button to choose backend (Ollama / LM Studio / Lemonade / Unsloth), URL, model, Thinking mode, Max tokens, and unload the model — independent from the Prompt tab's own AI settings; customize the prompt and Max Tags inline; results from both models are merged",
|
||||
helpTagger6: "Result tags can be sent to: (1) GenUI:P — appended to the GenerateUI tab's positive prompt textarea and applied to the loaded workflow immediately; (2) Send to Prompt — appended to the Prompt tab's positive textarea; (3) Save to Gallery — saved to Gallery image metadata (requires image opened from Gallery); (4) Write to File — embedded into JPEG EXIF (ImageDescription) or PNG tEXt (Tags key); (5) Save to DB — stored in the internal SQLite database",
|
||||
helpTagger7: "Batch tab: enter a folder path, configure WD Tagger and Ollama settings; output options: Save to DB (default on), Write to File (EXIF/PNG metadata), Write .txt (creates <filename>.txt alongside each image); click Start Batch to process all images in the folder; progress bar and log are updated in real time; Stop cancels after the current image",
|
||||
helpTagger7: "Batch tab: enter a folder path, configure WD Tagger and enable VLM tagging (uses the same ⚙ Settings as the Single tab); output options: Save to DB (default on), Write to File (EXIF/PNG metadata), Write .txt (creates <filename>.txt alongside each image); click Start Batch to process all images in the folder; progress bar and log are updated in real time; Stop cancels after the current image",
|
||||
helpTagger8: "DB tab: searchable database of all tagged images; click a row to open the edit panel and modify WD Tags / VLM Tags; Save updates the record, Delete removes it; Export CSV downloads all records as a CSV file",
|
||||
helpTagger9: "Install dependencies into ComfyUI's embedded Python: python_embeded\\python.exe -m pip install -r requirements.txt; for GPU ONNX inference install onnxruntime-gpu instead of onnxruntime; TensorFlow (for DeepDanbooru) is commented out by default due to size",
|
||||
|
||||
@@ -992,7 +1004,7 @@ const LANGUAGES = {
|
||||
helpAi2: "Translation pane: translate between Japanese, English, Chinese, or Free language using Ollama, LM Studio, Lemonade, or Unsloth; ⇄ swap button swaps both language selectors and text content; selections are saved automatically",
|
||||
helpAi3: "Chat pane: multi-turn conversation with the LLM; Enter to send a message, Shift+Enter for a newline; Clear button resets the conversation history; if the model supports tool calling and asks for an image (\"generate a cat picture\", etc.) it will run generation on the workflow currently loaded in GenerateUI and show the result inline; the \"Allow image generation\" checkbox in the pane header toggles this on/off; if an image is attached (dropped in the TOOLS pane) it is sent to the LLM as vision input and, when generate_image is called, used as the base for image-to-image generation instead of text-to-image; generate_image also accepts optional generation parameters the model can fill in from the request — steps, cfg, sampler_name, scheduler, denoise, seed, width, height, batch_size (number of images produced in that one call), and aspect_ratio (a ratio preset like \"3:2\", applied only if the workflow has a Resolution Selector node feeding width/height — ignored otherwise); anything the model doesn't supply keeps whatever the loaded workflow already has set; models verified to work well for tool calling and vision: Gemma 4:e4b, Qwen 3.5:9b, Ministral 3:3b (Ollama)",
|
||||
helpAi4: "TOOLS pane — VLM: drop an image (PNG/JPG/WebP) and select a task (Describe Image, Create Prompt, Create Tags), click Run; or select \"Create wildcards\", enter a category name and count to generate plain-text entries one per line; the dropped image is also shared with the Chat pane as its attachment (shown there and used for image-to-image generation) until cleared with the ✕ button",
|
||||
helpAi6: "Settings pane: choose backend (Ollama / LM Studio / Lemonade / Unsloth), set API URL, test connection, select model; Unsloth always requires an API key even for local access — set UNSLOTH_API_KEY in a .env file in the plugin folder (copy .env.example) and restart ComfyUI, the key is read server-side and never sent to the browser; Unsloth also requires \"Auto model switching (OpenAI API)\" to be turned ON in the Unsloth Desktop app itself (its own Settings screen) — without it, requests fail with HTTP 404 unless a model was already manually loaded in the Unsloth Studio UI; Unsloth reasoning models return their thinking in a separate reasoning_content field rather than inline <think> tags, so a low Max tokens can make the model spend its whole budget reasoning and return an empty reply — increase Max tokens (2048+) if replies come back blank; Generation section — Thinking mode toggle (off by default; Ollama receives a think flag, and regardless of backend any <think>...</think> block is stripped from the output when off, so reasoning models don't clutter Translation/Chat/TOOLS results) and Max tokens (Ollama: num_predict, LM Studio/Lemonade/Unsloth: max_tokens; 0 = unlimited); configure Free language names; Chat Image Generation section lets you enable a dedicated workflow for Chat-triggered text-to-image generation instead of the one currently loaded in GenerateUI; Chat I2I Generation section is the same but for image-to-image generation when an image is attached; settings are shared with the Library panel's A tab via localStorage",
|
||||
helpAi6: "Settings pane: choose backend (Ollama / LM Studio / Lemonade / Unsloth), set API URL, test connection, select model, and use the Unload Model button (next to Test connection) to free the loaded model from VRAM/memory — Ollama uses keep_alive:0, LM Studio uses /api/v1/models/unload, Lemonade uses /api/v1/unload; Unsloth has no unload API, so this shows an unsupported message for it; Unsloth always requires an API key even for local access — set UNSLOTH_API_KEY in a .env file in the plugin folder (copy .env.example) and restart ComfyUI, the key is read server-side and never sent to the browser; Unsloth also requires \"Auto model switching (OpenAI API)\" to be turned ON in the Unsloth Desktop app itself (its own Settings screen) — without it, requests fail with HTTP 404 unless a model was already manually loaded in the Unsloth Studio UI; Unsloth reasoning models return their thinking in a separate reasoning_content field rather than inline <think> tags, so a low Max tokens can make the model spend its whole budget reasoning and return an empty reply — increase Max tokens (2048+) if replies come back blank; Generation section — Thinking mode toggle (off by default; Ollama receives a think flag, and regardless of backend any <think>...</think> block is stripped from the output when off, so reasoning models don't clutter Translation/Chat/TOOLS results) and Max tokens (Ollama: num_predict, LM Studio/Lemonade/Unsloth: max_tokens; 0 = unlimited); configure Free language names; Chat Image Generation section lets you enable a dedicated workflow for Chat-triggered text-to-image generation instead of the one currently loaded in GenerateUI; Chat I2I Generation section is the same but for image-to-image generation when an image is attached; settings are shared with the Library panel's A tab via localStorage",
|
||||
helpAi7: "Chat pane — SVG: the LLM can also produce SVG graphics directly as text, with no ComfyUI workflow involved; ask it to draw something in SVG and, if the reply contains SVG code, it is rendered inline as a preview with a \"Save to Gallery\" button that writes it as a .svg file to the Gallery tab's output folder; this does not use tool calling, so it works with any model regardless of tool-calling support",
|
||||
helpAi8: "Chat pane — Skills: pick a skill from the dropdown above the message list to prepend its instructions to the conversation as a system prompt (not shown in the visible chat log); use the pencil button to open the skill manager and create, edit, or delete .md skill files, stored in user/default/Workflow-Studio/ai_skills/; a file's first line block between --- markers can define name/description shown in the dropdown; two starter skills are included by default: \"SVG Icon Generator\" (decomposes the subject into parts before drawing, for more recognizable SVG output) and \"Skill Creator\" (interviews you conversationally and drafts a new skill file, ready to save); when a reply contains a ```skill code block, a \"Save as new skill\" button appears below it that opens the manager with the draft pre-filled",
|
||||
helpAi9: "Tips for writing your own skills: give a clear frontmatter name/description so it reads well in the dropdown and tooltip; state the exact output format you want and, if there is a deliverable to extract later (like SVG or another skill file), wrap it in a distinctive fenced code block; write concrete, imperative instructions rather than vague ones - smaller local models follow explicit rules and a short worked example far better than general guidance; state hard constraints (forbidden content, security, length limits) explicitly rather than assuming they are implied; when in doubt, select the \"Skill Creator\" skill in the dropdown and describe what you want - it will interview you and draft the file for you",
|
||||
@@ -1218,7 +1230,7 @@ const LANGUAGES = {
|
||||
importError: "Import failed",
|
||||
exportFullBackup: "Full Backup (ZIP)",
|
||||
importFullBackup: "Restore Full Backup (ZIP)",
|
||||
fullBackupHint: "Full Backup (ZIP) additionally includes folder-based data (AI Skills, Lab Plans, Style presets) and the Tagger database — everything the JSON export above can't represent. Restoring overwrites existing files; restart ComfyUI afterward.",
|
||||
fullBackupHint: "Full Backup (ZIP) additionally includes folder-based data (AI Skills, Lab Plans, Video Plans, Style presets) and the Tagger database — everything the JSON export above can't represent. Restoring overwrites existing files; restart ComfyUI afterward.",
|
||||
fullBackupFilesUnit: "files",
|
||||
fullBackupIncludeWorkflows: "Include default workflows folder (user/default/workflows)",
|
||||
fullBackupIncludeWildcard: "Include Impact Pack wildcard folder (if present)",
|
||||
@@ -1315,31 +1327,29 @@ const LANGUAGES = {
|
||||
helpMetadata5: "Supported: ComfyUI PNG/WebP/MP4/JSON (standard + Flux.2 / Qwen-Image / Z-Image / Mage-Flow / LongCat / Boogu / HiDream E1 / FireRed / Ernie Image subgraph workflows; MP4 reads the workflow/prompt container tags written by SaveVideo, including all-in-one video nodes like MiniMax H3 ImageToVideo), SD WebUI, SD Forge, Fooocus.",
|
||||
helpMetadata6: "This is now a sub-tab inside the Gallery tab (to the right of Style_Catalog), rather than its own top-level tab — everything else about it works exactly the same",
|
||||
|
||||
// -- Video Tab (MiniMax H3, independent of GenerateUI) --
|
||||
// -- Video Tab (MiniMax H3 / LTX-2.5 / Wan2.2, independent of GenerateUI) --
|
||||
tabVideo: "Video",
|
||||
loadInVideo: "Load in Video",
|
||||
videoTitle: "Video (MiniMax H3)",
|
||||
videoFirstFrame: "First Frame (optional)",
|
||||
videoLastFrame: "Last Frame (optional)",
|
||||
videoDropOrClick: "Drop image or click to select",
|
||||
videoPrompt: "Prompt",
|
||||
videoAspectRatio: "Aspect Ratio",
|
||||
videoMegapixels: "Megapixels",
|
||||
videoMultiple: "Multiple",
|
||||
videoDuration: "Duration (seconds)",
|
||||
videoNoiseSeed: "Noise Seed",
|
||||
videoRandomizeSeed: "Randomize",
|
||||
videoGenerate: "Generate",
|
||||
videoEditPlaceholder: "Editing tools coming soon",
|
||||
videoNoWorkflowLoaded: "No workflow loaded",
|
||||
videoUnsupportedWorkflow: "This workflow does not contain a MiniMax H3 Image-to-Video node",
|
||||
videoUnsupportedWorkflow: "This workflow does not contain a supported video model node (MiniMax H3, LTX-2.5 Text/Image/First&Last-Frame to Video, or Wan2.2 Text to Video)",
|
||||
videoWorkflowLoadFailed: "Failed to load workflow",
|
||||
videoConfirmLoadWorkflow: (name) => `Load "${name}" as this plan's workflow?`,
|
||||
videoPlanMinOneBlock: "A plan needs at least one block",
|
||||
videoPlanEnterName: "Enter a name for this plan",
|
||||
videoPlanSaved: "Plan saved",
|
||||
videoPlanSaveFailed: "Failed to save plan",
|
||||
videoPlanLoaded: "Plan loaded",
|
||||
videoPlanLoadFailed: "Failed to load plan",
|
||||
videoConfirmClearPlan: "Clear the current plan?",
|
||||
videoPlanPause: "Pause",
|
||||
videoPlanResume: "Resume",
|
||||
videoWorkflowLoaded: (name) => `Workflow loaded: ${name}`,
|
||||
videoGenerateSuccess: "Video generated",
|
||||
videoDoneCount: (n) => `Done (${n} file${n === 1 ? "" : "s"})`,
|
||||
videoSourceLabel: "Video Source",
|
||||
videoSourceHint: "Load any video here to use Frame/GIF tools without generating one.",
|
||||
videoSourceDropLabel: "Drop video or click to select",
|
||||
videoNoVideo: "No video",
|
||||
videoSourcePreviewPlaceholder: "Select an asset or drop a video",
|
||||
videoResultPreviewPlaceholder: "No video generated yet",
|
||||
videoPropFrame: "Frame",
|
||||
videoPropGif: "GIF",
|
||||
videoFrameHint: "Play/seek the preview video to the position you want, then capture.",
|
||||
@@ -1356,15 +1366,26 @@ const LANGUAGES = {
|
||||
videoGifDoneCount: (n) => `Done (${n} frame${n === 1 ? "" : "s"})`,
|
||||
videoGifSaved: (name) => `GIF saved: ${name}`,
|
||||
videoNoSourceLoaded: "Load a video first (generate one, or drop a file into Video Source)",
|
||||
videoPropProject: "Project",
|
||||
videoProjectHint: "Saved plans",
|
||||
videoProjectEmpty: "No saved plans yet",
|
||||
videoProjectBlockCount: (n) => `${n} block${n === 1 ? "" : "s"}`,
|
||||
videoProjectDeleteConfirm: (name) => `Delete plan "${name}"?`,
|
||||
videoProjectDeleted: "Plan deleted",
|
||||
videoProjectDeleteFailed: "Failed to delete plan",
|
||||
videoProjectLoadListFailed: "Failed to load plan list",
|
||||
helpVideoTitle: "Video Tab",
|
||||
helpVideoDesc: "A dedicated video generation tab for the MiniMax H3 (Image to Video) workflow, independent of the GenerateUI tab.",
|
||||
helpVideo1: "Set first_frame (optional) / last_frame (optional) images, prompt, aspect_ratio / megapixels / multiple (resolution), duration (seconds), and noise_seed, then click Generate. Leaving first_frame empty runs the workflow text-only (bypassed), and workflows with no LoadImage node at all are also supported.",
|
||||
helpVideo2: "Model selection (UNet / CLIP / VAE / Audio VAE) is fixed to the loaded workflow's defaults and cannot be changed from this tab.",
|
||||
helpVideo3: "Use the \"Load in Video\" button in the Workflow tab's detail modal to load a workflow containing a MiniMax H3 Image-to-Video node. Unsupported workflows show an error instead.",
|
||||
helpVideo4: "Generated videos (mp4) can also be browsed and played back in the Gallery tab.",
|
||||
helpVideo5: "The Video Source panel next to the preview lets you drop or pick any local video (not just a generated one) to use the Frame/GIF tools below without running MiniMax H3 first; Clear resets it back to empty.",
|
||||
helpVideoDesc: "A dedicated video generation tab for MiniMax H3 (Image to Video), LTX-2.5 (Text / Image / First & Last Frame to Video), and Wan2.2 (Text to Video) workflows, independent of the GenerateUI tab. The center panel's Plan / Edit subtabs handle batch generation and (future) editing; the sidebar's Asset / Project subtabs handle browsing generated videos and saved plans.",
|
||||
helpVideo1: "Plan subtab: the topbar's settings row holds Aspect Ratio / Megapixels / Multiple / Duration (seconds) / Noise Seed as this plan's base settings — Duration always reflects the currently selected block (each block keeps its own value), the rest are plan-wide. A second row below adds Width / Height / Turbo Mode / Strength / Steps / Prompt Enhance, each enabled only for workflows that actually support it (see helpVideo2). Split the timeline into blocks with the + Split / + Block / Delete buttons — each block has its own Prompt, Duration, and First/Last Image — First Image can be None, an explicit image, or \"use previous block's last frame\" (an explicit Last Image on the previous block always wins over extracting one from its generated video). Click Run to generate every block in order; Pause/Cancel work mid-run.",
|
||||
helpVideo2: "A plan with a single block behaves exactly like the old one-shot form. Model selection (UNet / CLIP / VAE / Audio VAE) is fixed to the loaded workflow's defaults. For workflows with no ResolutionSelector node (e.g. Wan2.2, LTX-2.5 First & Last Frame to Video), the Aspect Ratio / Megapixels / Multiple fields are disabled and the workflow's own Width / Height become directly editable instead. Turbo Mode / Strength / Steps only apply to MiniMax H3's turbo LoRA, and Prompt Enhance only to LTX-2.5 — both stay disabled for other model families. Noise Seed is disabled for the one workflow that doesn't expose it: Wan2.2 Text-to-Video.",
|
||||
helpVideo3: "Use the \"Load in Video\" button in the Workflow tab's detail modal to load a workflow containing a MiniMax H3 Image-to-Video node, an LTX-2.5 Text/Image/First&Last-Frame-to-Video node, or a Wan2.2 Text-to-Video node — this starts a fresh single-block plan seeded from the workflow's own current values. Unsupported workflows show an error instead.",
|
||||
helpVideo4: "Generated videos (mp4) automatically appear in the Asset subtab's Video Temp group, and can also be browsed and played back in the Gallery tab. Organizing keepers into Video Assets is entirely up to you, on your own schedule.",
|
||||
helpVideo5: "The center panel shows two previews: the left one shows either the video you select in the Asset subtab or whatever you drop/pick in the Video Source panel on its left (Clear resets it to empty), letting you use the Frame/GIF tools without running the loaded video workflow first; the right one always shows the most recently generated clip.",
|
||||
helpVideo6: "Frame tab (right panel): play/seek the preview video to the position you want, click Capture Frame to grab that frame client-side, then Save to Output to write it as a PNG into ComfyUI's output folder.",
|
||||
helpVideo7: "GIF tab (right panel): set Start/End (seconds), FPS, and an optional Max Width, then Convert to GIF — the server decodes the video and encodes an animated GIF into ComfyUI's output folder.",
|
||||
helpVideo8: "Chaining: setting a block's First Image to \"use previous block's last frame\" continues smoothly from the previous clip — if that previous block has its own explicit Last Image, that image is used directly; otherwise the actual last frame of its generated video is extracted automatically.",
|
||||
helpVideo9: "Project tab (sidebar, next to Asset): browse every saved plan file (thumbnail, block count, last updated), click one to load it into the Plan editor, or delete it with the × button; clicking the same tab again collapses the panel.",
|
||||
helpVideo10: "Highlight color: the Prompt / Duration / First Image / Last Image / Aspect Ratio / Megapixels / Multiple / Noise Seed / Width / Height / Turbo Mode / Strength / Steps / Prompt Enhance labels turn the same highlight color as the GenerateUI Model tab (customizable in the Settings tab) when the loaded workflow actually supports that field — e.g. for a Wan2.2 workflow (no ResolutionSelector node), the Aspect Ratio / Megapixels / Multiple labels stay unhighlighted while Width / Height light up instead.",
|
||||
},
|
||||
|
||||
ja: {
|
||||
@@ -1547,6 +1568,9 @@ const LANGUAGES = {
|
||||
feederGalNoNode: "WFS_GalleryFeederノードが選択されていません",
|
||||
feederGalEmptyGroup: "選択グループに画像がありません",
|
||||
feederGroupCleared: "Feederグループをクリアしました",
|
||||
vtempGroupCleared: "__Video Temp__グループをクリアしました",
|
||||
vtempClearBtnLabel: "Clear __Video Temp__",
|
||||
vtempClearBtnTitle: "__Video Temp__グループをクリアします(動画生成物は自動的にここへ入ります。__Video Assets__への整理は任意のタイミングで手動で行ってください)",
|
||||
addedToFeeder: "Feederに追加しました",
|
||||
removedFromFeeder: "Feederから除外しました",
|
||||
appliedToWorkflow: "ワークフローに適用しました",
|
||||
@@ -1690,6 +1714,8 @@ const LANGUAGES = {
|
||||
textSizeLabel: "文字サイズ",
|
||||
textSizeTextarea: "プロンプト / チャット入力欄",
|
||||
textSizeHint: "適用対象: 生成UIプロンプト、AIアシスタントチャット、プリセットプロンプト、ワイルドカード編集、Metadataプロンプトプレビュー",
|
||||
videoVolumeLabel: "動画の音量",
|
||||
videoVolumeHint: "適用対象: Videoタブのプレビュー、Galleryタブの詳細/ライトボックス/比較動画プレーヤー。ここで設定した音量(または各動画自身のコントロールで変更した音量)は、アプリ内のどこで次に動画を開いても引き継がれます。",
|
||||
jsonColorsSection: "RAW JSON 文字色",
|
||||
jsonColorBase: "通常テキスト",
|
||||
jsonColorYellow: "名前 / スケジューラ",
|
||||
@@ -2007,7 +2033,7 @@ const LANGUAGES = {
|
||||
taggerThreshold: "閾値",
|
||||
taggerCharThreshold: "キャラ閾値",
|
||||
taggerGenerateTags: "タグ生成",
|
||||
taggerOllamaEnable: "Ollama VLM",
|
||||
taggerOllamaEnable: "VLMタグ付け",
|
||||
taggerOllamaUrl: "API URL",
|
||||
taggerOllamaModel: "モデル",
|
||||
taggerOllamaPrompt: "プロンプト",
|
||||
@@ -2076,6 +2102,12 @@ const LANGUAGES = {
|
||||
aiSettingsInputLang: "入力言語",
|
||||
aiSettingsOutputLang: "翻訳言語",
|
||||
aiSettingsSaveBtn: "設定を保存",
|
||||
aiUnloadModel: "モデルをアンロード",
|
||||
aiUnloading: "アンロード中...",
|
||||
aiUnloadDone: "モデルをアンロードしました",
|
||||
aiUnloadFailed: "アンロード失敗: ",
|
||||
aiUnloadUnsupported: "このバックエンドはAPI経由のアンロードに未対応です",
|
||||
aiUnloadNoModel: "先にモデルを選択してください",
|
||||
aiToastNoText: "テキストを入力してください",
|
||||
aiToastNoModel: "設定タブでモデルを選択してください",
|
||||
aiToastInvalidUrl: "URLは http:// または https:// で始まる必要があります",
|
||||
@@ -2146,7 +2178,8 @@ const LANGUAGES = {
|
||||
helpGen5: "Modelタブ:Checkpoint/VAE/Diffusion Model(UNETLoader / UnetLoaderGGUF / LoaderGGUF対応)/Text Encoder(CLIPLoader / DualCLIPLoader / ClipLoaderGGUF / DualClipLoaderGGUF対応 — typeおよびdevice選択付き、DualCLIPは2段モデル選択)は常時表示;ControlNetとHypernetwork(Strength入力付き)は使用頻度が低いためデフォルトで折りたたみ — 見出しをクリックで展開;LoRA(Single/Stackタブ)は右側に独立した列を表示;すべてのセレクタにフィルタ検索付き;LoRA Stack — Applyで有効な全LoRAを対象ノードに書き込み、同時にLoRA構文とCivitAIトリガーワードをPositiveプロンプトへ挿入;再Applyでは非アクティブなLoRAを削除し、アクティブなLoRAを再追加してプロンプトを更新",
|
||||
helpGen28: "Modelタブ — ハイライト色:読み込んだワークフローに実際に該当ノードが含まれる場合、各モデル種別(Checkpoint/VAE/Diffusion Model/Text Encoder/ControlNet/Hypernetwork)のラベルとLoRA列見出しが指定色(デフォルトは明るい緑)で表示される;ControlNet/Hypernetworkが折りたたまれた状態でも色は見えるため、展開しなくても使用有無が一目で分かる;色はSettingsタブでカスタマイズ可能",
|
||||
helpGen6: "Settingsタブ:KSamplerとLatent Imageを横並び(各50%幅)",
|
||||
helpGen7: "Raw JSONを各タブの右列に常時表示 — 直接編集してApplyでワークフロー即時反映;読み込んだワークフローにBypass/Muteノードがある場合、検索バー上部に一覧が表示される(Bypassは除外され配線が再接続される、Muteは除外されるが再接続はされない点はComfyUI本体と同じ)",
|
||||
helpGen31: "LTX-2.5とWan2.2の動画ワークフローも、専用のVideoタブだけでなく本タブに通常ワークフローとして読み込んだ場合に対応 — Positive/Negative PromptはLTX-2.5のLTXVDualCFGGuider / LTXVConditioningノードをたどって実際のプロンプト文を検出し、SettingsタブのLatent ImageはWan2.2のEmptyHunyuanLatentVideoとLTX-2.5のEmptyLTXVLatentVideoノードを認識(Length(フレーム数)欄も追加表示)して「No EmptyLatentImage node found」にならない;これらのワークフローからの生成もMiniMax H3の動画生成と同じ延長タイムアウトが適用される",
|
||||
helpGen7: "Raw JSONを各タブの右列に常時表示 — 直接編集してApplyでワークフロー即時反映;読み込んだワークフローにBypass/Muteノードがある場合、検索バー上部に一覧が表示される(Bypassは除外され配線が再接続される、Muteは除外されるが再接続はされない点はComfyUI本体と同じ);検索バーはヒット箇所をハイライト表示してスクロールするだけでエディタにカーソルを移動しないため、検索直後にキー入力してもJSONが誤って書き換わることはない — 編集する際はエディタ内をクリックしてから行う",
|
||||
helpGen8: "シード管理:ランダム / 固定 / 増加 / 減少",
|
||||
helpGen9: "画像生成、進捗表示、生成停止、結果表示",
|
||||
helpGen10: "Eagle連携:生成画像をEagleへ自動保存(SVG出力にも対応 — 標準SaveSVGNodeおよびcomfyui-tosvgのSave SVG Stringノードの両方)",
|
||||
@@ -2228,7 +2261,7 @@ const LANGUAGES = {
|
||||
helpLabResults3: "保存済みプランを読み込むと、プランファイルに記録された画像一覧からResultsの表示が復元されます",
|
||||
|
||||
helpSearchPlaceholder: "ヘルプを検索...",
|
||||
helpPrompt1: "AIアシスタント(Ollama / LM Studio / Lemonade):モデル選択、チャットでプロンプト相談、画像添付(ビジョンモデル対応);バックエンドとURLは設定タブで設定",
|
||||
helpPrompt1: "AIアシスタント(Ollama / LM Studio / Lemonade / Unsloth):チャットでプロンプト相談、画像添付(ビジョンモデル対応);⚙ 設定ボタンからバックエンド・接続URL・モデル・Thinking mode・Max tokensの選択とロード中モデルのアンロードが可能——設定はAI TOOLタブ・Taggerタブとは独立して保存される",
|
||||
helpPrompt2: "AIの応答をGenerateUIのプロンプトに適用",
|
||||
helpPrompt3: "翻訳機能:日⇔英、中⇔英",
|
||||
helpPrompt4: "プリセット管理:作成・編集、ポジティブ/ネガティブプロンプトのクリップボードコピー(PP/NP)",
|
||||
@@ -2258,11 +2291,11 @@ const LANGUAGES = {
|
||||
helpSettings2: "テーマ選択(13種プリセット)+カスタマイズ:カラー調整、背景パターン(ストライプ、ポルカドット、チェック、SVGタイリング)、フォント選択(日本語デザインフォント含む16種のGoogle Fonts)",
|
||||
helpSettings3: "ワークフローデータフォルダのパス変更・リセット",
|
||||
helpSettings4: "ComfyUI接続URL設定と接続テスト",
|
||||
helpSettings5: "AI Assistant(プロンプトタブ):バックエンド(Ollama / LM Studio / Lemonade)・API URL・デフォルトモデル・接続テスト",
|
||||
helpSettings5: "AI Assistant設定はこのタブから移動しました——Promptタブ・Taggerタブ・AI TOOLタブそれぞれが独自の⚙設定ボタン(バックエンド・URL・モデル・Thinking mode・Max tokens・モデルのアンロード)を持ち、個別に保存されます",
|
||||
helpSettings6: "デフォルトワークフローの設定・解除",
|
||||
helpSettings7: "Eagle連携URL、自動保存の有効/無効",
|
||||
helpSettings8: "データ管理:設定・メタデータ・プロンプトなど主要データをJSONにエクスポート、またはインポートして復元。インポート後はComfyUIを再起動してください。",
|
||||
helpSettings15: "フルバックアップ (ZIP):上記のJSONエクスポートと異なり、フォルダ形式のデータ(AI Skills、Lab Plan、Styleプリセット)とTaggerデータベースも含みます。復元すると既存ファイルは上書きされます。復元後はComfyUIを再起動してください。",
|
||||
helpSettings15: "フルバックアップ (ZIP):上記のJSONエクスポートと異なり、フォルダ形式のデータ(AI Skills、Lab Plan、Video Plan、Styleプリセット)とTaggerデータベースも含みます。復元すると既存ファイルは上書きされます。復元後はComfyUIを再起動してください。",
|
||||
helpSettings16: "フルバックアップのボタン上にある2つのチェックボックスで、デフォルトワークフローフォルダーとImpact Packのwildcardフォルダーもエクスポートに含められます。どちらもエクスポート専用で自動復元はされません。必要な場合はZIP内の_external/フォルダから手動でコピーしてください。",
|
||||
helpSettings9: "各セクションはアコーディオン式で折りたたみ可能",
|
||||
helpSettings10: "Wildcard Integration:WFSのワイルドカードディレクトリをComfyUI-Impact-Packのwildcardsディレクトリへリンク(Windowsはジャンクション、他OSはシンボリックリンク)。既存ファイルは自動で移行されます",
|
||||
@@ -2319,13 +2352,13 @@ const LANGUAGES = {
|
||||
|
||||
// -- Tagger Tab --
|
||||
helpTaggerTitle: "Taggerタブ",
|
||||
helpTagger1: "WD Tagger(ONNX)・SwinV2・DeepDanbooru(.h5)・Ollama VLMによる自動タグ付け — サブタブ: Single / Batch / DB",
|
||||
helpTagger1: "WD Tagger(ONNX)・SwinV2・DeepDanbooru(.h5)・VLM(Ollama / LM Studio / Lemonade / Unsloth)による自動タグ付け — サブタブ: Single / Batch / DB",
|
||||
helpTagger2: "モデル配置:ComfyUI/models/tagger/<モデル名>/ 以下に各モデルのフォルダを作成し、.onnx + selected_tags.csv(DeepDanbooruは .h5 + ラベルファイル)を格納",
|
||||
helpTagger3: "Singleタブ:プレビューエリアへ画像をドラッグ&ドロップ、またはUploadボタンでファイルを選択;GalleryタブのTaggerボタンで選択画像を直接開くことも可能",
|
||||
helpTagger4: "閾値スライダー:一般タグの信頼スコア下限(デフォルト0.35);キャラ閾値:character: プレフィックス付きタグ専用の閾値(デフォルト0.85)",
|
||||
helpTagger5: "Ollama VLM:チェックボックスをオンにするとWD Taggerと並行してビジョンモデルを実行;API URLとモデルを設定(↻で一覧更新)、プロンプトを編集可能;両モデルの結果はマージされる",
|
||||
helpTagger5: "VLMタグ付け:チェックボックスをオンにするとWD Taggerと並行してビジョンモデルを実行;⚙設定ボタンからバックエンド(Ollama / LM Studio / Lemonade / Unsloth)・URL・モデル・Thinking mode・Max tokensの選択とモデルのアンロードが可能——Promptタブ独自のAI設定とは別管理;プロンプトとMax Tagsはインラインで編集可能;両モデルの結果はマージされる",
|
||||
helpTagger6: "生成タグの送信先:(1) GenUI:P — 生成UIタブのポジティブプロンプトに追記し、読み込み中のワークフローへ即時適用;(2) プロンプトに送信 — Promptタブの正プロンプトテキストエリアに追記;(3) Galleryに保存 — ギャラリーの画像メタデータに保存(Galleryから開いた画像のみ有効);(4) ファイルに書込 — JPEGはEXIF(ImageDescription)、PNGはtEXt(Tagsキー)に書き込み;(5) DBに保存 — 内蔵SQLiteデータベースに保存",
|
||||
helpTagger7: "Batchタブ:処理対象フォルダパスを入力してWD Tagger・Ollamaの設定を行い、出力オプション(DBに保存〈デフォルトON〉・ファイルに書込〈EXIF/PNGメタデータ〉・.txt出力〈画像と同フォルダに <ファイル名>.txt を生成〉)を選択;バッチ開始で指定フォルダ内の全画像を処理;進行状況バーとログがリアルタイム更新;停止ボタンは現在の画像処理完了後にキャンセル",
|
||||
helpTagger7: "Batchタブ:処理対象フォルダパスを入力してWD Taggerを設定し、VLMタグ付けを有効化(Singleタブと同じ⚙設定を使用);出力オプション(DBに保存〈デフォルトON〉・ファイルに書込〈EXIF/PNGメタデータ〉・.txt出力〈画像と同フォルダに <ファイル名>.txt を生成〉)を選択;バッチ開始で指定フォルダ内の全画像を処理;進行状況バーとログがリアルタイム更新;停止ボタンは現在の画像処理完了後にキャンセル",
|
||||
helpTagger8: "DBタブ:タグ付けした画像の検索可能データベース;行をクリックすると編集パネルでWDタグ・VLMタグを編集可能;保存で更新、削除でレコード削除;CSV出力で全レコードをダウンロード",
|
||||
helpTagger9: "依存パッケージのインストール:python_embeded\\python.exe -m pip install -r requirements.txt;GPU推論にはonnxruntimeの代わりにonnxruntime-gpuをインストール;TensorFlow(DeepDanbooru用)はサイズ大のためデフォルトではコメントアウト",
|
||||
|
||||
@@ -2352,7 +2385,7 @@ const LANGUAGES = {
|
||||
helpAi2: "翻訳ペイン:Ollama、LM Studio、Lemonade、または Unsloth を使って日本語・英語・中国語・カスタム言語(Free)間でテキストを翻訳;⇄ ボタンで言語とテキストを同時入替;選択は自動保存",
|
||||
helpAi3: "Chat ペイン:LLM とのマルチターン会話;Enter で送信、Shift+Enter で改行;Clear ボタンで会話履歴をリセット;モデルがtool callingに対応している場合、「猫の画像を作って」のように頼むとGenerateUIに読み込み中のワークフローで生成を実行し、結果をチャット内に表示する;ペインヘッダーの「画像生成を許可する」チェックボックスでこの機能のON/OFFを切り替えられる;画像が添付されている場合(TOOLSペインにドロップした画像)はLLMにもビジョン入力として送信され、generate_image呼び出し時はT2Iの代わりにI2I(image-to-image)の元画像として使われる;generate_image呼び出しにはsteps・cfg・sampler_name・scheduler・denoise・seed、width・height、batch_size(その1回の呼び出しで生成する枚数)、aspect_ratio(\"3:2\"のような比率プリセット。ワークフローにwidth/heightを供給するResolution Selectorノードがある場合のみ適用され、それ以外は無視される)といった任意の生成パラメータも指定できる;モデルが指定しなかった項目は読み込み中のワークフローの現在の設定がそのまま使われる;tool callingとビジョンの動作を確認済みのモデル: Gemma 4:e4b、Qwen 3.5:9b、Ministral 3:3b(Ollama)",
|
||||
helpAi4: "TOOLS ペイン — VLM:画像(PNG/JPG/WebP)をドロップしてタスク(画像解説 / プロンプト作成 / タグ作成)を選んで Run;または「Create wildcards」を選んでカテゴリ名と件数を入力すると1行1エントリのワイルドカードを生成;ドロップした画像はChatペインの添付としても共有され(Chat側にも表示、I2I生成に使用)、✕ボタンでクリアするまで保持される",
|
||||
helpAi6: "Settings ペイン:バックエンド(Ollama / LM Studio / Lemonade / Unsloth)の選択、APIのURL設定、接続テスト、モデル選択;Unslothはローカルアクセスでも常にAPIキー認証が必須——プラグインフォルダの .env.example を .env にコピーして UNSLOTH_API_KEY を設定し ComfyUI を再起動する(キーはサーバー側でのみ読み込まれ、ブラウザには一切送信されない);Unsloth Desktopアプリ側の設定画面で「モデル自動切り替え (OpenAI API)」もONにする必要がある——OFFのままだと、Unsloth Studio上で事前にモデルを手動ロードしていない限り HTTP 404 で接続に失敗する;Unslothのreasoningモデルは思考内容をインラインの<think>タグではなく別のreasoning_contentフィールドで返すため、Max tokensが少ないとモデルが思考だけでトークンを使い切り、空の返信になることがある——返信が空になる場合はMax tokensを増やす(2048以上を推奨);Generationセクション — Thinking modeトグル(デフォルトOFF;OllamaにはthinkフラグとしてOFF/ONを送信、バックエンドを問わずOFF時は出力中の<think>...</think>ブロックをクライアント側で除去するため、推論モデルの思考過程がTranslation/Chat/TOOLSの結果に混入しない)とMax tokens(Ollama: num_predict、LM Studio/Lemonade/Unsloth: max_tokens;0で無制限);Free言語名の設定;Chat Image Generationセクションでは、ChatからのT2I画像生成にGenerateUIの現在の読み込みワークフローの代わりに専用ワークフローを使うよう設定できる;Chat I2I Generationセクションは同様の設定を画像添付時のI2I生成向けに提供する;設定は localStorage に保存され、Library パネルの A タブと共有される",
|
||||
helpAi6: "Settings ペイン:バックエンド(Ollama / LM Studio / Lemonade / Unsloth)の選択、APIのURL設定、接続テスト、モデル選択、および「Test connection」の右隣にある「Unload Model」ボタンでロード中のモデルをVRAM/メモリから解放——Ollamaは keep_alive:0、LM Studioは /api/v1/models/unload、Lemonadeは /api/v1/unload を使用;Unslothにはアンロード用APIが存在しないため未対応メッセージが表示される;Unslothはローカルアクセスでも常にAPIキー認証が必須——プラグインフォルダの .env.example を .env にコピーして UNSLOTH_API_KEY を設定し ComfyUI を再起動する(キーはサーバー側でのみ読み込まれ、ブラウザには一切送信されない);Unsloth Desktopアプリ側の設定画面で「モデル自動切り替え (OpenAI API)」もONにする必要がある——OFFのままだと、Unsloth Studio上で事前にモデルを手動ロードしていない限り HTTP 404 で接続に失敗する;Unslothのreasoningモデルは思考内容をインラインの<think>タグではなく別のreasoning_contentフィールドで返すため、Max tokensが少ないとモデルが思考だけでトークンを使い切り、空の返信になることがある——返信が空になる場合はMax tokensを増やす(2048以上を推奨);Generationセクション — Thinking modeトグル(デフォルトOFF;OllamaにはthinkフラグとしてOFF/ONを送信、バックエンドを問わずOFF時は出力中の<think>...</think>ブロックをクライアント側で除去するため、推論モデルの思考過程がTranslation/Chat/TOOLSの結果に混入しない)とMax tokens(Ollama: num_predict、LM Studio/Lemonade/Unsloth: max_tokens;0で無制限);Free言語名の設定;Chat Image Generationセクションでは、ChatからのT2I画像生成にGenerateUIの現在の読み込みワークフローの代わりに専用ワークフローを使うよう設定できる;Chat I2I Generationセクションは同様の設定を画像添付時のI2I生成向けに提供する;設定は localStorage に保存され、Library パネルの A タブと共有される",
|
||||
helpAi7: "Chat ペイン — SVG:LLMはComfyUIワークフローを一切使わず、SVGグラフィックをテキストとして直接生成することもできる;「SVGで〜を描いて」のように頼み、応答にSVGコードが含まれていれば自動でインラインプレビュー表示され、「Galleryに保存」ボタンでGalleryタブの出力フォルダに.svgファイルとして保存できる;tool calling(function calling)を使用しないため、tool calling非対応のモデルでも動作する",
|
||||
helpAi8: "Chat ペイン — スキル:メッセージ一覧上部のドロップダウンでスキルを選ぶと、その指示内容が system prompt として会話の先頭に付加される(表示上のチャット履歴には含まれない);鉛筆ボタンでスキル管理パネルを開き、.mdスキルファイルを作成・編集・削除できる(保存先: user/default/Workflow-Studio/ai_skills/);ファイル先頭の---で囲まれた部分にname/descriptionを書くとドロップダウンの表示に反映される;初期状態で2つのスキルを同梱: 「SVG Icon Generator」(描く前に対象を部位分解することで認識しやすいSVGを生成)と「Skill Creator」(対話形式で質問しながら新しいスキルファイルを下書きする);応答に```skillコードブロックが含まれる場合、メッセージ下部に「スキルとして保存」ボタンが表示され、内容が入った状態で管理パネルが開く",
|
||||
helpAi9: "スキル作成のヒント:ドロップダウンやツールチップで分かりやすいよう、frontmatterのname/descriptionは明確に書く;期待する出力形式を具体的に指示し、SVGや別のスキルファイルのように後で抽出したい成果物がある場合は専用のコードフェンスで囲むよう指示する;曖昧な指示より具体的で命令形の指示の方がローカルの小型モデルには効きやすく、短い実例を1つ添えるとさらに効果的;禁止事項(不適切な内容、セキュリティ、文字数制限など)は暗黙に期待せず明示的に書く;迷ったらドロップダウンで「Skill Creator」スキルを選び、作りたいスキルの概要を伝えれば対話形式で下書きしてくれる",
|
||||
@@ -2577,7 +2610,7 @@ const LANGUAGES = {
|
||||
importError: "インポート失敗",
|
||||
exportFullBackup: "フルバックアップ (ZIP)",
|
||||
importFullBackup: "フルバックアップを復元 (ZIP)",
|
||||
fullBackupHint: "フルバックアップ(ZIP)は上記のJSONエクスポートでは表現できないフォルダ形式のデータ(AI Skills、Lab Plan、Styleプリセット)とTaggerデータベースも含みます。復元すると既存ファイルは上書きされます。復元後はComfyUIを再起動してください。",
|
||||
fullBackupHint: "フルバックアップ(ZIP)は上記のJSONエクスポートでは表現できないフォルダ形式のデータ(AI Skills、Lab Plan、Video Plan、Styleプリセット)とTaggerデータベースも含みます。復元すると既存ファイルは上書きされます。復元後はComfyUIを再起動してください。",
|
||||
fullBackupFilesUnit: "件",
|
||||
fullBackupIncludeWorkflows: "デフォルトワークフローフォルダーを含める (user/default/workflows)",
|
||||
fullBackupIncludeWildcard: "Impact Packのwildcardフォルダーを含める(存在する場合)",
|
||||
@@ -2674,31 +2707,29 @@ const LANGUAGES = {
|
||||
helpMetadata5: "対応フォーマット: ComfyUI PNG/WebP/MP4/JSON(標準形式 + Flux.2 / Qwen-Image / Z-Image / Mage-Flow / LongCat / Boogu / HiDream E1 / FireRed / Ernie Image サブグラフ形式;MP4はSaveVideoが書き込むworkflow/promptコンテナタグを読み取り、MiniMax H3 ImageToVideoのようなオールインワン動画ノードにも対応)・SD WebUI・SD Forge・Fooocus。",
|
||||
helpMetadata6: "現在は Gallery タブ内のサブタブ(Style_Catalog の右隣)になっており、独立したトップレベルタブではありません — それ以外の動作は全く同じです",
|
||||
|
||||
// -- Video タブ(MiniMax H3専用、GenerateUIタブとは独立) --
|
||||
// -- Video タブ(MiniMax H3 / LTX-2.5 / Wan2.2対応、GenerateUIタブとは独立) --
|
||||
tabVideo: "Video",
|
||||
loadInVideo: "Videoに読み込み",
|
||||
videoTitle: "Video (MiniMax H3)",
|
||||
videoFirstFrame: "First Frame(任意)",
|
||||
videoLastFrame: "Last Frame(任意)",
|
||||
videoDropOrClick: "画像をドロップまたはクリックして選択",
|
||||
videoPrompt: "Prompt",
|
||||
videoAspectRatio: "Aspect Ratio",
|
||||
videoMegapixels: "Megapixels",
|
||||
videoMultiple: "Multiple",
|
||||
videoDuration: "Duration(秒)",
|
||||
videoNoiseSeed: "Noise Seed",
|
||||
videoRandomizeSeed: "ランダム化",
|
||||
videoGenerate: "Generate",
|
||||
videoEditPlaceholder: "編集機能は今後追加予定",
|
||||
videoNoWorkflowLoaded: "ワークフローが読み込まれていません",
|
||||
videoUnsupportedWorkflow: "このワークフローにはMiniMax H3のImage to Videoノードが含まれていません",
|
||||
videoUnsupportedWorkflow: "このワークフローには対応する動画モデルノード(MiniMax H3、LTX-2.5のText/Image/First&Last-Frame to Video、またはWan2.2のText to Video)が含まれていません",
|
||||
videoWorkflowLoadFailed: "ワークフローの読み込みに失敗しました",
|
||||
videoConfirmLoadWorkflow: (name) => `「${name}」をこのPlanのワークフローとして読み込みますか?`,
|
||||
videoPlanMinOneBlock: "Planには最低1つのブロックが必要です",
|
||||
videoPlanEnterName: "Planの名前を入力してください",
|
||||
videoPlanSaved: "Planを保存しました",
|
||||
videoPlanSaveFailed: "Planの保存に失敗しました",
|
||||
videoPlanLoaded: "Planを読み込みました",
|
||||
videoPlanLoadFailed: "Planの読み込みに失敗しました",
|
||||
videoConfirmClearPlan: "現在のPlanをクリアしますか?",
|
||||
videoPlanPause: "一時停止",
|
||||
videoPlanResume: "再開",
|
||||
videoWorkflowLoaded: (name) => `ワークフローを読み込みました: ${name}`,
|
||||
videoGenerateSuccess: "動画を生成しました",
|
||||
videoDoneCount: (n) => `完了(${n}件)`,
|
||||
videoSourceLabel: "動画ソース",
|
||||
videoSourceHint: "生成せずにFrame/GIF機能を使いたい場合はここに任意の動画を読み込めます。",
|
||||
videoSourceDropLabel: "動画をドロップまたはクリックして選択",
|
||||
videoNoVideo: "動画なし",
|
||||
videoSourcePreviewPlaceholder: "アセットを選択するか動画をドロップしてください",
|
||||
videoResultPreviewPlaceholder: "生成された動画はまだありません",
|
||||
videoPropFrame: "Frame",
|
||||
videoPropGif: "GIF",
|
||||
videoFrameHint: "プレビュー動画を再生・シークして止めたい位置で「Capture Frame」を押してください。",
|
||||
@@ -2715,15 +2746,26 @@ const LANGUAGES = {
|
||||
videoGifDoneCount: (n) => `完了(${n}フレーム)`,
|
||||
videoGifSaved: (name) => `GIFを保存しました: ${name}`,
|
||||
videoNoSourceLoaded: "先に動画を用意してください(生成するか、動画ソースにファイルをドロップ)",
|
||||
videoPropProject: "Project",
|
||||
videoProjectHint: "保存済みのPlan",
|
||||
videoProjectEmpty: "保存済みのPlanはまだありません",
|
||||
videoProjectBlockCount: (n) => `${n}ブロック`,
|
||||
videoProjectDeleteConfirm: (name) => `Plan「${name}」を削除しますか?`,
|
||||
videoProjectDeleted: "Planを削除しました",
|
||||
videoProjectDeleteFailed: "Planの削除に失敗しました",
|
||||
videoProjectLoadListFailed: "Plan一覧の読み込みに失敗しました",
|
||||
helpVideoTitle: "Video タブ",
|
||||
helpVideoDesc: "MiniMax H3 (Image to Video) ワークフロー専用の動画生成タブ。GenerateUIタブとは独立して動作します。",
|
||||
helpVideo1: "first_frame(任意)/last_frame(任意)の画像、prompt、aspect_ratio/megapixels/multiple(解像度)、duration(秒)、noise_seedを指定してGenerateをクリックします。first_frameを未指定にするとテキストのみでバイパス実行され、LoadImageノード自体が無いワークフローにも対応しています。",
|
||||
helpVideo2: "モデル選択(UNet/CLIP/VAE/Audio VAE)は読み込んだワークフローの既定値に固定され、このタブでは変更できません。",
|
||||
helpVideo3: "Workflowタブの詳細モーダルにある「Videoに読み込み」ボタンから、MiniMax H3のImage to Videoノードを含むワークフローを読み込めます。対応していないワークフローはエラー表示になります。",
|
||||
helpVideo4: "生成した動画(mp4)はGalleryタブでも閲覧・再生できます。",
|
||||
helpVideo5: "プレビューの横にある「Video Source」パネルでは、生成した動画に限らず任意のローカル動画をドロップ/選択して、下のFrame/GIF機能をMiniMax H3を実行せずに使えます。Clearで選択をリセットできます。",
|
||||
helpVideoDesc: "MiniMax H3 (Image to Video)、LTX-2.5 (Text / Image / First & Last Frame to Video)、Wan2.2 (Text to Video) ワークフロー対応の動画生成タブ。GenerateUIタブとは独立して動作します。中央パネルのPlan/Editサブタブがバッチ生成と(将来の)編集を、左サイドバーのAsset/Projectサブタブが生成済み動画の閲覧と保存済みPlanの一覧を扱います。",
|
||||
helpVideo1: "Planサブタブ: 上部の設定行にAspect Ratio/Megapixels/Multiple/Duration(秒)/Noise SeedがこのPlanの基本設定として並びます——Durationは常に現在選択中のブロックの値を表示・編集します(各ブロックが独自の値を持つ)が、それ以外はPlan全体で共通の値です。その下の2行目にはWidth/Height/Turbo Mode/Strength/Steps/Prompt Enhanceが並び、読み込んだワークフローが実際に対応する項目だけ入力可能になります(詳細はhelpVideo2)。「+ Split」「+ Block」「Delete」ボタンでタイムラインをブロックに分割すると、各ブロックは独自のPrompt・Duration・First/Last Imageを持ちます(First Imageは「なし」「画像を指定」「前ブロックの最終フレームを使用」から選択可能。前ブロックに明示的なLast Imageが設定されていれば、フレーム抽出よりそちらが優先されます)。Runを押すと全ブロックを順番に生成します。実行中もPause/Cancelが使えます。",
|
||||
helpVideo2: "ブロックが1個だけのPlanは、以前の単発生成フォームと同じ動作になります。モデル選択(UNet/CLIP/VAE/Audio VAE)は読み込んだワークフローの既定値に固定されます。ResolutionSelectorノードを持たないワークフロー(Wan2.2、LTX-2.5のFirst & Last Frame to Videoなど)はAspect Ratio/Megapixels/Multiple欄が無効化される代わりに、ワークフロー自体のWidth/Heightを直接編集できるようになります。Turbo Mode/Strength/StepsはMiniMax H3のturbo LoRA専用、Prompt EnhanceはLTX-2.5専用で、他のモデルファミリーでは無効のままです。Noise SeedはWan2.2のText to Videoのみ公開入力を持たないため無効化されます。",
|
||||
helpVideo3: "Workflowタブの詳細モーダルにある「Videoに読み込み」ボタンから、MiniMax H3のImage to Videoノード、LTX-2.5のText/Image/First&Last-Frame to Videoノード、またはWan2.2のText to Videoノードを含むワークフローを読み込めます。この操作でワークフローの現在値を反映したブロック1個の新規Planが作成されます。対応していないワークフローはエラー表示になります。",
|
||||
helpVideo4: "生成した動画(mp4)はAssetサブタブのVideo Tempグループに自動的に反映されるほか、Galleryタブでも閲覧・再生できます。残したい動画をVideo Assetsへ整理するタイミングはユーザー任意です。",
|
||||
helpVideo5: "中央パネルには2つのプレビューがあります。左側はAssetサブタブで選択した動画、または左隣の「Video Source」パネルにドロップ/選択した任意のローカル動画を表示し(Clearでリセット)、読み込んだワークフローを実行せずにFrame/GIF機能を使えます。右側は常に直近で生成されたクリップを表示します。",
|
||||
helpVideo6: "Frameタブ(右パネル): プレビュー動画を再生・シークして止めたい位置で「Capture Frame」を押すとその場でフレームをキャプチャし、「Save to Output」でPNGとしてComfyUIのOutputフォルダに保存します。",
|
||||
helpVideo7: "GIFタブ(右パネル): Start/End(秒)・FPS・Max Width(任意)を指定して「Convert to GIF」を押すと、サーバー側で動画をデコードしアニメーションGIFとしてComfyUIのOutputフォルダに保存します。",
|
||||
helpVideo8: "チェイン機能: ブロックのFirst Imageを「前ブロックの最終フレームを使用」に設定すると、前のクリップから連続した映像になります。前ブロックに明示的なLast Imageが設定されていればそれがそのまま使われ、無ければ生成された動画から実際の最終フレームが自動抽出されます。",
|
||||
helpVideo9: "Projectタブ(左サイドバー、Assetの隣): 保存済みの全Planファイル(サムネイル・ブロック数・更新日時)を一覧表示し、クリックでPlanエディタへ読み込み、×ボタンで削除できます。同じタブをもう一度押すとパネルを閉じます。",
|
||||
helpVideo10: "ハイライト表示: 読み込んだワークフローが実際にサポートしているフィールドに応じて、Prompt/Duration/First Image/Last Image/Aspect Ratio/Megapixels/Multiple/Noise Seed/Width/Height/Turbo Mode/Strength/Steps/Prompt Enhanceのラベルが、GenerateUI ModelタブのハイライトとSettingsタブで共通設定できる色に変わります。例えばWan2.2ワークフロー(ResolutionSelectorノードが無い)ではAspect Ratio/Megapixels/Multipleはハイライトされない代わりに、Width/Heightがハイライトされます。",
|
||||
},
|
||||
|
||||
zh: {
|
||||
@@ -2906,6 +2948,9 @@ const LANGUAGES = {
|
||||
feederGalNoNode: "未选择WFS_GalleryFeeder节点",
|
||||
feederGalEmptyGroup: "所选组中没有图片",
|
||||
feederGroupCleared: "已清空Feeder组",
|
||||
vtempGroupCleared: "已清空__Video Temp__组",
|
||||
vtempClearBtnLabel: "Clear __Video Temp__",
|
||||
vtempClearBtnTitle: "清空__Video Temp__组(视频生成结果会自动进入此组,整理到__Video Assets__由用户自行选择时机手动完成)",
|
||||
addedToFeeder: "已添加到Feeder",
|
||||
removedFromFeeder: "已从Feeder移除",
|
||||
appliedToWorkflow: "已应用到工作流",
|
||||
@@ -3049,6 +3094,8 @@ const LANGUAGES = {
|
||||
textSizeLabel: "文字大小",
|
||||
textSizeTextarea: "提示词 / 聊天输入框",
|
||||
textSizeHint: "适用于:生成UI提示词、AI助手聊天、预设提示词、通配符编辑、Metadata提示词预览",
|
||||
videoVolumeLabel: "视频音量",
|
||||
videoVolumeHint: "适用于:Video 标签页预览、Gallery 标签页详情/灯箱/对比视频播放器。在此设置的音量(或在任意视频自身控件中调整的音量)会在应用内下次打开任意视频时保留。",
|
||||
jsonColorsSection: "RAW JSON 文字颜色",
|
||||
jsonColorBase: "普通文本",
|
||||
jsonColorYellow: "名称 / 调度器",
|
||||
@@ -3366,7 +3413,7 @@ const LANGUAGES = {
|
||||
taggerThreshold: "阈值",
|
||||
taggerCharThreshold: "角色阈值",
|
||||
taggerGenerateTags: "生成标签",
|
||||
taggerOllamaEnable: "Ollama VLM",
|
||||
taggerOllamaEnable: "VLM打标",
|
||||
taggerOllamaUrl: "API URL",
|
||||
taggerOllamaModel: "模型",
|
||||
taggerOllamaPrompt: "提示词",
|
||||
@@ -3435,6 +3482,12 @@ const LANGUAGES = {
|
||||
aiSettingsInputLang: "输入语言",
|
||||
aiSettingsOutputLang: "翻译语言",
|
||||
aiSettingsSaveBtn: "保存设置",
|
||||
aiUnloadModel: "卸载模型",
|
||||
aiUnloading: "卸载中...",
|
||||
aiUnloadDone: "模型已卸载",
|
||||
aiUnloadFailed: "卸载失败: ",
|
||||
aiUnloadUnsupported: "此后端不支持通过API卸载",
|
||||
aiUnloadNoModel: "请先选择模型",
|
||||
aiToastNoText: "请输入文字",
|
||||
aiToastNoModel: "请在设置标签中选择模型",
|
||||
aiToastInvalidUrl: "URL必须以 http:// 或 https:// 开头",
|
||||
@@ -3505,7 +3558,8 @@ const LANGUAGES = {
|
||||
helpGen5: "Model标签:Checkpoint/VAE/Diffusion Model(支持UNETLoader / UnetLoaderGGUF / LoaderGGUF)/Text Encoder(支持CLIPLoader / DualCLIPLoader / ClipLoaderGGUF / DualClipLoaderGGUF — 含type和device选择器,DualCLIP显示两段模型选择)始终显示;ControlNet和Hypernetwork(带Strength输入)因使用频率较低默认折叠 — 点击标题展开;LoRA(Single/Stack标签)拥有独立的列;所有选择器均含筛选;LoRA Stack — 点击Apply会将所有启用的LoRA写入目标节点,并同时将LoRA语法和CivitAI触发词插入Positive提示词;再次Apply会移除未启用的LoRA并重新添加启用的LoRA以更新提示词",
|
||||
helpGen28: "Model标签 — 高亮颜色:当前工作流实际包含某类型节点时(Checkpoint/VAE/Diffusion Model/Text Encoder/ControlNet/Hypernetwork),对应标签及LoRA列标题会以指定颜色(默认亮绿色)显示;即使ControlNet/Hypernetwork处于折叠状态该颜色依然可见,无需展开即可判断是否在使用;颜色可在Settings标签中自定义",
|
||||
helpGen6: "Settings标签:KSampler与Latent Image并排显示(各占50%宽度)",
|
||||
helpGen7: "Raw JSON在每个标签右列常驻显示 — 直接编辑并Apply即时重载工作流;如果加载的工作流包含Bypass或Mute节点,搜索栏上方会显示列表(Bypass节点会被排除但其连线会重新连接;Mute节点会被排除且不重新连接,与ComfyUI本体行为一致)",
|
||||
helpGen31: "LTX-2.5和Wan2.2视频工作流在本标签中作为普通工作流加载时(不仅限于专用的Video标签)也可正常使用 — Positive/Negative Prompt会沿LTX-2.5的LTXVDualCFGGuider / LTXVConditioning节点追溯找到实际提示词文本,Settings标签的Latent Image部分能识别Wan2.2的EmptyHunyuanLatentVideo和LTX-2.5的EmptyLTXVLatentVideo节点(并新增Length(帧数)字段),不再显示\"No EmptyLatentImage node found\";从这些工作流生成时也会应用与MiniMax H3视频生成相同的延长超时",
|
||||
helpGen7: "Raw JSON在每个标签右列常驻显示 — 直接编辑并Apply即时重载工作流;如果加载的工作流包含Bypass或Mute节点,搜索栏上方会显示列表(Bypass节点会被排除但其连线会重新连接;Mute节点会被排除且不重新连接,与ComfyUI本体行为一致);搜索栏只会高亮匹配项并滚动到该位置,不会将光标移入编辑器,因此搜索后立即按键不会意外覆盖JSON — 需要先点击编辑器内部才能实际编辑",
|
||||
helpGen8: "种子管理:随机/固定/递增/递减",
|
||||
helpGen9: "生成图片、进度显示、停止生成、查看结果",
|
||||
helpGen10: "Eagle集成:自动保存生成图片到Eagle(也支持SVG输出 — 标准SaveSVGNode节点和comfyui-tosvg的Save SVG String节点均可)",
|
||||
@@ -3587,7 +3641,7 @@ const LANGUAGES = {
|
||||
helpLabResults3: "加载已保存的方案时,会根据方案文件中记录的图片列表恢复Results网格",
|
||||
|
||||
helpSearchPlaceholder: "搜索帮助...",
|
||||
helpPrompt1: "AI助手(Ollama / LM Studio / Lemonade):模型选择、聊天咨询提示词、图片附件(视觉模型);后端和URL在设置标签页配置",
|
||||
helpPrompt1: "AI助手(Ollama / LM Studio / Lemonade / Unsloth):聊天咨询提示词、图片附件(视觉模型);点击⚙设置按钮可选择后端、连接URL、模型、Thinking mode、Max tokens,并卸载已加载的模型——设置与AI TOOL标签页、Tagger标签页相互独立",
|
||||
helpPrompt2: "将AI回复应用到生成UI的提示词",
|
||||
helpPrompt3: "翻译功能:日\u2194英、中\u2194英",
|
||||
helpPrompt4: "预设管理:创建、编辑、正面/负面提示词剪贴板复制(PP/NP)",
|
||||
@@ -3617,11 +3671,11 @@ const LANGUAGES = {
|
||||
helpSettings2: "主题选择(13种预设)+ 自定义:颜色调整、背景图案(条纹、波点、棋盘格、SVG平铺)、字体选择(含日文显示字体在内的16种Google Fonts)",
|
||||
helpSettings3: "工作流数据文件夹路径更改/重置",
|
||||
helpSettings4: "ComfyUI连接URL设置和测试",
|
||||
helpSettings5: "AI助手(提示词标签页):后端(Ollama / LM Studio / Lemonade)、API URL、默认模型、连接测试",
|
||||
helpSettings5: "AI助手设置已从此标签页移出——Prompt标签页、Tagger标签页、AI TOOL标签页现在各自拥有独立的⚙设置按钮(后端、URL、模型、Thinking mode、Max tokens、卸载模型),分别单独保存",
|
||||
helpSettings6: "默认工作流设置/取消",
|
||||
helpSettings7: "Eagle集成URL、自动保存开关",
|
||||
helpSettings8: "数据管理:将设置、元数据、提示词等主要数据导出为JSON文件,或导入以恢复。导入后请重启ComfyUI。",
|
||||
helpSettings15: "完整备份 (ZIP):与上方的JSON导出不同,还包含文件夹型数据(AI Skills、Lab Plan、Style预设)以及Tagger数据库。恢复会覆盖现有文件,恢复后请重启ComfyUI。",
|
||||
helpSettings15: "完整备份 (ZIP):与上方的JSON导出不同,还包含文件夹型数据(AI Skills、Lab Plan、Video Plan、Style预设)以及Tagger数据库。恢复会覆盖现有文件,恢复后请重启ComfyUI。",
|
||||
helpSettings16: "完整备份按钮上方的两个复选框可将ComfyUI默认工作流文件夹和Impact Pack的wildcard文件夹一并导出。两者均仅用于导出,不会自动恢复。如需要,请从ZIP中的_external/文件夹手动复制回去。",
|
||||
helpSettings9: "各部分可折叠展开",
|
||||
helpSettings10: "Wildcard Integration:将WFS通配符目录链接到ComfyUI-Impact-Pack的wildcards目录(Windows为目录联结,其他OS为符号链接);现有文件自动迁移",
|
||||
@@ -3679,13 +3733,13 @@ const LANGUAGES = {
|
||||
|
||||
// -- Tagger Tab --
|
||||
helpTaggerTitle: "Tagger标签",
|
||||
helpTagger1: "使用WD Tagger(ONNX)、SwinV2、DeepDanbooru(.h5)和Ollama VLM进行自动图像标注 — 子标签:Single / Batch / DB",
|
||||
helpTagger1: "使用WD Tagger(ONNX)、SwinV2、DeepDanbooru(.h5)和VLM(Ollama / LM Studio / Lemonade / Unsloth)进行自动图像标注 — 子标签:Single / Batch / DB",
|
||||
helpTagger2: "模型放置:在ComfyUI/models/tagger/<模型名>/ 下为每个模型创建单独子文件夹,必须包含 .onnx + selected_tags.csv(DeepDanbooru为 .h5 + 标签文件)",
|
||||
helpTagger3: "Single标签:将图像拖放到预览区域,或点击Upload选择文件;图库详情面板的Tagger按钮可直接在此处打开所选图像",
|
||||
helpTagger4: "阈值滑块:一般标签的最低置信度(默认0.35);角色阈值:character: 前缀标签的独立阈值(默认0.85)",
|
||||
helpTagger5: "Ollama VLM:勾选复选框可与WD Tagger并行运行视觉模型;设置API URL、选择模型(点击↻刷新列表)并自定义提示词;两个模型的结果将合并",
|
||||
helpTagger5: "VLM打标:勾选复选框可与WD Tagger并行运行视觉模型;点击⚙设置按钮可选择后端(Ollama / LM Studio / Lemonade / Unsloth)、URL、模型、Thinking mode、Max tokens,并卸载模型——与Prompt标签页自身的AI设置相互独立;提示词和Max Tags可在标签页内直接编辑;两个模型的结果将合并",
|
||||
helpTagger6: "生成标签的发送目标:(1) GenUI:P — 追加到生成UI标签的正向提示词并立即应用到已加载工作流;(2) 发送到提示词 — 追加到提示词标签的正向文本区;(3) 保存到图库 — 保存到图库图像元数据(仅限从图库打开的图像);(4) 写入文件 — JPEG写入EXIF(ImageDescription)、PNG写入tEXt(Tags键);(5) 保存到DB — 存入内置SQLite数据库",
|
||||
helpTagger7: "Batch标签:输入目标文件夹路径并配置WD Tagger和Ollama设置,选择输出选项(保存DB〈默认开启〉、写入文件〈EXIF/PNG元数据〉、输出.txt〈在图像同目录生成 <文件名>.txt〉);开始批处理后将处理文件夹内所有图像;进度条和日志实时更新;停止按钮在当前图像处理完成后取消",
|
||||
helpTagger7: "Batch标签:输入目标文件夹路径并配置WD Tagger,启用VLM打标(与Single标签使用相同的⚙设置);选择输出选项(保存DB〈默认开启〉、写入文件〈EXIF/PNG元数据〉、输出.txt〈在图像同目录生成 <文件名>.txt〉);开始批处理后将处理文件夹内所有图像;进度条和日志实时更新;停止按钮在当前图像处理完成后取消",
|
||||
helpTagger8: "DB标签:所有已标注图像的可搜索数据库;点击行可在编辑面板中修改WD标签/VLM标签;保存更新记录,删除移除记录;导出CSV可下载所有记录",
|
||||
helpTagger9: "安装依赖包:python_embeded\\python.exe -m pip install -r requirements.txt;GPU推理请安装onnxruntime-gpu替代onnxruntime;TensorFlow(用于DeepDanbooru)因体积较大默认已注释",
|
||||
|
||||
@@ -3712,7 +3766,7 @@ const LANGUAGES = {
|
||||
helpAi2: "翻译面板:使用 Ollama、LM Studio、Lemonade 或 Unsloth 在日语、英语、中文或自定义语言(Free)之间翻译;⇄ 按钮同时互换语言和文本内容;选择自动保存",
|
||||
helpAi3: "Chat 面板:与 LLM 进行多轮对话;Enter 发送消息,Shift+Enter 换行;Clear 按钮重置对话历史;如果模型支持 tool calling,当你要求生成图像(例如\"生成一张猫的图片\")时,会使用 GenerateUI 中当前加载的工作流执行生成,并在对话中显示结果;面板标题栏的\"允许生成图像\"复选框可开关此功能;如果附加了图像(在 TOOLS 面板中拖放的图像),该图像会作为视觉输入发送给 LLM,调用 generate_image 时会以该图像为基础执行图生图(I2I),而不是文生图;generate_image 还接受可选的生成参数——steps、cfg、sampler_name、scheduler、denoise、seed、width、height、batch_size(该次调用生成的图像数量),以及 aspect_ratio(形如\"3:2\"的比例预设,仅当工作流中存在向 width/height 供值的 Resolution Selector 节点时才会生效,否则忽略);模型未提供的参数将保留当前已加载工作流的设置;已验证可正常支持 tool calling 与视觉功能的模型:Gemma 4:e4b、Qwen 3.5:9b、Ministral 3:3b(Ollama)",
|
||||
helpAi4: "TOOLS 面板 — VLM:拖放图像(PNG/JPG/WebP)并选择任务(图像描述 / 提示词生成 / 标签生成),点击 Run;或选择「Create wildcards」,输入类别名称和数量生成纯文本通配符条目(每行一条);拖放的图像也会作为 Chat 面板的附件共享(在该处显示并用于图生图生成),直到点击 ✕ 按钮清除",
|
||||
helpAi6: "Settings 面板:选择后端(Ollama / LM Studio / Lemonade / Unsloth)、设置 API URL、测试连接、选择模型;Unsloth 即使在本地访问时也始终需要 API 密钥认证——将插件文件夹中的 .env.example 复制为 .env 并设置 UNSLOTH_API_KEY,然后重启 ComfyUI(密钥仅在服务器端读取,绝不会发送到浏览器);还需要在 Unsloth Desktop 应用自身的设置界面中开启「Auto model switching (OpenAI API)」——若保持关闭,除非已在 Unsloth Studio 中手动加载过模型,否则请求会以 HTTP 404 失败;Unsloth 的推理模型会将思考内容放在单独的 reasoning_content 字段中,而不是内联的 <think> 标签里,因此 Max tokens 太小会导致模型把全部配额都用在思考上,返回空白回复——如果回复为空,请调高 Max tokens(建议 2048 以上);Generation 部分 — Thinking mode 开关(默认关闭;Ollama会收到think标志,无论使用哪个后端,关闭时都会从输出中去除<think>...</think>思考块,避免推理模型的思考过程混入Translation/Chat/TOOLS的结果)以及 Max tokens(Ollama: num_predict,LM Studio/Lemonade/Unsloth: max_tokens;0为不限);配置 Free 语言名称;Chat 图像生成部分可让 Chat 触发的文生图使用专用工作流,而不是 GenerateUI 中当前加载的工作流;Chat I2I 生成部分提供相同设置,用于附加图像时的图生图生成;设置保存至 localStorage,并与 Library 面板的 A 标签共享",
|
||||
helpAi6: "Settings 面板:选择后端(Ollama / LM Studio / Lemonade / Unsloth)、设置 API URL、测试连接、选择模型,以及使用「Test connection」右侧的「Unload Model」按钮将已加载的模型从显存/内存中卸载——Ollama 使用 keep_alive:0,LM Studio 使用 /api/v1/models/unload,Lemonade 使用 /api/v1/unload;Unsloth 没有卸载 API,因此会显示不支持的提示;Unsloth 即使在本地访问时也始终需要 API 密钥认证——将插件文件夹中的 .env.example 复制为 .env 并设置 UNSLOTH_API_KEY,然后重启 ComfyUI(密钥仅在服务器端读取,绝不会发送到浏览器);还需要在 Unsloth Desktop 应用自身的设置界面中开启「Auto model switching (OpenAI API)」——若保持关闭,除非已在 Unsloth Studio 中手动加载过模型,否则请求会以 HTTP 404 失败;Unsloth 的推理模型会将思考内容放在单独的 reasoning_content 字段中,而不是内联的 <think> 标签里,因此 Max tokens 太小会导致模型把全部配额都用在思考上,返回空白回复——如果回复为空,请调高 Max tokens(建议 2048 以上);Generation 部分 — Thinking mode 开关(默认关闭;Ollama会收到think标志,无论使用哪个后端,关闭时都会从输出中去除<think>...</think>思考块,避免推理模型的思考过程混入Translation/Chat/TOOLS的结果)以及 Max tokens(Ollama: num_predict,LM Studio/Lemonade/Unsloth: max_tokens;0为不限);配置 Free 语言名称;Chat 图像生成部分可让 Chat 触发的文生图使用专用工作流,而不是 GenerateUI 中当前加载的工作流;Chat I2I 生成部分提供相同设置,用于附加图像时的图生图生成;设置保存至 localStorage,并与 Library 面板的 A 标签共享",
|
||||
helpAi7: "Chat 面板 — SVG:LLM 还可以直接以文本形式生成 SVG 图形,完全不涉及 ComfyUI 工作流;只需要求它用 SVG 绘制内容,如果回复中包含 SVG 代码,会自动渲染为内嵌预览,并提供\"保存到图库\"按钮,将其保存为 .svg 文件到 Gallery 标签页的输出文件夹;该功能不使用 tool calling(函数调用),因此不支持 tool calling 的模型也可以使用",
|
||||
helpAi8: "Chat 面板 — 技能:在消息列表上方的下拉菜单中选择一个技能,其内容会作为 system prompt 添加到对话开头(不会显示在可见的聊天记录中);点击铅笔按钮打开技能管理面板,可创建、编辑、删除 .md 技能文件(保存路径:user/default/Workflow-Studio/ai_skills/);文件开头 --- 之间的 name/description 字段会显示在下拉菜单中;默认内置两个技能:「SVG Icon Generator」(在绘制前先将对象拆解为多个部件,以生成更易识别的 SVG)和「Skill Creator」(通过对话向你提问并起草新的技能文件);当回复中包含```skill代码块时,消息下方会出现「保存为技能」按钮,点击后会打开管理面板并预填内容",
|
||||
helpAi9: "编写技能的小贴士:为 frontmatter 的 name/description 写清楚的内容,便于在下拉菜单和提示中阅读;明确说明期望的输出格式,如果有需要后续提取的成果物(如 SVG 或另一个技能文件),指示它用专门的代码围栏包裹;具体、祈使句式的指令比笼统的说明对本地小模型更有效,附上一个简短示例效果更佳;明确写出硬性约束(禁止内容、安全性、长度限制等),不要指望模型会自行推断;如果不确定怎么写,可以在下拉菜单中选择「Skill Creator」技能并描述你想要的技能,它会通过提问帮你起草",
|
||||
@@ -3937,7 +3991,7 @@ const LANGUAGES = {
|
||||
importError: "导入失败",
|
||||
exportFullBackup: "完整备份 (ZIP)",
|
||||
importFullBackup: "恢复完整备份 (ZIP)",
|
||||
fullBackupHint: "完整备份(ZIP)还包含上方JSON导出无法表示的文件夹型数据(AI Skills、Lab Plan、Style预设)以及Tagger数据库。恢复会覆盖现有文件,恢复后请重启ComfyUI。",
|
||||
fullBackupHint: "完整备份(ZIP)还包含上方JSON导出无法表示的文件夹型数据(AI Skills、Lab Plan、Video Plan、Style预设)以及Tagger数据库。恢复会覆盖现有文件,恢复后请重启ComfyUI。",
|
||||
fullBackupFilesUnit: "个文件",
|
||||
fullBackupIncludeWorkflows: "包含默认工作流文件夹 (user/default/workflows)",
|
||||
fullBackupIncludeWildcard: "包含Impact Pack的wildcard文件夹(如存在)",
|
||||
@@ -4034,31 +4088,29 @@ const LANGUAGES = {
|
||||
helpMetadata5: "支持格式:ComfyUI PNG/WebP/MP4/JSON(标准格式 + Flux.2 / Qwen-Image / Z-Image / Mage-Flow / LongCat / Boogu / HiDream E1 / FireRed / Ernie Image 子图工作流;MP4读取SaveVideo写入的workflow/prompt容器标签,也支持MiniMax H3 ImageToVideo等一体化视频节点)、SD WebUI、SD Forge、Fooocus。",
|
||||
helpMetadata6: "现在它是 Gallery 标签页内的一个子标签(位于 Style_Catalog 右侧),不再是独立的顶层标签页 — 其余操作方式完全相同",
|
||||
|
||||
// -- Video 标签页(MiniMax H3 专用,独立于 GenerateUI) --
|
||||
// -- Video 标签页(支持 MiniMax H3 / LTX-2.5 / Wan2.2,独立于 GenerateUI) --
|
||||
tabVideo: "Video",
|
||||
loadInVideo: "加载到Video",
|
||||
videoTitle: "Video (MiniMax H3)",
|
||||
videoFirstFrame: "First Frame(可选)",
|
||||
videoLastFrame: "Last Frame(可选)",
|
||||
videoDropOrClick: "拖放图片或点击选择",
|
||||
videoPrompt: "Prompt",
|
||||
videoAspectRatio: "Aspect Ratio",
|
||||
videoMegapixels: "Megapixels",
|
||||
videoMultiple: "Multiple",
|
||||
videoDuration: "Duration(秒)",
|
||||
videoNoiseSeed: "Noise Seed",
|
||||
videoRandomizeSeed: "随机化",
|
||||
videoGenerate: "Generate",
|
||||
videoEditPlaceholder: "编辑功能即将推出",
|
||||
videoNoWorkflowLoaded: "尚未加载工作流",
|
||||
videoUnsupportedWorkflow: "该工作流不包含 MiniMax H3 的 Image to Video 节点",
|
||||
videoUnsupportedWorkflow: "该工作流不包含受支持的视频模型节点(MiniMax H3、LTX-2.5 的 Text/Image/First&Last-Frame to Video,或 Wan2.2 的 Text to Video)",
|
||||
videoWorkflowLoadFailed: "工作流加载失败",
|
||||
videoConfirmLoadWorkflow: (name) => `要将“${name}”加载为该 Plan 的工作流吗?`,
|
||||
videoPlanMinOneBlock: "Plan 至少需要一个区块",
|
||||
videoPlanEnterName: "请输入该 Plan 的名称",
|
||||
videoPlanSaved: "Plan 已保存",
|
||||
videoPlanSaveFailed: "Plan 保存失败",
|
||||
videoPlanLoaded: "Plan 已加载",
|
||||
videoPlanLoadFailed: "Plan 加载失败",
|
||||
videoConfirmClearPlan: "要清空当前 Plan 吗?",
|
||||
videoPlanPause: "暂停",
|
||||
videoPlanResume: "继续",
|
||||
videoWorkflowLoaded: (name) => `已加载工作流: ${name}`,
|
||||
videoGenerateSuccess: "视频已生成",
|
||||
videoDoneCount: (n) => `完成(${n} 个文件)`,
|
||||
videoSourceLabel: "视频来源",
|
||||
videoSourceHint: "无需生成,也可在此加载任意视频以使用Frame/GIF工具。",
|
||||
videoSourceDropLabel: "拖放视频或点击选择",
|
||||
videoNoVideo: "暂无视频",
|
||||
videoSourcePreviewPlaceholder: "选择素材或拖放视频",
|
||||
videoResultPreviewPlaceholder: "尚未生成视频",
|
||||
videoPropFrame: "Frame",
|
||||
videoPropGif: "GIF",
|
||||
videoFrameHint: "播放/拖动预览视频到想要的位置,然后点击截取。",
|
||||
@@ -4075,15 +4127,26 @@ const LANGUAGES = {
|
||||
videoGifDoneCount: (n) => `完成(${n} 帧)`,
|
||||
videoGifSaved: (name) => `已保存GIF: ${name}`,
|
||||
videoNoSourceLoaded: "请先准备视频(生成一个,或将文件拖入视频来源)",
|
||||
videoPropProject: "Project",
|
||||
videoProjectHint: "已保存的 Plan",
|
||||
videoProjectEmpty: "暂无已保存的 Plan",
|
||||
videoProjectBlockCount: (n) => `${n} 个区块`,
|
||||
videoProjectDeleteConfirm: (name) => `确定删除 Plan「${name}」吗?`,
|
||||
videoProjectDeleted: "Plan 已删除",
|
||||
videoProjectDeleteFailed: "Plan 删除失败",
|
||||
videoProjectLoadListFailed: "Plan 列表加载失败",
|
||||
helpVideoTitle: "Video 标签页",
|
||||
helpVideoDesc: "MiniMax H3(Image to Video)工作流专用的视频生成标签页,独立于 GenerateUI 标签页运行。",
|
||||
helpVideo1: "设置 first_frame(可选)/last_frame(可选)图片、prompt、aspect_ratio/megapixels/multiple(分辨率)、duration(秒)和 noise_seed,然后点击 Generate。不指定 first_frame 时将以纯文本方式绕过执行,也支持完全没有 LoadImage 节点的工作流。",
|
||||
helpVideo2: "模型选择(UNet/CLIP/VAE/Audio VAE)固定为所加载工作流的默认值,无法在此标签页中修改。",
|
||||
helpVideo3: "可通过 Workflow 标签页详情弹窗中的「加载到Video」按钮,加载包含 MiniMax H3 Image to Video 节点的工作流。不支持的工作流会显示错误。",
|
||||
helpVideo4: "生成的视频(mp4)也可以在 Gallery 标签页中浏览和播放。",
|
||||
helpVideo5: "预览旁边的「Video Source」面板可以拖放或选择任意本地视频(不仅限于生成的视频),无需先运行MiniMax H3即可使用下方的Frame/GIF工具。点击Clear可重置选择。",
|
||||
helpVideoDesc: "支持 MiniMax H3(Image to Video)、LTX-2.5(Text / Image / First & Last Frame to Video)、Wan2.2(Text to Video)工作流的视频生成标签页,独立于 GenerateUI 标签页运行。中央面板的 Plan/Edit 子标签负责批量生成和(未来的)编辑;侧边栏的 Asset/Project 子标签负责浏览已生成的视频和已保存的 Plan。",
|
||||
helpVideo1: "Plan 子标签:顶部设置行包含 Aspect Ratio/Megapixels/Multiple/Duration(秒)/Noise Seed,作为该 Plan 的基础设置——Duration 始终显示并可编辑当前选中区块的值(每个区块保留自己的值),其余字段则是整个 Plan 共用的。下方第二行是 Width/Height/Turbo Mode/Strength/Steps/Prompt Enhance,仅当所加载的工作流实际支持该项时才可输入(详见 helpVideo2)。用「+ Split」「+ Block」「Delete」按钮把时间线分割成多个区块后,每个区块都有自己的 Prompt、Duration 以及 First/Last Image(First Image 可选择“无”、“指定图片”或“使用前一个区块的最后一帧”——若前一个区块已明确设置了 Last Image,则优先使用该图片而非提取帧)。点击 Run 会按顺序生成所有区块,运行中也可以 Pause/Cancel。",
|
||||
helpVideo2: "只有一个区块的 Plan 与旧版单次生成表单效果完全相同。模型选择(UNet/CLIP/VAE/Audio VAE)固定为所加载工作流的默认值。没有 ResolutionSelector 节点的工作流(如 Wan2.2、LTX-2.5 的 First & Last Frame to Video)会禁用 Aspect Ratio/Megapixels/Multiple 字段,改为可以直接编辑工作流自身的 Width/Height。Turbo Mode/Strength/Steps 仅适用于 MiniMax H3 的 turbo LoRA,Prompt Enhance 仅适用于 LTX-2.5——其他模型系列中这些字段保持禁用。Noise Seed 仅在 Wan2.2 的 Text to Video 中会被禁用,因为该变体未公开此输入。",
|
||||
helpVideo3: "在 Workflow 标签页的详情弹窗中使用「加载到Video」按钮,可以加载包含 MiniMax H3 的 Image to Video 节点、LTX-2.5 的 Text/Image/First&Last-Frame to Video 节点、或 Wan2.2 的 Text to Video 节点的工作流——此操作会创建一个仅含一个区块、并以该工作流当前值为初始值的新 Plan。不受支持的工作流会显示错误提示。",
|
||||
helpVideo4: "生成的视频(mp4)会自动出现在 Asset 子标签的 Video Temp 组中,也可以在 Gallery 标签页中浏览和播放。是否整理到 Video Assets,由您自行决定时机。",
|
||||
helpVideo5: "中间面板有两个预览区:左侧显示您在 Asset 子标签中选择的视频,或拖放/选择到左边「Video Source」面板中的任意本地视频(点击 Clear 可重置),无需先运行已加载的视频工作流即可使用 Frame/GIF 工具;右侧始终显示最近一次生成的片段。",
|
||||
helpVideo6: "Frame标签页(右侧面板):播放/拖动预览视频到想要的位置,点击「Capture Frame」在客户端截取该帧,再点击「Save to Output」将其保存为PNG到ComfyUI的输出文件夹。",
|
||||
helpVideo7: "GIF标签页(右侧面板):设置Start/End(秒)、FPS和可选的Max Width,点击「Convert to GIF」后,服务器会解码视频并将动画GIF保存到ComfyUI的输出文件夹。",
|
||||
helpVideo8: "链接功能:将某个区块的 First Image 设置为“使用前一个区块的最后一帧”,即可与上一个片段流畅衔接——如果前一个区块已明确设置了 Last Image,将直接使用该图片;否则会自动从其生成的视频中提取实际的最后一帧。",
|
||||
helpVideo9: "Project标签页(左侧边栏,与Asset并列):浏览所有已保存的 Plan 文件(缩略图、区块数、最后更新时间),点击即可加载到 Plan 编辑器,或用 × 按钮删除;再次点击同一标签会收起面板。",
|
||||
helpVideo10: "高亮颜色:当所加载的工作流实际支持该字段时,Prompt / Duration / First Image / Last Image / Aspect Ratio / Megapixels / Multiple / Noise Seed / Width / Height / Turbo Mode / Strength / Steps / Prompt Enhance 标签会变为与 GenerateUI Model 标签页相同的高亮颜色(可在 Settings 标签页自定义)——例如 Wan2.2 工作流(没有 ResolutionSelector 节点)中,Aspect Ratio / Megapixels / Multiple 不会高亮,取而代之的是 Width / Height 会高亮。",
|
||||
},
|
||||
};
|
||||
|
||||
|
||||
@@ -1,10 +1,11 @@
|
||||
/**
|
||||
* Prompt Tab - AI Assistant (Ollama / LM Studio chat, translate, apply to GenerateUI)
|
||||
* Prompt Tab - AI Assistant (Ollama / LM Studio / Lemonade / Unsloth chat, translate, apply to GenerateUI)
|
||||
*/
|
||||
|
||||
import { showToast } from "./app.js";
|
||||
import { t } from "./i18n.js";
|
||||
import { getAiBackendDefaultUrl } from "./util.js";
|
||||
import { unslothProxy } from "./util.js";
|
||||
import { openAiBackendSettingsModal, getAiBackendConfig } from "./ai-settings-modal.js";
|
||||
|
||||
// ============================================
|
||||
// State
|
||||
@@ -17,64 +18,73 @@ const ollamaState = {
|
||||
|
||||
const PROMPT_AI_KEY = "wfm_prompt_ai_settings";
|
||||
|
||||
function loadPromptAiSettings() {
|
||||
try { return JSON.parse(localStorage.getItem(PROMPT_AI_KEY) || "{}"); } catch { return {}; }
|
||||
}
|
||||
|
||||
// バックエンド変更検知用: モデル一覧を取得した時点のバックエンド名を記録
|
||||
let _promptAiBackendForModels = null;
|
||||
|
||||
export function getPromptAiConfig() {
|
||||
const s = loadPromptAiSettings();
|
||||
const backend = s.backend || "ollama";
|
||||
const url = (s.backendUrl || getAiBackendDefaultUrl(backend)).replace(/\/$/, "");
|
||||
return { backend, url };
|
||||
return getAiBackendConfig(PROMPT_AI_KEY);
|
||||
}
|
||||
|
||||
export async function fetchAiModels() {
|
||||
const { backend, url } = getPromptAiConfig();
|
||||
// Ollama-style messages (with .images) → OpenAI互換 content 配列に変換
|
||||
function _toOpenAiMessages(messages) {
|
||||
return messages.map(msg => {
|
||||
if (msg.images?.length) {
|
||||
return {
|
||||
role: msg.role,
|
||||
content: [
|
||||
{ type: "text", text: msg.content },
|
||||
...msg.images.map(b64 => ({ type: "image_url", image_url: { url: `data:image/jpeg;base64,${b64}` } })),
|
||||
],
|
||||
};
|
||||
}
|
||||
return { role: msg.role, content: msg.content };
|
||||
});
|
||||
}
|
||||
|
||||
function _stripThinkingTags(text) {
|
||||
return (text || "")
|
||||
.replace(/<think>[\s\S]*?<\/think>/gi, "")
|
||||
.replace(/<thinking>[\s\S]*?<\/thinking>/gi, "")
|
||||
.trim();
|
||||
}
|
||||
|
||||
// Ollamaは `think` (bool) と `options.num_predict`、OpenAI互換は `max_tokens` で制御
|
||||
function _applyGenOptions(body, backend, cfg) {
|
||||
if (backend === "ollama") {
|
||||
const res = await fetch(`${url}/api/tags`);
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
return (await res.json()).models?.map(m => m.name) || [];
|
||||
} else {
|
||||
const res = await fetch(`${url}/v1/models`);
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
return ((await res.json()).data || []).map(m => m.id);
|
||||
body.think = !!cfg.thinkingMode;
|
||||
if (cfg.maxTokens > 0) body.options = { ...(body.options || {}), num_predict: cfg.maxTokens };
|
||||
} else if (cfg.maxTokens > 0) {
|
||||
body.max_tokens = cfg.maxTokens;
|
||||
}
|
||||
return body;
|
||||
}
|
||||
|
||||
async function chatWithAi(model, messages) {
|
||||
const { backend, url } = getPromptAiConfig();
|
||||
const cfg = getPromptAiConfig();
|
||||
const { backend, url } = cfg;
|
||||
if (backend === "ollama") {
|
||||
const res = await fetch(`${url}/api/chat`, {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ model, messages, stream: false }),
|
||||
body: JSON.stringify(_applyGenOptions({ model, messages, stream: false }, backend, cfg)),
|
||||
});
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
return (await res.json()).message?.content || "";
|
||||
const text = (await res.json()).message?.content || "";
|
||||
return cfg.thinkingMode ? text : _stripThinkingTags(text);
|
||||
} else if (backend === "unsloth") {
|
||||
const body = _applyGenOptions({ model, messages: _toOpenAiMessages(messages), stream: false }, backend, cfg);
|
||||
const data = await unslothProxy(url, "/v1/chat/completions", "POST", body);
|
||||
const msg = data.choices?.[0]?.message;
|
||||
// Unslothはreasoningを別フィールドで返すため<think>タグに畳んで表示に混ぜる
|
||||
const text = (msg?.reasoning_content ? `<think>${msg.reasoning_content}</think>` : "") + (msg?.content || "");
|
||||
return cfg.thinkingMode ? text : _stripThinkingTags(text);
|
||||
} else {
|
||||
// LM Studio / Lemonade (OpenAI-compatible): convert Ollama-style messages (with .images) to OpenAI content arrays
|
||||
const openAiMessages = messages.map(msg => {
|
||||
if (msg.images?.length) {
|
||||
return {
|
||||
role: msg.role,
|
||||
content: [
|
||||
{ type: "text", text: msg.content },
|
||||
...msg.images.map(b64 => ({ type: "image_url", image_url: { url: `data:image/jpeg;base64,${b64}` } })),
|
||||
],
|
||||
};
|
||||
}
|
||||
return { role: msg.role, content: msg.content };
|
||||
});
|
||||
// LM Studio / Lemonade (OpenAI-compatible)
|
||||
const res = await fetch(`${url}/v1/chat/completions`, {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ model, messages: openAiMessages, stream: false }),
|
||||
body: JSON.stringify(_applyGenOptions({ model, messages: _toOpenAiMessages(messages), stream: false }, backend, cfg)),
|
||||
});
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
return (await res.json()).choices?.[0]?.message?.content || "";
|
||||
const text = (await res.json()).choices?.[0]?.message?.content || "";
|
||||
return cfg.thinkingMode ? text : _stripThinkingTags(text);
|
||||
}
|
||||
}
|
||||
|
||||
@@ -192,37 +202,30 @@ function updateAttachmentDisplay() {
|
||||
container.appendChild(item);
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// Status label (設定モーダルで選択中のbackend/modelを表示)
|
||||
// ============================================
|
||||
|
||||
function _updateStatusLabel() {
|
||||
const status = document.getElementById("wfm-ollama-status");
|
||||
if (!status) return;
|
||||
const { backend, model } = getPromptAiConfig();
|
||||
status.textContent = model ? `${backend}: ${model}` : `${backend}: ${t("selectModelFirst")}`;
|
||||
status.className = model ? "wfm-ollama-status connected" : "wfm-ollama-status error";
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// Send Message
|
||||
// ============================================
|
||||
|
||||
async function sendMessage() {
|
||||
const input = document.getElementById("wfm-ollama-input");
|
||||
const modelSelect = document.getElementById("wfm-ollama-model");
|
||||
if (!input || !modelSelect) return;
|
||||
if (!input) return;
|
||||
|
||||
const message = input.value.trim();
|
||||
if (!message) return;
|
||||
|
||||
// バックエンドが変更されていたらモデル一覧を自動更新
|
||||
const { backend } = getPromptAiConfig();
|
||||
if (backend !== _promptAiBackendForModels) {
|
||||
const status = document.getElementById("wfm-ollama-status");
|
||||
if (status) { status.textContent = `Switching to ${backend}...`; status.className = "wfm-ollama-status"; }
|
||||
try {
|
||||
const models = await fetchAiModels();
|
||||
const savedModel = loadPromptAiSettings().model || "";
|
||||
modelSelect.innerHTML = models.length
|
||||
? models.map(name => `<option value="${name}" ${name === savedModel ? "selected" : ""}>${name}</option>`).join("")
|
||||
: `<option value="">${t("noModelsFound")}</option>`;
|
||||
_promptAiBackendForModels = backend;
|
||||
if (status) { status.textContent = `${models.length} models [${backend}]`; status.className = "wfm-ollama-status connected"; }
|
||||
} catch {
|
||||
if (status) { status.textContent = t("failedConnect"); status.className = "wfm-ollama-status error"; }
|
||||
}
|
||||
}
|
||||
|
||||
const model = modelSelect.value;
|
||||
const { model } = getPromptAiConfig();
|
||||
if (!model) {
|
||||
showToast(t("selectModelFirst"), "error");
|
||||
return;
|
||||
@@ -259,13 +262,12 @@ async function sendMessage() {
|
||||
|
||||
async function sendTranslate(direction) {
|
||||
const input = document.getElementById("wfm-ollama-input");
|
||||
const modelSelect = document.getElementById("wfm-ollama-model");
|
||||
if (!input || !modelSelect) return;
|
||||
if (!input) return;
|
||||
|
||||
const text = input.value.trim();
|
||||
if (!text) return;
|
||||
|
||||
const model = modelSelect.value;
|
||||
const { model } = getPromptAiConfig();
|
||||
if (!model) {
|
||||
showToast(t("selectModelFirst"), "error");
|
||||
return;
|
||||
@@ -318,48 +320,11 @@ function applyToGenerateUI(text) {
|
||||
// ============================================
|
||||
|
||||
export function initAiChatUI() {
|
||||
// AI model refresh
|
||||
async function refreshModels() {
|
||||
const select = document.getElementById("wfm-ollama-model");
|
||||
const status = document.getElementById("wfm-ollama-status");
|
||||
const { backend } = getPromptAiConfig();
|
||||
try {
|
||||
const models = await fetchAiModels();
|
||||
const savedModel = loadPromptAiSettings().model || "";
|
||||
if (select) {
|
||||
select.innerHTML = models.length
|
||||
? models.map(name => `<option value="${name}" ${name === savedModel ? "selected" : ""}>${name}</option>`).join("")
|
||||
: `<option value="">${t("noModelsFound")}</option>`;
|
||||
}
|
||||
_promptAiBackendForModels = backend;
|
||||
if (status) {
|
||||
status.textContent = `${models.length} models [${backend}]`;
|
||||
status.className = "wfm-ollama-status connected";
|
||||
}
|
||||
} catch {
|
||||
if (status) {
|
||||
status.textContent = t("failedConnect");
|
||||
status.className = "wfm-ollama-status error";
|
||||
}
|
||||
}
|
||||
}
|
||||
_updateStatusLabel();
|
||||
|
||||
// Auto-load models on init
|
||||
refreshModels();
|
||||
|
||||
document.getElementById("wfm-ollama-refresh-btn")?.addEventListener("click", refreshModels);
|
||||
|
||||
// Test connection
|
||||
document.getElementById("wfm-ollama-test-btn")?.addEventListener("click", async () => {
|
||||
const status = document.getElementById("wfm-ollama-status");
|
||||
if (status) { status.textContent = "Testing..."; status.className = "wfm-ollama-status"; }
|
||||
try {
|
||||
await fetchAiModels();
|
||||
if (status) { status.textContent = t("connectedCheck"); status.className = "wfm-ollama-status connected"; }
|
||||
await refreshModels();
|
||||
} catch {
|
||||
if (status) { status.textContent = t("failedConnect"); status.className = "wfm-ollama-status error"; }
|
||||
}
|
||||
// Settings modal
|
||||
document.getElementById("wfm-ollama-settings-btn")?.addEventListener("click", () => {
|
||||
openAiBackendSettingsModal(PROMPT_AI_KEY, t("settings"), _updateStatusLabel);
|
||||
});
|
||||
|
||||
// Send message
|
||||
|
||||
@@ -6,7 +6,7 @@ import { showToast } from "./app.js";
|
||||
import { comfyUI } from "./comfyui-client.js";
|
||||
import { t, getLang, getSummaryLang, setLang, setSummaryLang, getLanguageOptions, getSummaryLanguageOptions } from "./i18n.js";
|
||||
|
||||
import { getSettings, readJsonStorage, getAiBackendDefaultUrl } from "./util.js";
|
||||
import { getSettings, readJsonStorage } from "./util.js";
|
||||
|
||||
const SETTINGS_KEY = "wfm_settings";
|
||||
|
||||
@@ -336,6 +336,34 @@ export function applyTextareaFontSize(size) {
|
||||
el.textContent = `${TEXTAREA_FONT_SIZE_TARGETS} { font-size: ${px}px !important; }`;
|
||||
}
|
||||
|
||||
// Video playback volume — shared by every <video> player in the app (Video tab preview,
|
||||
// Gallery detail/lightbox/compare). The browser default for a freshly created <video> element
|
||||
// is always 100%, and Gallery's players are recreated from scratch each time a different video
|
||||
// is opened, so without this the volume silently jumps back to max on every video switch.
|
||||
const VIDEO_VOLUME_DEFAULT = 1;
|
||||
|
||||
export function getVideoVolume() {
|
||||
const v = loadLocalSettings().videoVolume;
|
||||
return typeof v === "number" && v >= 0 && v <= 1 ? v : VIDEO_VOLUME_DEFAULT;
|
||||
}
|
||||
|
||||
function setVideoVolume(volume) {
|
||||
const clamped = Math.max(0, Math.min(1, volume));
|
||||
saveLocalSettings({ videoVolume: clamped });
|
||||
return clamped;
|
||||
}
|
||||
|
||||
// Applies the saved volume to a <video> element, and keeps it in sync with any further change
|
||||
// the user makes via that element's own native controls — so adjusting the volume on any video
|
||||
// player anywhere in the app is remembered for the next video opened anywhere else.
|
||||
export function applyStoredVideoVolume(videoEl) {
|
||||
if (!videoEl) return;
|
||||
videoEl.volume = getVideoVolume();
|
||||
if (videoEl.dataset.wfmVolumeWired) return;
|
||||
videoEl.dataset.wfmVolumeWired = "1";
|
||||
videoEl.addEventListener("volumechange", () => setVideoVolume(videoEl.volume));
|
||||
}
|
||||
|
||||
// JSON highlight color settings
|
||||
const JSON_COLOR_STYLE_ID = "wfm-json-color-style";
|
||||
|
||||
@@ -378,7 +406,7 @@ export function applyModelTabActiveColor(color) {
|
||||
el.id = MODEL_ACTIVE_COLOR_STYLE_ID;
|
||||
document.head.appendChild(el);
|
||||
}
|
||||
el.textContent = `.wfm-form-group label.wfm-model-label-active,\n.wfm-settings-summary.wfm-model-label-active,\n#wfm-gen-lora-col-title.wfm-model-label-active,\n.wfm-lab-model-view-btn.wfm-model-label-active { color: ${val}; }`;
|
||||
el.textContent = `.wfm-form-group label.wfm-model-label-active,\n.wfm-settings-summary.wfm-model-label-active,\n#wfm-gen-lora-col-title.wfm-model-label-active,\n.wfm-lab-model-view-btn.wfm-model-label-active,\n.wfm-video-plan-content label.wfm-model-label-active { color: ${val}; }`;
|
||||
}
|
||||
|
||||
export function applyTheme(themeId) {
|
||||
@@ -575,6 +603,24 @@ export async function initSettingsTab() {
|
||||
</div>
|
||||
</details>
|
||||
|
||||
<!-- Video Volume -->
|
||||
<details class="wfm-settings-section" open>
|
||||
<summary class="wfm-settings-summary">${t("videoVolumeLabel") || "Video Volume"}</summary>
|
||||
<div class="wfm-form-group">
|
||||
<label style="display:flex;align-items:center;justify-content:space-between;">
|
||||
<span>${t("videoVolumeLabel") || "Video Volume"}</span>
|
||||
<span id="wfm-video-volume-val" style="font-size:12px;color:var(--wfm-text-secondary);">${Math.round(getVideoVolume() * 100)}%</span>
|
||||
</label>
|
||||
<input type="range" class="wfm-range" id="wfm-video-volume"
|
||||
min="0" max="100" step="1"
|
||||
value="${Math.round(getVideoVolume() * 100)}"
|
||||
style="width:100%;margin-top:4px;">
|
||||
<small style="color:var(--wfm-text-secondary);font-size:11px;display:block;margin-top:4px;">
|
||||
${t("videoVolumeHint") || "Applies to: Video tab preview, Gallery detail/lightbox/compare video players"}
|
||||
</small>
|
||||
</div>
|
||||
</details>
|
||||
|
||||
<!-- RAW JSON Colors -->
|
||||
<details class="wfm-settings-section" open>
|
||||
<summary class="wfm-settings-summary">${t("jsonColorsSection") || "RAW JSON Colors"}</summary>
|
||||
@@ -691,44 +737,6 @@ export async function initSettingsTab() {
|
||||
<button class="wfm-btn wfm-btn-primary wfm-btn-sm" id="wfm-settings-default-ckpt-save">${t("save")}</button>
|
||||
</details>
|
||||
|
||||
<!-- AI Assistant Settings (Prompt Tab) -->
|
||||
<details class="wfm-settings-section">
|
||||
<summary class="wfm-settings-summary">${t("ollamaSettings")}</summary>
|
||||
<div class="wfm-form-group">
|
||||
<label>${t("aiSettingsBackend")}</label>
|
||||
<div class="wfm-ai-backend-row">
|
||||
<label class="wfm-ai-radio-label">
|
||||
<input type="radio" name="wfm-prompt-ai-backend" value="ollama"> Ollama
|
||||
</label>
|
||||
<label class="wfm-ai-radio-label">
|
||||
<input type="radio" name="wfm-prompt-ai-backend" value="lmstudio"> LM Studio
|
||||
</label>
|
||||
<label class="wfm-ai-radio-label">
|
||||
<input type="radio" name="wfm-prompt-ai-backend" value="lemonade"> Lemonade
|
||||
</label>
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-form-group">
|
||||
<label>${t("ollamaUrl")}</label>
|
||||
<input type="text" class="wfm-input" id="wfm-settings-prompt-ai-url"
|
||||
placeholder="http://localhost:11434">
|
||||
</div>
|
||||
<div class="wfm-form-group">
|
||||
<label>${t("ollamaDefaultModel")}</label>
|
||||
<div style="display:flex;gap:8px;">
|
||||
<select class="wfm-select" id="wfm-settings-prompt-ai-model" style="flex:1;">
|
||||
<option value="">${t("selectModel")}</option>
|
||||
</select>
|
||||
<button class="wfm-btn wfm-btn-sm" id="wfm-settings-prompt-ai-refresh">${t("refresh")}</button>
|
||||
</div>
|
||||
</div>
|
||||
<div style="display:flex;gap:8px;margin-top:8px;">
|
||||
<button class="wfm-btn wfm-btn-primary wfm-btn-sm" id="wfm-settings-prompt-ai-save">${t("saveOllama")}</button>
|
||||
<button class="wfm-btn wfm-btn-sm" id="wfm-settings-prompt-ai-test">${t("testConnection")}</button>
|
||||
<span id="wfm-settings-prompt-ai-status" style="font-size:12px;line-height:28px;"></span>
|
||||
</div>
|
||||
</details>
|
||||
|
||||
<!-- CivitAI Settings -->
|
||||
<details class="wfm-settings-section">
|
||||
<summary class="wfm-settings-summary">${t("civitaiApiKeySetting")}</summary>
|
||||
@@ -1158,92 +1166,6 @@ export async function initSettingsTab() {
|
||||
}
|
||||
});
|
||||
|
||||
// --- AI Assistant (Prompt Tab) settings ---
|
||||
const PROMPT_AI_KEY = "wfm_prompt_ai_settings";
|
||||
const loadPromptAiCfg = () => {
|
||||
try { return JSON.parse(localStorage.getItem(PROMPT_AI_KEY) || "{}"); } catch { return {}; }
|
||||
};
|
||||
const savePromptAiCfg = (patch) => {
|
||||
const data = { ...loadPromptAiCfg(), ...patch };
|
||||
localStorage.setItem(PROMPT_AI_KEY, JSON.stringify(data));
|
||||
};
|
||||
|
||||
// Restore saved values into UI
|
||||
const promptAiSaved = loadPromptAiCfg();
|
||||
const promptAiBackendSaved = promptAiSaved.backend || "ollama";
|
||||
document.querySelectorAll('input[name="wfm-prompt-ai-backend"]').forEach(r => {
|
||||
r.checked = r.value === promptAiBackendSaved;
|
||||
});
|
||||
const promptAiUrlEl = document.getElementById("wfm-settings-prompt-ai-url");
|
||||
if (promptAiUrlEl) {
|
||||
promptAiUrlEl.value = promptAiSaved.backendUrl || "";
|
||||
promptAiUrlEl.placeholder = getAiBackendDefaultUrl(promptAiBackendSaved);
|
||||
}
|
||||
|
||||
// Backend change → switch URL to the new backend's default
|
||||
document.querySelectorAll('input[name="wfm-prompt-ai-backend"]').forEach(r => {
|
||||
r.addEventListener("change", () => {
|
||||
const backend = document.querySelector('input[name="wfm-prompt-ai-backend"]:checked')?.value || "ollama";
|
||||
if (promptAiUrlEl) promptAiUrlEl.value = getAiBackendDefaultUrl(backend);
|
||||
});
|
||||
});
|
||||
|
||||
// Load models directly from the selected backend
|
||||
async function loadPromptAiModels() {
|
||||
const select = document.getElementById("wfm-settings-prompt-ai-model");
|
||||
if (!select) return;
|
||||
const backend = document.querySelector('input[name="wfm-prompt-ai-backend"]:checked')?.value || "ollama";
|
||||
const url = (promptAiUrlEl?.value.trim() || getAiBackendDefaultUrl(backend)).replace(/\/$/, "");
|
||||
try {
|
||||
let models = [];
|
||||
if (backend === "ollama") {
|
||||
const res = await fetch(`${url}/api/tags`);
|
||||
models = (await res.json()).models?.map(m => m.name) || [];
|
||||
} else {
|
||||
const res = await fetch(`${url}/v1/models`);
|
||||
models = ((await res.json()).data || []).map(m => m.id);
|
||||
}
|
||||
const saved = loadPromptAiCfg().model || "";
|
||||
select.innerHTML = models.length
|
||||
? models.map(name => `<option value="${name}" ${name === saved ? "selected" : ""}>${name}</option>`).join("")
|
||||
: `<option value="">${t("noModelsFound")}</option>`;
|
||||
} catch {
|
||||
select.innerHTML = `<option value="">${t("failedLoadModels")}</option>`;
|
||||
}
|
||||
}
|
||||
await loadPromptAiModels();
|
||||
|
||||
document.getElementById("wfm-settings-prompt-ai-refresh")?.addEventListener("click", loadPromptAiModels);
|
||||
|
||||
document.getElementById("wfm-settings-prompt-ai-test")?.addEventListener("click", async () => {
|
||||
const statusEl = document.getElementById("wfm-settings-prompt-ai-status");
|
||||
const backend = document.querySelector('input[name="wfm-prompt-ai-backend"]:checked')?.value || "ollama";
|
||||
const url = (promptAiUrlEl?.value.trim() || getAiBackendDefaultUrl(backend)).replace(/\/$/, "");
|
||||
if (statusEl) { statusEl.textContent = t("aiStatusConnecting"); statusEl.style.color = "var(--wfm-text-secondary)"; }
|
||||
try {
|
||||
let count = 0;
|
||||
if (backend === "ollama") {
|
||||
const res = await fetch(`${url}/api/tags`);
|
||||
count = ((await res.json()).models || []).length;
|
||||
} else {
|
||||
const res = await fetch(`${url}/v1/models`);
|
||||
count = ((await res.json()).data || []).length;
|
||||
}
|
||||
if (statusEl) { statusEl.textContent = `${t("ollamaConnected")} (${count} models)`; statusEl.style.color = "var(--wfm-success)"; }
|
||||
await loadPromptAiModels();
|
||||
} catch (err) {
|
||||
if (statusEl) { statusEl.textContent = `${t("ollamaFailed")}: ${err.message}`; statusEl.style.color = "var(--wfm-danger)"; }
|
||||
}
|
||||
});
|
||||
|
||||
document.getElementById("wfm-settings-prompt-ai-save")?.addEventListener("click", () => {
|
||||
const backend = document.querySelector('input[name="wfm-prompt-ai-backend"]:checked')?.value || "ollama";
|
||||
const url = promptAiUrlEl?.value.trim() || "";
|
||||
const model = document.getElementById("wfm-settings-prompt-ai-model")?.value || "";
|
||||
savePromptAiCfg({ backend, backendUrl: url, model });
|
||||
showToast(t("ollamaSaved"), "success");
|
||||
});
|
||||
|
||||
// CivitAI host select
|
||||
document.getElementById("wfm-settings-civitai-host")?.addEventListener("change", async (e) => {
|
||||
const host = e.target.value;
|
||||
@@ -1361,6 +1283,16 @@ export async function initSettingsTab() {
|
||||
applyTextareaFontSize(px);
|
||||
});
|
||||
|
||||
// --- Video volume slider (auto-saves immediately, no "Save" click needed — a dragged
|
||||
// slider that silently didn't persist would defeat the whole point of this setting) ---
|
||||
document.getElementById("wfm-video-volume")?.addEventListener("input", (e) => {
|
||||
const pct = parseInt(e.target.value) || 0;
|
||||
const valEl = document.getElementById("wfm-video-volume-val");
|
||||
if (valEl) valEl.textContent = `${pct}%`;
|
||||
const volume = setVideoVolume(pct / 100);
|
||||
document.querySelectorAll("video").forEach((v) => { v.volume = volume; });
|
||||
});
|
||||
|
||||
// --- JSON highlight color pickers ---
|
||||
document.getElementById("wfm-json-color-grid")?.addEventListener("input", (e) => {
|
||||
if (e.target.type !== "color") return;
|
||||
|
||||
@@ -1,10 +1,16 @@
|
||||
/**
|
||||
* Tagger Tab
|
||||
* Handles WD Tagger / DeepDanbooru + Ollama VLM single/batch tagging.
|
||||
* Handles WD Tagger / DeepDanbooru + VLM (Ollama/LM Studio/Lemonade/Unsloth) single/batch tagging.
|
||||
*/
|
||||
|
||||
import { t } from "./i18n.js";
|
||||
import { showToast } from "./app.js";
|
||||
import { openAiBackendSettingsModal, getAiBackendConfig } from "./ai-settings-modal.js";
|
||||
|
||||
const TAGGER_AI_KEY = "wfm_tagger_ai_settings";
|
||||
function getTaggerAiConfig() {
|
||||
return getAiBackendConfig(TAGGER_AI_KEY);
|
||||
}
|
||||
|
||||
// ── 状態 ────────────────────────────────────────────────────────
|
||||
|
||||
@@ -32,7 +38,7 @@ export function initTaggerTab() {
|
||||
_setupBatchActions();
|
||||
_setupDbActions();
|
||||
_loadModels();
|
||||
_loadSettings();
|
||||
_updateVlmBackendIndicators();
|
||||
}
|
||||
|
||||
/** GalleryタブからTaggerタブへ画像を渡す */
|
||||
@@ -74,8 +80,6 @@ function _applyI18n() {
|
||||
"wfm-tagger-char-threshold-label": "taggerCharThreshold",
|
||||
"wfm-tagger-generate-btn": "taggerGenerateTags",
|
||||
"wfm-tagger-ollama-header-label": "taggerOllamaEnable",
|
||||
"wfm-tagger-ollama-url-label": "taggerOllamaUrl",
|
||||
"wfm-tagger-ollama-model-label": "taggerOllamaModel",
|
||||
"wfm-tagger-ollama-prompt-label": "taggerOllamaPrompt",
|
||||
"wfm-tagger-ollama-max-label": "taggerOllamaMaxTags",
|
||||
"wfm-tagger-result-header": "taggerResult",
|
||||
@@ -87,8 +91,7 @@ function _applyI18n() {
|
||||
"wfm-tagger-batch-folder-header": "taggerBatchFolder",
|
||||
"wfm-tagger-batch-threshold-label": "taggerThreshold",
|
||||
"wfm-tagger-batch-char-threshold-label": "taggerCharThreshold",
|
||||
"wfm-tagger-batch-url-label": "taggerOllamaUrl",
|
||||
"wfm-tagger-batch-model-label": "taggerOllamaModel",
|
||||
"wfm-tagger-batch-ollama-header-label": "taggerOllamaEnable",
|
||||
"wfm-tagger-batch-prompt-label": "taggerOllamaPrompt",
|
||||
"wfm-tagger-batch-output-header": "taggerBatchOutput",
|
||||
"wfm-tagger-batch-save-db-label": "taggerSaveToDB",
|
||||
@@ -113,6 +116,11 @@ function _applyI18n() {
|
||||
if (el) el.textContent = t(key);
|
||||
}
|
||||
|
||||
["wfm-tagger-ollama-settings-btn", "wfm-tagger-batch-ollama-settings-btn"].forEach(id => {
|
||||
const el = document.getElementById(id);
|
||||
if (el) el.title = t("settings");
|
||||
});
|
||||
|
||||
// サブタブボタン
|
||||
const subtabKeys = ["taggerSingleTab", "taggerBatchTab", "taggerDbTab"];
|
||||
document.querySelectorAll(".wfm-tagger-subtab-btn").forEach((btn, i) => {
|
||||
@@ -168,6 +176,24 @@ function _setupOllamaToggle() {
|
||||
});
|
||||
wrap.style.display = chk.checked ? "" : "none";
|
||||
}
|
||||
|
||||
document.getElementById("wfm-tagger-ollama-settings-btn")?.addEventListener("click", () => {
|
||||
openAiBackendSettingsModal(TAGGER_AI_KEY, t("settings"), _updateVlmBackendIndicators);
|
||||
});
|
||||
document.getElementById("wfm-tagger-batch-ollama-settings-btn")?.addEventListener("click", () => {
|
||||
openAiBackendSettingsModal(TAGGER_AI_KEY, t("settings"), _updateVlmBackendIndicators);
|
||||
});
|
||||
}
|
||||
|
||||
// ── VLMバックエンド表示 (Taggerタブ独自のAI設定を参照) ────────────
|
||||
|
||||
function _updateVlmBackendIndicators() {
|
||||
const { backend, model } = getTaggerAiConfig();
|
||||
const label = `${backend}: ${model || t("taggerNoModel")}`;
|
||||
const singleEl = document.getElementById("wfm-tagger-ollama-backend-value");
|
||||
if (singleEl) singleEl.textContent = label;
|
||||
const batchEl = document.getElementById("wfm-tagger-batch-backend-value");
|
||||
if (batchEl) batchEl.textContent = label;
|
||||
}
|
||||
|
||||
// ── モデル一覧ロード ─────────────────────────────────────────────
|
||||
@@ -188,61 +214,6 @@ async function _loadModels() {
|
||||
}
|
||||
}
|
||||
|
||||
// ── Ollamaモデル一覧ロード ───────────────────────────────────────
|
||||
|
||||
async function _loadOllamaModels(urlId, selId) {
|
||||
const urlEl = document.getElementById(urlId);
|
||||
const selEl = document.getElementById(selId);
|
||||
if (!urlEl || !selEl) return;
|
||||
const api = urlEl.value || "http://127.0.0.1:11434";
|
||||
try {
|
||||
const res = await fetch(`/wfm/tagger/ollama/models?api_url=${encodeURIComponent(api)}`);
|
||||
const data = await res.json();
|
||||
const models = data.models || [];
|
||||
if (models.length === 0) {
|
||||
selEl.innerHTML = `<option value="">(${t("taggerNoModel")})</option>`;
|
||||
} else {
|
||||
selEl.innerHTML = models.map(m => `<option value="${m}">${m}</option>`).join("");
|
||||
}
|
||||
} catch {
|
||||
selEl.innerHTML = `<option value="">(${t("taggerNoModel")})</option>`;
|
||||
}
|
||||
}
|
||||
|
||||
// ── 設定の読み込み/保存 ─────────────────────────────────────────
|
||||
|
||||
async function _loadSettings() {
|
||||
try {
|
||||
const res = await fetch("/wfm/tagger/settings");
|
||||
const data = await res.json();
|
||||
if (data.ollama_url) {
|
||||
const el = document.getElementById("wfm-tagger-ollama-url");
|
||||
if (el) el.value = data.ollama_url;
|
||||
}
|
||||
if (data.batch_ollama_url) {
|
||||
const el = document.getElementById("wfm-tagger-batch-ollama-url");
|
||||
if (el) el.value = data.batch_ollama_url;
|
||||
}
|
||||
} catch {
|
||||
// 初回は無視
|
||||
}
|
||||
}
|
||||
|
||||
async function _saveSettings() {
|
||||
try {
|
||||
await fetch("/wfm/tagger/settings", {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({
|
||||
ollama_url: document.getElementById("wfm-tagger-ollama-url")?.value || "",
|
||||
batch_ollama_url: document.getElementById("wfm-tagger-batch-ollama-url")?.value || "",
|
||||
}),
|
||||
});
|
||||
} catch {
|
||||
// サイレントに失敗
|
||||
}
|
||||
}
|
||||
|
||||
// ── Single サブタブ ─────────────────────────────────────────────
|
||||
|
||||
function _setupSingleActions() {
|
||||
@@ -279,11 +250,6 @@ function _setupSingleActions() {
|
||||
// タグ生成
|
||||
document.getElementById("wfm-tagger-generate-btn")?.addEventListener("click", _generateTags);
|
||||
|
||||
// Ollamaリフレッシュ
|
||||
document.getElementById("wfm-tagger-ollama-refresh-btn")?.addEventListener("click", () => {
|
||||
_loadOllamaModels("wfm-tagger-ollama-url", "wfm-tagger-ollama-model");
|
||||
});
|
||||
|
||||
// 結果アクション
|
||||
document.getElementById("wfm-tagger-send-genui-btn")?.addEventListener("click", _sendToGenUI);
|
||||
document.getElementById("wfm-tagger-send-prompt-btn")?.addEventListener("click", _sendToPrompt);
|
||||
@@ -321,8 +287,7 @@ async function _generateTags() {
|
||||
const threshold = parseFloat(document.getElementById("wfm-tagger-threshold")?.value || "0.35");
|
||||
const charThreshold = parseFloat(document.getElementById("wfm-tagger-char-threshold")?.value || "0.85");
|
||||
const useOllama = document.getElementById("wfm-tagger-ollama-enable")?.checked || false;
|
||||
const ollamaUrl = document.getElementById("wfm-tagger-ollama-url")?.value || "http://127.0.0.1:11434";
|
||||
const ollamaModel = document.getElementById("wfm-tagger-ollama-model")?.value || "";
|
||||
const { backend: vlmBackend, url: vlmUrl, model: ollamaModel, thinkingMode, maxTokens } = getTaggerAiConfig();
|
||||
const ollamaPrompt = document.getElementById("wfm-tagger-ollama-prompt")?.value || "";
|
||||
const maxTags = parseInt(document.getElementById("wfm-tagger-ollama-max-tags")?.value || "40");
|
||||
|
||||
@@ -344,12 +309,13 @@ async function _generateTags() {
|
||||
}
|
||||
|
||||
if (useOllama && ollamaModel) {
|
||||
const res2 = await fetch("/wfm/tagger/ollama/predict", {
|
||||
const res2 = await fetch("/wfm/tagger/vlm/predict", {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({
|
||||
image_b64: state.imageB64, api_url: ollamaUrl,
|
||||
image_b64: state.imageB64, backend: vlmBackend, api_url: vlmUrl,
|
||||
model: ollamaModel, prompt: ollamaPrompt, max_tags: maxTags,
|
||||
thinking_mode: thinkingMode, max_tokens: maxTokens,
|
||||
}),
|
||||
});
|
||||
const data2 = await res2.json();
|
||||
@@ -361,7 +327,6 @@ async function _generateTags() {
|
||||
if (!tags) { showToast(t("taggerNoTags"), "warning"); return; }
|
||||
document.getElementById("wfm-tagger-result").value = tags;
|
||||
showToast(t("taggerDone"), "success");
|
||||
_saveSettings();
|
||||
} catch (e) {
|
||||
showToast(e.message, "error");
|
||||
} finally {
|
||||
@@ -453,10 +418,6 @@ async function _saveToDb() {
|
||||
// ── Batch サブタブ ───────────────────────────────────────────────
|
||||
|
||||
function _setupBatchActions() {
|
||||
document.getElementById("wfm-tagger-batch-ollama-refresh-btn")?.addEventListener("click", () => {
|
||||
_loadOllamaModels("wfm-tagger-batch-ollama-url", "wfm-tagger-batch-ollama-model");
|
||||
});
|
||||
|
||||
document.getElementById("wfm-tagger-batch-start-btn")?.addEventListener("click", _batchStart);
|
||||
document.getElementById("wfm-tagger-batch-stop-btn")?.addEventListener("click", _batchStop);
|
||||
}
|
||||
@@ -465,15 +426,19 @@ async function _batchStart() {
|
||||
const folder = document.getElementById("wfm-tagger-batch-folder")?.value || "";
|
||||
if (!folder) { showToast(t("taggerBatchFolder"), "warning"); return; }
|
||||
|
||||
const { backend: vlmBackend, url: vlmUrl, model: vlmModel, thinkingMode, maxTokens } = getTaggerAiConfig();
|
||||
const body = {
|
||||
folder,
|
||||
model: document.getElementById("wfm-tagger-batch-model")?.value || "",
|
||||
threshold: parseFloat(document.getElementById("wfm-tagger-batch-threshold")?.value || "0.35"),
|
||||
char_threshold: parseFloat(document.getElementById("wfm-tagger-batch-char-threshold")?.value || "0.85"),
|
||||
use_ollama: document.getElementById("wfm-tagger-batch-ollama-enable")?.checked || false,
|
||||
ollama_api: document.getElementById("wfm-tagger-batch-ollama-url")?.value || "http://127.0.0.1:11434",
|
||||
ollama_model: document.getElementById("wfm-tagger-batch-ollama-model")?.value || "",
|
||||
vlm_backend: vlmBackend,
|
||||
vlm_api_url: vlmUrl,
|
||||
ollama_model: vlmModel,
|
||||
ollama_prompt: document.getElementById("wfm-tagger-batch-ollama-prompt")?.value || "",
|
||||
thinking_mode: thinkingMode,
|
||||
max_tokens: maxTokens,
|
||||
save_db: document.getElementById("wfm-tagger-batch-save-db")?.checked ?? true,
|
||||
write_file: document.getElementById("wfm-tagger-batch-write-file")?.checked || false,
|
||||
write_txt: document.getElementById("wfm-tagger-batch-write-txt")?.checked || false,
|
||||
|
||||
@@ -109,6 +109,52 @@ export function getAiBackendDefaultUrl(backend) {
|
||||
return AI_BACKEND_DEFAULT_URLS[backend] || AI_BACKEND_DEFAULT_URLS.ollama;
|
||||
}
|
||||
|
||||
// Unslothはローカルでも常にAPIキーが必要なため、フロントから直接叩かず
|
||||
// サーバー側プロキシ(/api/wfm/unsloth/proxy)経由でキーを付与して中継する
|
||||
// (see py/routes/unsloth_routes.py)
|
||||
export async function unslothProxy(baseUrl, path, method, payload) {
|
||||
const res = await fetch("/api/wfm/unsloth/proxy", {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ baseUrl, path, method, payload }),
|
||||
});
|
||||
const data = await res.json().catch(() => ({}));
|
||||
if (!res.ok) throw new Error(data.message || `HTTP ${res.status}`);
|
||||
return data;
|
||||
}
|
||||
|
||||
// ローカルVLM/LLMバックエンドからモデルをVRAM/メモリからアンロードする。
|
||||
// 公式APIが存在しない場合(Unsloth)は "UNSUPPORTED" エラーを投げる。
|
||||
export async function unloadAiModel(url, backend, model) {
|
||||
if (!model) throw new Error("No model selected");
|
||||
if (backend === "ollama") {
|
||||
// keep_alive:0 + 空プロンプトが公式に文書化されたアンロード方法
|
||||
// (専用エンドポイントは存在しない) https://docs.ollama.com/api
|
||||
const res = await fetch(`${url}/api/generate`, {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ model, prompt: "", keep_alive: 0 }),
|
||||
});
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
} else if (backend === "lmstudio") {
|
||||
const res = await fetch(`${url}/api/v1/models/unload`, {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ instance_id: model }),
|
||||
});
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
} else if (backend === "lemonade") {
|
||||
const res = await fetch(`${url}/api/v1/unload`, {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ model_name: model }),
|
||||
});
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
} else {
|
||||
throw new Error("UNSUPPORTED");
|
||||
}
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// Eagle Auto-Save
|
||||
// ============================================
|
||||
|
||||
@@ -0,0 +1,296 @@
|
||||
/**
|
||||
* Video Tab - Asset subtab: browses the videos a Plan run has generated.
|
||||
*
|
||||
* Deliberately thin — it reuses Gallery's existing backend (groups, tags/memo
|
||||
* sidecar, thumbnailing) exactly like feeder-tab.js's own Gallery mode does,
|
||||
* rather than re-implementing folder browsing, bulk selection, etc. Anything
|
||||
* beyond basic browsing/tagging (move, export, delete, multi-select) is left
|
||||
* to the real Gallery tab via the "Open in Gallery" button.
|
||||
*/
|
||||
|
||||
import { VIDEO_GROUP, VTEMP_GROUP, ensureVideoGroup } from "./gallery-tab.js";
|
||||
import { setSourcePreview } from "./video-preview.js";
|
||||
|
||||
// Sentinel for the "All Video Assets" option — not a real backend group, since
|
||||
// Gallery's group filter only ever matches one group at a time. Selecting it
|
||||
// fetches VIDEO_GROUP and VTEMP_GROUP separately and merges them (see _loadImages).
|
||||
const ALL_GROUPS_VALUE = "__video_asset_all__";
|
||||
|
||||
// Display names are now identical to the underlying group names (minus the
|
||||
// "__...__" wrapping) — no more per-plan "VideoPlan:<name>" sub-groups, so the
|
||||
// dropdown is always exactly these three fixed entries.
|
||||
const _GROUPS = [ALL_GROUPS_VALUE, VIDEO_GROUP, VTEMP_GROUP];
|
||||
|
||||
const _s = {
|
||||
outputDir: "",
|
||||
group: ALL_GROUPS_VALUE,
|
||||
images: [],
|
||||
selectedPath: null,
|
||||
loaded: false, // becomes true once the Asset subtab has been shown at least once
|
||||
};
|
||||
|
||||
async function _fetchOutputDir() {
|
||||
if (_s.outputDir) return;
|
||||
try {
|
||||
const res = await fetch("/api/wfm/settings/output-dir");
|
||||
if (res.ok) {
|
||||
const data = await res.json();
|
||||
_s.outputDir = (data.current || "").replace(/\\/g, "/").replace(/\/$/, "");
|
||||
}
|
||||
} catch { /* non-critical */ }
|
||||
}
|
||||
|
||||
function _groupLabel(g) {
|
||||
if (g === ALL_GROUPS_VALUE) return "All Video Assets";
|
||||
if (g === VIDEO_GROUP) return "Video Assets";
|
||||
if (g === VTEMP_GROUP) return "Video Temp";
|
||||
return g;
|
||||
}
|
||||
|
||||
function _renderGroupSelect() {
|
||||
const sel = document.getElementById("wfm-video-asset-group");
|
||||
if (!sel) return;
|
||||
sel.innerHTML = _GROUPS
|
||||
.map((g) => `<option value="${g}"${g === _s.group ? " selected" : ""}>${_groupLabel(g)}</option>`)
|
||||
.join("");
|
||||
}
|
||||
|
||||
async function _fetchGroupImages(group) {
|
||||
const params = new URLSearchParams({ folder: _s.outputDir, group, recursive: "true", sort: "date_desc" });
|
||||
const res = await fetch(`/wfm/gallery/images?${params}`);
|
||||
if (!res.ok) throw new Error(String(res.status));
|
||||
const data = await res.json();
|
||||
return data.images || [];
|
||||
}
|
||||
|
||||
async function _loadImages() {
|
||||
const grid = document.getElementById("wfm-video-asset-grid");
|
||||
const statusEl = document.getElementById("wfm-video-asset-status");
|
||||
if (!grid) return;
|
||||
await _fetchOutputDir();
|
||||
if (!_s.outputDir) {
|
||||
grid.innerHTML = `<div class="wfm-placeholder">No output folder configured</div>`;
|
||||
return;
|
||||
}
|
||||
grid.innerHTML = `<div class="wfm-placeholder">Loading...</div>`;
|
||||
try {
|
||||
let images;
|
||||
if (_s.group === ALL_GROUPS_VALUE) {
|
||||
// "All Video Assets" = the union of the curated __Video Assets__
|
||||
// group and __Video Temp__ (auto-populated by every plan run,
|
||||
// organized into __Video Assets__ by the user on their own
|
||||
// schedule) — not a single backend group filter, so fetch both
|
||||
// and merge.
|
||||
const [curated, temp] = await Promise.all([
|
||||
_fetchGroupImages(VIDEO_GROUP),
|
||||
_fetchGroupImages(VTEMP_GROUP),
|
||||
]);
|
||||
const byPath = new Map();
|
||||
for (const img of [...curated, ...temp]) byPath.set(img.path, img);
|
||||
images = Array.from(byPath.values()).sort((a, b) => b.mtime - a.mtime);
|
||||
} else {
|
||||
images = await _fetchGroupImages(_s.group);
|
||||
}
|
||||
_s.images = images;
|
||||
_renderGrid();
|
||||
if (statusEl) statusEl.textContent = `${_s.images.length} video(s)`;
|
||||
} catch (err) {
|
||||
_s.images = [];
|
||||
grid.innerHTML = `<div class="wfm-placeholder" style="color:var(--wfm-danger)">Load failed: ${err.message}</div>`;
|
||||
if (statusEl) statusEl.textContent = "";
|
||||
}
|
||||
}
|
||||
|
||||
function _renderGrid() {
|
||||
const grid = document.getElementById("wfm-video-asset-grid");
|
||||
if (!grid) return;
|
||||
if (_s.images.length === 0) {
|
||||
grid.innerHTML = `<div class="wfm-placeholder">No videos yet</div>`;
|
||||
return;
|
||||
}
|
||||
grid.innerHTML = "";
|
||||
for (const img of _s.images) grid.appendChild(_makeCard(img));
|
||||
}
|
||||
|
||||
function _makeCard(img) {
|
||||
const card = document.createElement("div");
|
||||
card.className = "wfm-video-asset-card" + (img.path === _s.selectedPath ? " selected" : "");
|
||||
card.dataset.path = img.path;
|
||||
|
||||
const thumb = document.createElement("img");
|
||||
thumb.className = "wfm-video-asset-card-img";
|
||||
thumb.loading = "lazy";
|
||||
thumb.src = `/wfm/gallery/image/thumb?path=${encodeURIComponent(img.path)}&w=200`;
|
||||
thumb.onerror = () => { thumb.style.display = "none"; };
|
||||
|
||||
const name = document.createElement("div");
|
||||
name.className = "wfm-video-asset-card-name";
|
||||
name.textContent = img.filename;
|
||||
name.title = img.filename;
|
||||
|
||||
card.append(thumb, name);
|
||||
card.addEventListener("click", () => _selectImage(img));
|
||||
return card;
|
||||
}
|
||||
|
||||
function _selectImage(img) {
|
||||
_s.selectedPath = img.path;
|
||||
document.querySelectorAll(".wfm-video-asset-card").forEach((c) => {
|
||||
c.classList.toggle("selected", c.dataset.path === img.path);
|
||||
});
|
||||
_renderDetail(img);
|
||||
_loadIntoSourcePreview(img);
|
||||
}
|
||||
|
||||
// Feeds the selected asset's video into the center panel's Asset/Source preview
|
||||
// pane (see video-preview.js) so it's visible without switching tabs, and so the
|
||||
// Frame/GIF property tools can operate on it just like a Video Source drop.
|
||||
// Fetched as a Blob and wrapped as a "local" source rather than trying to map
|
||||
// Gallery's arbitrary absolute path onto ComfyUI's filename/subfolder/type
|
||||
// triple — that keeps the GIF tool's existing upload-on-first-use path working
|
||||
// unchanged for both cases.
|
||||
async function _loadIntoSourcePreview(img) {
|
||||
try {
|
||||
const res = await fetch(`/wfm/gallery/image/serve?path=${encodeURIComponent(img.path)}`);
|
||||
if (!res.ok) throw new Error(String(res.status));
|
||||
const blob = await res.blob();
|
||||
const file = new File([blob], img.filename, { type: blob.type || "video/mp4" });
|
||||
setSourcePreview(URL.createObjectURL(file), { kind: "local", file });
|
||||
} catch (err) {
|
||||
console.warn("[VideoAsset] failed to load preview:", err);
|
||||
}
|
||||
}
|
||||
|
||||
function _renderDetail(img) {
|
||||
const panel = document.getElementById("wfm-video-asset-detail");
|
||||
if (!panel) return;
|
||||
// Filename/memo are untrusted (filesystem names, user-entered text) — the
|
||||
// markup skeleton is static, and those two values are assigned afterward
|
||||
// via textContent/.value, never interpolated into the HTML string itself.
|
||||
panel.innerHTML = `
|
||||
<div class="wfm-video-asset-name" id="wfm-video-asset-name"></div>
|
||||
<label>Tags</label>
|
||||
<div class="wfm-video-asset-tags" id="wfm-video-asset-tags"></div>
|
||||
<div style="display:flex;gap:6px;">
|
||||
<input type="text" id="wfm-video-asset-tag-input" class="wfm-input" placeholder="Add tag" style="flex:1;">
|
||||
<button type="button" class="wfm-btn wfm-btn-sm" id="wfm-video-asset-tag-add">Add</button>
|
||||
</div>
|
||||
<label style="margin-top:10px;">Memo</label>
|
||||
<textarea id="wfm-video-asset-memo" class="wfm-textarea" rows="3"></textarea>
|
||||
<button type="button" class="wfm-btn wfm-btn-sm" id="wfm-video-asset-memo-save" style="margin-top:6px;">Save Memo</button>
|
||||
<button type="button" class="wfm-btn wfm-btn-primary wfm-btn-sm" id="wfm-video-asset-open-gallery" style="width:100%;margin-top:12px;">Open in Gallery</button>
|
||||
`;
|
||||
|
||||
const nameEl = document.getElementById("wfm-video-asset-name");
|
||||
if (nameEl) { nameEl.textContent = img.filename; nameEl.title = img.filename; }
|
||||
const memoEl = document.getElementById("wfm-video-asset-memo");
|
||||
if (memoEl) memoEl.value = img.memo || "";
|
||||
|
||||
_renderTags(img);
|
||||
|
||||
panel.querySelector("#wfm-video-asset-tag-add")?.addEventListener("click", async () => {
|
||||
const input = panel.querySelector("#wfm-video-asset-tag-input");
|
||||
const tag = input?.value.trim();
|
||||
if (!tag) return;
|
||||
const tags = Array.from(new Set([...(img.tags || []), tag]));
|
||||
await _saveMeta(img.path, { tags });
|
||||
img.tags = tags;
|
||||
input.value = "";
|
||||
_renderTags(img);
|
||||
});
|
||||
|
||||
panel.querySelector("#wfm-video-asset-memo-save")?.addEventListener("click", async () => {
|
||||
const memo = panel.querySelector("#wfm-video-asset-memo")?.value || "";
|
||||
await _saveMeta(img.path, { memo });
|
||||
img.memo = memo;
|
||||
});
|
||||
|
||||
panel.querySelector("#wfm-video-asset-open-gallery")?.addEventListener("click", () => {
|
||||
document.querySelector('.wfm-tab[data-tab="gallery"]')?.click();
|
||||
const filterSel = document.getElementById("wfm-gallery-group-filter");
|
||||
if (filterSel) {
|
||||
// ALL_GROUPS_VALUE is a virtual union with no Gallery-side equivalent
|
||||
// (Gallery's own filter only ever matches one real group) — fall back
|
||||
// to the curated group, the closer of the two to "everything worth keeping".
|
||||
filterSel.value = _s.group === ALL_GROUPS_VALUE ? VIDEO_GROUP : _s.group;
|
||||
filterSel.dispatchEvent(new Event("change"));
|
||||
}
|
||||
});
|
||||
}
|
||||
|
||||
function _renderTags(img) {
|
||||
const container = document.getElementById("wfm-video-asset-tags");
|
||||
if (!container) return;
|
||||
const tags = img.tags || [];
|
||||
container.innerHTML = "";
|
||||
if (tags.length === 0) {
|
||||
const placeholder = document.createElement("span");
|
||||
placeholder.className = "wfm-placeholder";
|
||||
placeholder.textContent = "No tags";
|
||||
container.appendChild(placeholder);
|
||||
return;
|
||||
}
|
||||
// Built via DOM APIs (not innerHTML) since tag text is user-entered —
|
||||
// textContent keeps it inert regardless of what characters it contains.
|
||||
for (const tag of tags) {
|
||||
const pill = document.createElement("span");
|
||||
pill.className = "wfm-video-asset-tag";
|
||||
pill.append(document.createTextNode(`${tag} `));
|
||||
|
||||
const removeBtn = document.createElement("button");
|
||||
removeBtn.type = "button";
|
||||
removeBtn.textContent = "×";
|
||||
removeBtn.addEventListener("click", async () => {
|
||||
const newTags = tags.filter((t2) => t2 !== tag);
|
||||
await _saveMeta(img.path, { tags: newTags });
|
||||
img.tags = newTags;
|
||||
_renderTags(img);
|
||||
});
|
||||
|
||||
pill.appendChild(removeBtn);
|
||||
container.appendChild(pill);
|
||||
}
|
||||
}
|
||||
|
||||
async function _saveMeta(path, data) {
|
||||
try {
|
||||
await fetch("/wfm/gallery/image/meta", {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ path, ...data }),
|
||||
});
|
||||
} catch (err) {
|
||||
console.warn("[VideoAsset] saveMeta failed:", err);
|
||||
}
|
||||
}
|
||||
|
||||
// Called whenever the Asset subtab becomes active (see video-tab.js's subtab
|
||||
// toggle) — always refetches rather than caching, so a Plan run's newly
|
||||
// generated videos show up as soon as the user switches over to look.
|
||||
export async function refreshVideoAssetTab() {
|
||||
if (!_s.loaded) {
|
||||
_renderGroupSelect();
|
||||
_s.loaded = true;
|
||||
}
|
||||
await _loadImages();
|
||||
}
|
||||
|
||||
export function initVideoAssetTab() {
|
||||
document.getElementById("wfm-video-asset-group")?.addEventListener("change", (e) => {
|
||||
_s.group = e.target.value;
|
||||
_s.selectedPath = null;
|
||||
const panel = document.getElementById("wfm-video-asset-detail");
|
||||
if (panel) panel.innerHTML = `<span class="wfm-placeholder">Select a video</span>`;
|
||||
_loadImages();
|
||||
});
|
||||
document.getElementById("wfm-video-asset-refresh")?.addEventListener("click", () => _loadImages());
|
||||
|
||||
// Neither reserved group is ever auto-created by a batch run itself (see
|
||||
// video-plan-tab.js's _ensureVideoAssetGroups, which only ensures
|
||||
// __Video Temp__ right before a run starts), so a fresh install or a group
|
||||
// deleted via Gallery's Manage Groups would otherwise never come back on
|
||||
// its own — add_to_group() happily records membership on individual images
|
||||
// without ever re-registering the group itself. ensureVideoGroup() ensures
|
||||
// both __Video Assets__ and __Video Temp__ every time the Asset subtab inits.
|
||||
ensureVideoGroup();
|
||||
}
|
||||
@@ -0,0 +1,82 @@
|
||||
/**
|
||||
* Video Tab - shared state for the two center-panel preview panes:
|
||||
* "source" (#wfm-video-source-preview-video — an Asset selection or a
|
||||
* locally-dropped file) and "result" (#wfm-video-preview-video — the latest
|
||||
* generated clip). video-asset-tab.js (Asset selection), video-plan-tab.js
|
||||
* (batch run results) and video-tab.js (the Video Source drop zone, Frame/GIF
|
||||
* tools) all need to read or write these. Pulling this into its own module
|
||||
* lets all three depend on it without needing to import each other —
|
||||
* video-tab.js already imports both of the others for init/refresh, so a
|
||||
* reverse import from either back into video-tab.js would create a cycle.
|
||||
*/
|
||||
|
||||
const _PANES = {
|
||||
source: { video: "wfm-video-source-preview-video", placeholder: "wfm-video-source-preview-placeholder" },
|
||||
result: { video: "wfm-video-preview-video", placeholder: "wfm-video-preview-placeholder" },
|
||||
};
|
||||
|
||||
const _objectUrls = { source: null, result: null };
|
||||
|
||||
// Whichever pane most recently received a video is what the Frame/GIF property
|
||||
// tabs act on (see getActivePreviewSource/getActivePreviewVideoElement below) —
|
||||
// an Asset selection or Video Source drop activates "source", a batch run
|
||||
// finishing a block activates "result".
|
||||
let _activePane = null; // "source" | "result" | null
|
||||
let _activeSource = null;
|
||||
|
||||
function _setPreview(pane, url, source) {
|
||||
const ids = _PANES[pane];
|
||||
const video = document.getElementById(ids.video);
|
||||
const placeholder = document.getElementById(ids.placeholder);
|
||||
if (!video || !placeholder) return;
|
||||
|
||||
if (_objectUrls[pane]) {
|
||||
URL.revokeObjectURL(_objectUrls[pane]);
|
||||
_objectUrls[pane] = null;
|
||||
}
|
||||
if (url && url.startsWith("blob:")) _objectUrls[pane] = url;
|
||||
|
||||
if (url) {
|
||||
video.src = url;
|
||||
video.style.display = "block";
|
||||
placeholder.style.display = "none";
|
||||
_activePane = pane;
|
||||
_activeSource = source;
|
||||
} else {
|
||||
video.pause();
|
||||
video.removeAttribute("src");
|
||||
video.load();
|
||||
video.style.display = "none";
|
||||
placeholder.style.display = "";
|
||||
if (_activePane === pane) { _activePane = null; _activeSource = null; }
|
||||
}
|
||||
}
|
||||
|
||||
// Sets (or clears, with url=null) the Asset-selection/Video-Source-drop pane.
|
||||
export function setSourcePreview(url, source) { _setPreview("source", url, source); }
|
||||
|
||||
// Sets (or clears) the generated-result pane — called once per block as a
|
||||
// batch run's video output comes in.
|
||||
export function setResultPreview(url, source) { _setPreview("result", url, source); }
|
||||
|
||||
// What the Frame/GIF property tabs operate on: { kind: "output"|"input", filename,
|
||||
// subfolder, type } for anything already on the server, or { kind: "local", file }
|
||||
// for a picked/dropped file not yet uploaded. null if neither pane has a video.
|
||||
export function getActivePreviewSource() { return _activeSource; }
|
||||
|
||||
// The GIF tab uploads a still-local source on first use and needs to remember
|
||||
// the resulting server-side reference so a repeat conversion doesn't re-upload —
|
||||
// this rewrites the active source in place without touching either <video> element.
|
||||
export function updateActivePreviewSourceRef(source) { _activeSource = source; }
|
||||
|
||||
// The <video> element the Frame/GIF tools should read/capture from, or null if
|
||||
// neither pane currently has a video loaded.
|
||||
export function getActivePreviewVideoElement() {
|
||||
if (!_activePane) return null;
|
||||
return document.getElementById(_PANES[_activePane].video);
|
||||
}
|
||||
|
||||
// Both panes' <video> elements share the same persistent volume setting.
|
||||
export function getAllPreviewVideoElements() {
|
||||
return Object.values(_PANES).map((ids) => document.getElementById(ids.video)).filter(Boolean);
|
||||
}
|
||||
@@ -0,0 +1,126 @@
|
||||
/**
|
||||
* Video Tab - Sidebar "Project" subtab (next to Asset): browses saved Video
|
||||
* Plan files (ws_videoplan_*.json in video_plan/), independent of which plan
|
||||
* (if any) is currently loaded in the Plan editor.
|
||||
*
|
||||
* Deliberately thin, mirroring video-asset-tab.js's own scope — clicking an
|
||||
* item hands off to video-plan-tab.js's openSavedVideoPlan() rather than
|
||||
* re-implementing plan loading here.
|
||||
*/
|
||||
|
||||
import { showToast } from "./app.js";
|
||||
import { t } from "./i18n.js";
|
||||
import { escapeHtml } from "./util.js";
|
||||
import { openSavedVideoPlan } from "./video-plan-tab.js";
|
||||
|
||||
const _s = {
|
||||
plans: [],
|
||||
activeFilename: null,
|
||||
loaded: false, // becomes true once the Project subtab has been shown at least once
|
||||
};
|
||||
|
||||
function _formatUpdatedAt(iso) {
|
||||
if (!iso) return "";
|
||||
const d = new Date(iso);
|
||||
if (isNaN(d.getTime())) return "";
|
||||
return d.toLocaleString();
|
||||
}
|
||||
|
||||
function _renderList() {
|
||||
const list = document.getElementById("wfm-video-project-list");
|
||||
if (!list) return;
|
||||
if (_s.plans.length === 0) {
|
||||
list.innerHTML = `<span class="wfm-placeholder">${t("videoProjectEmpty")}</span>`;
|
||||
return;
|
||||
}
|
||||
list.innerHTML = "";
|
||||
for (const plan of _s.plans) list.appendChild(_makeItem(plan));
|
||||
}
|
||||
|
||||
function _makeItem(plan) {
|
||||
const item = document.createElement("div");
|
||||
item.className = "wfm-video-project-item" + (plan.filename === _s.activeFilename ? " active" : "");
|
||||
item.dataset.filename = plan.filename;
|
||||
|
||||
const thumb = document.createElement("img");
|
||||
thumb.className = "wfm-video-project-item-thumb";
|
||||
thumb.loading = "lazy";
|
||||
if (plan.thumbnail) thumb.src = plan.thumbnail;
|
||||
thumb.onerror = () => { thumb.style.visibility = "hidden"; };
|
||||
|
||||
const info = document.createElement("div");
|
||||
info.className = "wfm-video-project-item-info";
|
||||
|
||||
const name = document.createElement("div");
|
||||
name.className = "wfm-video-project-item-name";
|
||||
name.textContent = plan.name || plan.filename;
|
||||
name.title = plan.filename;
|
||||
|
||||
const meta = document.createElement("div");
|
||||
meta.className = "wfm-video-project-item-meta";
|
||||
const blockLabel = t("videoProjectBlockCount", plan.block_count ?? 0);
|
||||
const updated = _formatUpdatedAt(plan.updated_at);
|
||||
meta.textContent = updated ? `${blockLabel} · ${updated}` : blockLabel;
|
||||
meta.title = plan.note || "";
|
||||
|
||||
info.append(name, meta);
|
||||
|
||||
const deleteBtn = document.createElement("button");
|
||||
deleteBtn.type = "button";
|
||||
deleteBtn.className = "wfm-video-project-item-delete";
|
||||
deleteBtn.textContent = "×";
|
||||
deleteBtn.title = t("delete");
|
||||
deleteBtn.addEventListener("click", (e) => {
|
||||
e.stopPropagation();
|
||||
_deletePlan(plan);
|
||||
});
|
||||
|
||||
item.append(thumb, info, deleteBtn);
|
||||
item.addEventListener("click", () => _openPlan(plan));
|
||||
return item;
|
||||
}
|
||||
|
||||
async function _openPlan(plan) {
|
||||
_s.activeFilename = plan.filename;
|
||||
_renderList();
|
||||
await openSavedVideoPlan(plan.filename);
|
||||
}
|
||||
|
||||
async function _deletePlan(plan) {
|
||||
if (!window.confirm(t("videoProjectDeleteConfirm", plan.name || plan.filename))) return;
|
||||
try {
|
||||
const res = await fetch("/api/wfm/video/plans/delete", {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ filename: plan.filename }),
|
||||
});
|
||||
const json = await res.json();
|
||||
if (!res.ok) throw new Error(json.error || `HTTP ${res.status}`);
|
||||
if (_s.activeFilename === plan.filename) _s.activeFilename = null;
|
||||
showToast(t("videoProjectDeleted"), "success");
|
||||
await refreshVideoProjectTab();
|
||||
} catch (err) {
|
||||
showToast(`${t("videoProjectDeleteFailed")}: ${err.message}`, "error");
|
||||
}
|
||||
}
|
||||
|
||||
// Called whenever the Project subtab becomes active (see video-tab.js's prop-tab
|
||||
// toggle) — always refetches rather than caching, so a plan saved elsewhere
|
||||
// (Plan pane's Save/Save As) shows up as soon as the user switches over to look.
|
||||
export async function refreshVideoProjectTab() {
|
||||
const list = document.getElementById("wfm-video-project-list");
|
||||
if (!list) return;
|
||||
try {
|
||||
const res = await fetch("/api/wfm/video/plans");
|
||||
if (!res.ok) throw new Error(String(res.status));
|
||||
_s.plans = await res.json();
|
||||
_renderList();
|
||||
} catch (err) {
|
||||
list.innerHTML = `<span class="wfm-placeholder" style="color:var(--wfm-danger)">${escapeHtml(t("videoProjectLoadListFailed"))}: ${escapeHtml(err.message)}</span>`;
|
||||
}
|
||||
_s.loaded = true;
|
||||
}
|
||||
|
||||
export function initVideoProjectTab() {
|
||||
document.getElementById("wfm-video-project-refresh")?.addEventListener("click", () => refreshVideoProjectTab());
|
||||
}
|
||||
@@ -1,187 +1,81 @@
|
||||
/**
|
||||
* Video Tab - MiniMax H3 (Image to Video) 専用の動画生成UI
|
||||
* GenerateUIタブとは完全に独立。UI形式ワークフローJSONを直接編集し、
|
||||
* comfyWorkflow.convertUiToApi() でAPI形式に変換して実行する。
|
||||
* 状態は「テンプレートJSON+フォーム値」のみ保持し、生成の都度
|
||||
* structuredClone() したコピーに書き込む(複数回生成をまたいだID不整合を防ぐ)。
|
||||
* Video Tab - top-level orchestration for the Plan / Asset / Edit subtabs, plus
|
||||
* the Frame-capture / GIF-conversion / Video-Source tools (kept exactly as they
|
||||
* were — they don't depend on which subtab is active and stay visible across
|
||||
* all three; see video-tab.css's persistent-panel layout).
|
||||
*
|
||||
* Batch generation (the former single-shot form) now lives in
|
||||
* video-plan-tab.js, and per-block workflow manipulation in video-workflow.js.
|
||||
* This file only re-exports loadWorkflowIntoVideoEditor so workflow-tab.js's
|
||||
* "Load in Video" button needs no changes.
|
||||
*/
|
||||
|
||||
import { showToast } from "./app.js";
|
||||
import { t } from "./i18n.js";
|
||||
import { comfyUI } from "./comfyui-client.js";
|
||||
import { comfyWorkflow } from "./comfyui-workflow.js";
|
||||
import { escapeHtml } from "./util.js";
|
||||
import { applyStoredVideoVolume } from "./settings-tab.js";
|
||||
import { initVideoPlanTab, loadWorkflowIntoVideoEditor } from "./video-plan-tab.js";
|
||||
import { initVideoAssetTab, refreshVideoAssetTab } from "./video-asset-tab.js";
|
||||
import { initVideoProjectTab, refreshVideoProjectTab } from "./video-project-tab.js";
|
||||
import {
|
||||
setSourcePreview, getActivePreviewSource, updateActivePreviewSourceRef,
|
||||
getActivePreviewVideoElement, getAllPreviewVideoElements,
|
||||
} from "./video-preview.js";
|
||||
|
||||
const DEFAULT_WORKFLOW_FILENAME = "minimax_test.json";
|
||||
|
||||
const state = {
|
||||
templateWorkflow: null,
|
||||
templateFilename: null,
|
||||
firstFrameFilename: null,
|
||||
lastFrameFilename: null,
|
||||
generating: false,
|
||||
// Whatever's currently shown in the center preview frame — a just-generated
|
||||
// result, or a video dropped/picked in the Video Source panel. Used by the
|
||||
// Frame/GIF property tabs so they work on any video, not just generated ones.
|
||||
// { kind: "output"|"input", filename, subfolder, type } for anything already on
|
||||
// the server, or { kind: "local", file } for a picked file not yet uploaded.
|
||||
previewSource: null,
|
||||
};
|
||||
export { loadWorkflowIntoVideoEditor };
|
||||
|
||||
// ============================================
|
||||
// ワークフロー取得
|
||||
// Subtab switching — two INDEPENDENT groups sharing the same .wfm-video-subtab-*
|
||||
// look, kept deliberately uncoupled: the sidebar's Asset/Project pair collapses
|
||||
// entirely when re-clicked (nothing needs to always be visible there — Video
|
||||
// Source covers the "load something to work with" case), while the center
|
||||
// Plan/Edit pair is a "always exactly one visible" 2-way tab. Querying each
|
||||
// scoped to its own container (rather than one global querySelectorAll) is
|
||||
// what keeps clicking one from affecting the other.
|
||||
// ============================================
|
||||
|
||||
async function getRawWorkflow(filename) {
|
||||
const res = await fetch(`/api/wfm/workflows/raw?filename=${encodeURIComponent(filename)}`);
|
||||
if (!res.ok) throw new Error(`HTTP ${res.status}`);
|
||||
return await res.json();
|
||||
function _initCenterSubtabToggle() {
|
||||
const scope = document.querySelector(".wfm-video-center-panel");
|
||||
if (!scope) return;
|
||||
scope.querySelectorAll(".wfm-video-subtab-btn").forEach((btn) => {
|
||||
btn.addEventListener("click", () => {
|
||||
const target = btn.dataset.videoSubtab;
|
||||
scope.querySelectorAll(".wfm-video-subtab-btn").forEach((b) => b.classList.remove("active"));
|
||||
btn.classList.add("active");
|
||||
scope.querySelectorAll(".wfm-video-subtab-panel").forEach((p) => {
|
||||
p.style.display = p.dataset.videoSubtabPanel === target ? "" : "none";
|
||||
});
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
// Sidebar Asset/Project pair: clicking a button shows its panel and hides the
|
||||
// other; clicking the already-active button collapses it (both panels hidden),
|
||||
// letting the video preview reclaim the sidebar's width when neither is needed.
|
||||
function _initSidebarSubtabToggle() {
|
||||
const sidebar = document.querySelector(".wfm-video-form-panel");
|
||||
if (!sidebar) return;
|
||||
const buttons = sidebar.querySelectorAll(".wfm-video-subtab-btn");
|
||||
buttons.forEach((btn) => {
|
||||
btn.addEventListener("click", () => {
|
||||
const target = btn.dataset.videoSubtab;
|
||||
const panel = document.getElementById(`wfm-video-subtab-${target}`);
|
||||
const willShow = !!panel && panel.style.display === "none";
|
||||
buttons.forEach((b) => b.classList.remove("active"));
|
||||
sidebar.querySelectorAll(".wfm-video-subtab-panel").forEach((p) => { p.style.display = "none"; });
|
||||
if (willShow) {
|
||||
btn.classList.add("active");
|
||||
panel.style.display = "";
|
||||
if (target === "asset") refreshVideoAssetTab();
|
||||
else if (target === "project") refreshVideoProjectTab();
|
||||
}
|
||||
});
|
||||
});
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// MiniMax H3ノードの動的特定(ノードIDをハードコードしない)
|
||||
// ============================================
|
||||
|
||||
// ノードのinputs[]のうちwidgetキーを持つものだけを抽出した並び順で、名前からインデックスを引く。
|
||||
// widgets_values配列はこの並び順と1:1対応する(link接続されていてもwidgetキーを持つ入力は
|
||||
// widgets_valuesにスロットを持つ「legacy full」形式のため)。
|
||||
function _widgetIndex(node, name) {
|
||||
const widgetInputs = (node?.inputs || []).filter((inp) => inp.widget);
|
||||
return widgetInputs.findIndex((inp) => inp.name === name);
|
||||
}
|
||||
|
||||
function locateMiniMaxNodes(workflow) {
|
||||
if (!Array.isArray(workflow?.nodes) || !Array.isArray(workflow?.links)) return null;
|
||||
|
||||
const sgDef = (workflow.definitions?.subgraphs || [])
|
||||
.find((sg) => (sg.nodes || []).some((n) => n.type === "MiniMaxH3ImageToVideo"));
|
||||
if (!sgDef) return null;
|
||||
|
||||
const instanceNode = workflow.nodes.find((n) => n.type === sgDef.id);
|
||||
if (!instanceNode || !Array.isArray(instanceNode.widgets_values)) return null;
|
||||
|
||||
const firstFrameSlot = instanceNode.inputs.findIndex((inp) => inp.name === "first_frame");
|
||||
const lastFrameSlot = instanceNode.inputs.findIndex((inp) => inp.name === "last_frame");
|
||||
const widthSlot = instanceNode.inputs.findIndex((inp) => inp.name === "width");
|
||||
if (firstFrameSlot === -1 || lastFrameSlot === -1 || widthSlot === -1) return null;
|
||||
|
||||
const findLinkedNode = (targetSlot) => {
|
||||
const link = workflow.links.find((l) => l[3] === instanceNode.id && l[4] === targetSlot);
|
||||
if (!link) return null;
|
||||
return workflow.nodes.find((n) => n.id === link[1]) || null;
|
||||
};
|
||||
|
||||
// first_frameはoptional入力のため、LoadImageノードが接続されていないワークフロー
|
||||
// (テキストのみで動作するT2V構成など)もサポート対象とする。未接続の場合は
|
||||
// loadImageNode: null のまま返し、必要ならrunGeneration側で動的にノードを注入する。
|
||||
const rawLoadImageNode = findLinkedNode(firstFrameSlot);
|
||||
const loadImageNode = (rawLoadImageNode && rawLoadImageNode.type === "LoadImage") ? rawLoadImageNode : null;
|
||||
const resolutionNode = findLinkedNode(widthSlot);
|
||||
if (!resolutionNode || resolutionNode.type !== "ResolutionSelector") return null;
|
||||
|
||||
const promptIdx = _widgetIndex(instanceNode, "prompt");
|
||||
const durationIdx = _widgetIndex(instanceNode, "value_1");
|
||||
if (promptIdx === -1 || durationIdx === -1) return null;
|
||||
|
||||
return {
|
||||
sgDef, instanceNode, loadImageNode, resolutionNode,
|
||||
firstFrameSlot, lastFrameSlot, promptIdx, durationIdx,
|
||||
};
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// ワークフロー読み込み
|
||||
// ============================================
|
||||
|
||||
function _showFramePreview(which, filename) {
|
||||
const previewImg = document.getElementById(`wfm-video-${which}-frame-preview`);
|
||||
const wrap = document.getElementById(`wfm-video-${which}-frame-wrap`);
|
||||
if (!previewImg || !wrap || !filename) return;
|
||||
previewImg.src = `${comfyUI.baseUrl}/view?filename=${encodeURIComponent(filename)}&type=input`;
|
||||
wrap.style.display = "";
|
||||
}
|
||||
|
||||
export async function loadWorkflowIntoVideoEditor(workflow, filename) {
|
||||
const nodes = locateMiniMaxNodes(workflow);
|
||||
if (!nodes) {
|
||||
showToast(t("videoUnsupportedWorkflow"), "error");
|
||||
return false;
|
||||
}
|
||||
|
||||
state.templateWorkflow = workflow;
|
||||
state.templateFilename = filename || "";
|
||||
state.firstFrameFilename = null;
|
||||
state.lastFrameFilename = null;
|
||||
|
||||
const nameEl = document.getElementById("wfm-video-wf-name");
|
||||
if (nameEl) nameEl.textContent = filename || "Loaded Workflow";
|
||||
|
||||
const { instanceNode, resolutionNode, loadImageNode, promptIdx, durationIdx } = nodes;
|
||||
|
||||
const promptEl = document.getElementById("wfm-video-prompt");
|
||||
if (promptEl) promptEl.value = instanceNode.widgets_values[promptIdx] ?? "";
|
||||
|
||||
const durationEl = document.getElementById("wfm-video-duration");
|
||||
if (durationEl) durationEl.value = instanceNode.widgets_values[durationIdx] ?? 2;
|
||||
|
||||
const arIdx = _widgetIndex(resolutionNode, "aspect_ratio");
|
||||
const mpIdx = _widgetIndex(resolutionNode, "megapixels");
|
||||
const multIdx = _widgetIndex(resolutionNode, "multiple");
|
||||
const aspectEl = document.getElementById("wfm-video-aspect-ratio");
|
||||
if (aspectEl && arIdx !== -1 && resolutionNode.widgets_values[arIdx] != null) {
|
||||
aspectEl.value = resolutionNode.widgets_values[arIdx];
|
||||
}
|
||||
const mpEl = document.getElementById("wfm-video-megapixels");
|
||||
if (mpEl && mpIdx !== -1) mpEl.value = resolutionNode.widgets_values[mpIdx] ?? mpEl.value;
|
||||
const multEl = document.getElementById("wfm-video-multiple");
|
||||
if (multEl && multIdx !== -1) multEl.value = resolutionNode.widgets_values[multIdx] ?? multEl.value;
|
||||
|
||||
const fnIdx = _widgetIndex(loadImageNode, "image");
|
||||
if (fnIdx !== -1 && loadImageNode.widgets_values[fnIdx]) {
|
||||
state.firstFrameFilename = loadImageNode.widgets_values[fnIdx];
|
||||
_showFramePreview("first", state.firstFrameFilename);
|
||||
}
|
||||
|
||||
showToast(t("videoWorkflowLoaded", filename || ""), "success");
|
||||
return true;
|
||||
}
|
||||
|
||||
async function loadDefaultWorkflow() {
|
||||
try {
|
||||
const wf = await getRawWorkflow(DEFAULT_WORKFLOW_FILENAME);
|
||||
await loadWorkflowIntoVideoEditor(wf, DEFAULT_WORKFLOW_FILENAME);
|
||||
} catch {
|
||||
// 初回自動ロード失敗は静かに無視する(環境によってファイルが存在しないこともある)。
|
||||
// Workflowタブの「Load in Video」ボタンから明示的に読み込める。
|
||||
}
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// Aspect Ratio 選択肢(object_infoから動的取得、ハードコードしない)
|
||||
// ============================================
|
||||
|
||||
async function _populateAspectRatioOptions() {
|
||||
const select = document.getElementById("wfm-video-aspect-ratio");
|
||||
if (!select) return;
|
||||
try {
|
||||
const info = await comfyUI.fetchObjectInfo("ResolutionSelector");
|
||||
const inputDef = info?.ResolutionSelector?.input?.required?.aspect_ratio;
|
||||
if (!inputDef) return;
|
||||
const first = inputDef[0];
|
||||
let values = null;
|
||||
if (Array.isArray(first)) values = first;
|
||||
else if (typeof first === "string" && Array.isArray(inputDef[1]?.values)) values = inputDef[1].values;
|
||||
else if (typeof first === "string" && Array.isArray(inputDef[1]?.options)) values = inputDef[1].options;
|
||||
if (!values?.length) return;
|
||||
select.innerHTML = values.map((v) => `<option value="${escapeHtml(v)}">${escapeHtml(v)}</option>`).join("");
|
||||
} catch {
|
||||
// ResolutionSelectorが未導入の環境などは選択肢が空のまま(手入力不可のselectなので実質何もできないが、
|
||||
// Videoタブ自体の初期化は継続させる)。
|
||||
}
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// first_frame / last_frame アップロード
|
||||
// first_frame / last_frame アップロード(Video Sourceパネル・Frame/GIFタブと共有する
|
||||
// 汎用ドロップゾーン配線ヘルパー。video-plan-tab.jsのブロック画像アップロードとは別物)
|
||||
// ============================================
|
||||
|
||||
function _wireDropZone(dropZoneId, fileInputId, onFile) {
|
||||
@@ -200,279 +94,6 @@ function _wireDropZone(dropZoneId, fileInputId, onFile) {
|
||||
});
|
||||
}
|
||||
|
||||
async function _handleFrameUpload(which, file) {
|
||||
if (!file || !file.type.startsWith("image/")) return;
|
||||
const statusEl = document.getElementById(`wfm-video-${which}-frame-status`);
|
||||
const previewImg = document.getElementById(`wfm-video-${which}-frame-preview`);
|
||||
const wrap = document.getElementById(`wfm-video-${which}-frame-wrap`);
|
||||
if (previewImg) previewImg.src = URL.createObjectURL(file);
|
||||
if (wrap) wrap.style.display = "";
|
||||
if (statusEl) statusEl.textContent = "Uploading...";
|
||||
try {
|
||||
const result = await comfyUI.uploadImage(file, file.name);
|
||||
if (which === "first") state.firstFrameFilename = result.name;
|
||||
else state.lastFrameFilename = result.name;
|
||||
if (statusEl) {
|
||||
statusEl.textContent = `✓ ${result.name}`;
|
||||
statusEl.style.color = "var(--wfm-success)";
|
||||
}
|
||||
} catch (err) {
|
||||
if (statusEl) {
|
||||
statusEl.textContent = `✗ ${err.message}`;
|
||||
statusEl.style.color = "var(--wfm-danger)";
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
function _clearFrame(which) {
|
||||
if (which === "first") state.firstFrameFilename = null;
|
||||
else state.lastFrameFilename = null;
|
||||
const wrap = document.getElementById(`wfm-video-${which}-frame-wrap`);
|
||||
const previewImg = document.getElementById(`wfm-video-${which}-frame-preview`);
|
||||
const statusEl = document.getElementById(`wfm-video-${which}-frame-status`);
|
||||
const fileInput = document.getElementById(`wfm-video-${which}-frame-file`);
|
||||
if (wrap) wrap.style.display = "none";
|
||||
if (previewImg) previewImg.src = "";
|
||||
if (statusEl) statusEl.textContent = "";
|
||||
if (fileInput) fileInput.value = "";
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// フォーム値の読み取り・ワークフローへの反映
|
||||
// ============================================
|
||||
|
||||
function _readFormValues() {
|
||||
return {
|
||||
prompt: document.getElementById("wfm-video-prompt")?.value || "",
|
||||
aspectRatio: document.getElementById("wfm-video-aspect-ratio")?.value || "",
|
||||
megapixels: Number(document.getElementById("wfm-video-megapixels")?.value) || 0.2,
|
||||
multiple: Number(document.getElementById("wfm-video-multiple")?.value) || 32,
|
||||
duration: Number(document.getElementById("wfm-video-duration")?.value) || 2,
|
||||
};
|
||||
}
|
||||
|
||||
function _applyFormToWorkflow(nodes, form) {
|
||||
const { instanceNode, resolutionNode, loadImageNode, promptIdx, durationIdx } = nodes;
|
||||
|
||||
instanceNode.widgets_values[promptIdx] = form.prompt;
|
||||
instanceNode.widgets_values[durationIdx] = form.duration;
|
||||
|
||||
const arIdx = _widgetIndex(resolutionNode, "aspect_ratio");
|
||||
const mpIdx = _widgetIndex(resolutionNode, "megapixels");
|
||||
const multIdx = _widgetIndex(resolutionNode, "multiple");
|
||||
if (arIdx !== -1) resolutionNode.widgets_values[arIdx] = form.aspectRatio;
|
||||
if (mpIdx !== -1) resolutionNode.widgets_values[mpIdx] = form.megapixels;
|
||||
if (multIdx !== -1) resolutionNode.widgets_values[multIdx] = form.multiple;
|
||||
|
||||
// first_frameは既存のLoadImageノードが接続されている場合のみここで書き換える。
|
||||
// 接続が無い場合(loadImageNode: null)は、first_frameが新規指定された時だけ
|
||||
// _injectFrameNode()でノードごと注入する(未指定ならバイパス=未接続のまま実行)。
|
||||
if (loadImageNode) {
|
||||
const fnIdx = _widgetIndex(loadImageNode, "image");
|
||||
if (fnIdx !== -1) loadImageNode.widgets_values[fnIdx] = state.firstFrameFilename;
|
||||
}
|
||||
}
|
||||
|
||||
// first_frame/last_frameが未接続のワークフローに対して、画像が指定された時だけ
|
||||
// LoadImageノードを新規注入する共通ヘルパー。ノードID/リンクIDはclone内の実際の
|
||||
// 最大値+1で採番するため、重複ID/リンクID不整合は起きない
|
||||
// (CLAUDE.md記載の既知の落とし穴への対策)。未指定時は何もしない
|
||||
// (テンプレート由来のlink:nullのまま=クリーンな状態を毎回cloneするので残留の心配がない=バイパス扱い)。
|
||||
function _injectFrameNode(clone, instanceNode, targetSlot, filename) {
|
||||
const maxNodeId = Math.max(clone.last_node_id || 0, ...clone.nodes.map((n) => n.id));
|
||||
const maxLinkId = Math.max(clone.last_link_id || 0, ...clone.links.map((l) => l[0]));
|
||||
const newNodeId = maxNodeId + 1;
|
||||
const newLinkId = maxLinkId + 1;
|
||||
|
||||
clone.nodes.push({
|
||||
id: newNodeId,
|
||||
type: "LoadImage",
|
||||
pos: [(instanceNode.pos?.[0] || 0) - 260, (instanceNode.pos?.[1] || 0) + 40],
|
||||
size: [280, 314],
|
||||
flags: {},
|
||||
order: clone.nodes.length,
|
||||
mode: 0,
|
||||
inputs: [
|
||||
{ localized_name: "image", name: "image", type: "COMBO", widget: { name: "image" }, link: null },
|
||||
{ localized_name: "choose file to upload", name: "upload", type: "IMAGEUPLOAD", widget: { name: "upload" }, link: null },
|
||||
],
|
||||
outputs: [
|
||||
{ localized_name: "IMAGE", name: "IMAGE", type: "IMAGE", links: [newLinkId] },
|
||||
{ localized_name: "MASK", name: "MASK", type: "MASK", links: null },
|
||||
],
|
||||
properties: { "Node name for S&R": "LoadImage" },
|
||||
widgets_values: [filename, "image"],
|
||||
});
|
||||
|
||||
clone.links.push([newLinkId, newNodeId, 0, instanceNode.id, targetSlot, "IMAGE"]);
|
||||
const targetInput = instanceNode.inputs[targetSlot];
|
||||
if (targetInput) targetInput.link = newLinkId;
|
||||
|
||||
clone.last_node_id = newNodeId;
|
||||
clone.last_link_id = newLinkId;
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// 実行
|
||||
// ============================================
|
||||
|
||||
async function runGeneration() {
|
||||
if (state.generating) return;
|
||||
if (!state.templateWorkflow) {
|
||||
showToast(t("videoNoWorkflowLoaded"), "error");
|
||||
return;
|
||||
}
|
||||
|
||||
const clone = structuredClone(state.templateWorkflow);
|
||||
const nodes = locateMiniMaxNodes(clone);
|
||||
if (!nodes) {
|
||||
showToast(t("videoUnsupportedWorkflow"), "error");
|
||||
return;
|
||||
}
|
||||
|
||||
_applyFormToWorkflow(nodes, _readFormValues());
|
||||
// first_frame: 既存のLoadImageノードが無いワークフロー(T2V構成等)で、
|
||||
// ユーザーが新たに画像を指定した場合のみノードを注入する。未指定ならバイパス(未接続のまま実行)。
|
||||
if (!nodes.loadImageNode && state.firstFrameFilename) {
|
||||
_injectFrameNode(clone, nodes.instanceNode, nodes.firstFrameSlot, state.firstFrameFilename);
|
||||
}
|
||||
if (state.lastFrameFilename) {
|
||||
_injectFrameNode(clone, nodes.instanceNode, nodes.lastFrameSlot, state.lastFrameFilename);
|
||||
}
|
||||
|
||||
const genBtn = document.getElementById("wfm-video-generate-btn");
|
||||
const progressBar = document.getElementById("wfm-video-progress-bar");
|
||||
const progressText = document.getElementById("wfm-video-progress-text");
|
||||
|
||||
state.generating = true;
|
||||
if (genBtn) genBtn.disabled = true;
|
||||
if (progressBar) progressBar.style.width = "0%";
|
||||
if (progressText) progressText.textContent = "Converting workflow...";
|
||||
|
||||
try {
|
||||
const apiWorkflow = await comfyWorkflow.convertUiToApi(clone);
|
||||
|
||||
const seedValue = Number(document.getElementById("wfm-video-noise-seed")?.value) || 0;
|
||||
const seedMode = document.getElementById("wfm-video-seed-randomize")?.checked ? "random" : "fixed";
|
||||
|
||||
const { images, seed } = await comfyUI.generate(apiWorkflow, {
|
||||
seedMode,
|
||||
seedValue,
|
||||
timeoutMs: 30 * 60 * 1000, // 動画生成は静止画より長時間になりうる
|
||||
onProgress: (pct) => {
|
||||
if (progressBar) progressBar.style.width = `${(pct * 100).toFixed(1)}%`;
|
||||
if (progressText) progressText.textContent = `${(pct * 100).toFixed(0)}%`;
|
||||
},
|
||||
});
|
||||
|
||||
const seedEl = document.getElementById("wfm-video-noise-seed");
|
||||
if (seedEl) seedEl.value = seed;
|
||||
|
||||
const outputMedia = images.filter((img) => img.type !== "temp");
|
||||
if (progressText) progressText.textContent = t("videoDoneCount", outputMedia.length);
|
||||
if (progressBar) progressBar.style.width = "100%";
|
||||
|
||||
_renderResult(outputMedia);
|
||||
await _saveGeneratedVideoMeta(outputMedia, apiWorkflow);
|
||||
showToast(t("videoGenerateSuccess"), "success");
|
||||
} catch (err) {
|
||||
showToast(t("errorWithMsg", err.message), "error");
|
||||
if (progressText) progressText.textContent = "Error";
|
||||
} finally {
|
||||
state.generating = false;
|
||||
if (genBtn) genBtn.disabled = false;
|
||||
}
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// 結果表示
|
||||
// ============================================
|
||||
|
||||
// Sets (or clears) the center preview frame's video and records where it came from —
|
||||
// `source` is what the Frame/GIF property tabs act on (see state.previewSource above).
|
||||
// Revokes the previous blob: URL (if any) so picking a series of local files doesn't
|
||||
// leak memory.
|
||||
let _previewObjectUrl = null;
|
||||
|
||||
function _setPreviewMedia(url, source) {
|
||||
state.previewSource = source;
|
||||
const video = document.getElementById("wfm-video-preview-video");
|
||||
const placeholder = document.getElementById("wfm-video-preview-placeholder");
|
||||
if (!video || !placeholder) return;
|
||||
|
||||
if (_previewObjectUrl) {
|
||||
URL.revokeObjectURL(_previewObjectUrl);
|
||||
_previewObjectUrl = null;
|
||||
}
|
||||
if (url && url.startsWith("blob:")) _previewObjectUrl = url;
|
||||
|
||||
if (url) {
|
||||
video.src = url;
|
||||
video.style.display = "block";
|
||||
placeholder.style.display = "none";
|
||||
} else {
|
||||
video.pause();
|
||||
video.removeAttribute("src");
|
||||
video.load();
|
||||
video.style.display = "none";
|
||||
placeholder.style.display = "";
|
||||
}
|
||||
}
|
||||
|
||||
function _renderResult(images) {
|
||||
// MiniMax H3 always emits a single VIDEO output — but guard generically (prefer
|
||||
// an mp4 if present) in case a future video workflow's SaveVideo/PreviewVideo
|
||||
// ordering differs.
|
||||
const media = (images || []).find((img) => img.filename.toLowerCase().endsWith(".mp4")) || images?.[0];
|
||||
if (!media) {
|
||||
_setPreviewMedia(null, null);
|
||||
return;
|
||||
}
|
||||
const params = new URLSearchParams({ filename: media.filename, subfolder: media.subfolder || "", type: media.type || "output" });
|
||||
const src = `${comfyUI.baseUrl}/view?${params}`;
|
||||
_setPreviewMedia(src, {
|
||||
kind: media.type === "input" ? "input" : "output",
|
||||
filename: media.filename,
|
||||
subfolder: media.subfolder || "",
|
||||
type: media.type || "output",
|
||||
});
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// Gallery連携(生成結果のワークフローをサイドカーメタとして保存)
|
||||
// ============================================
|
||||
|
||||
let _outputDir = "";
|
||||
|
||||
async function _fetchOutputDir() {
|
||||
try {
|
||||
const res = await fetch("/api/wfm/settings/output-dir");
|
||||
if (res.ok) {
|
||||
const data = await res.json();
|
||||
_outputDir = (data.current || "").replace(/\\/g, "/").replace(/\/$/, "");
|
||||
}
|
||||
} catch { /* non-critical */ }
|
||||
}
|
||||
|
||||
async function _saveGeneratedVideoMeta(images, workflow) {
|
||||
if (!_outputDir) await _fetchOutputDir();
|
||||
if (!_outputDir) return;
|
||||
for (const img of images) {
|
||||
if (img.type !== "output") continue;
|
||||
const parts = [_outputDir];
|
||||
if (img.subfolder) parts.push(img.subfolder);
|
||||
parts.push(img.filename);
|
||||
const path = parts.join("/");
|
||||
try {
|
||||
await fetch("/wfm/gallery/image/meta", {
|
||||
method: "POST",
|
||||
headers: { "Content-Type": "application/json" },
|
||||
body: JSON.stringify({ path, workflow }),
|
||||
});
|
||||
} catch { /* non-critical */ }
|
||||
}
|
||||
}
|
||||
|
||||
// ============================================
|
||||
// i18nの適用(app.jsのapplyI18nToHtml()と同じ「個別要素にt()を適用」方式)
|
||||
// ============================================
|
||||
@@ -482,29 +103,17 @@ function _applyVideoI18n() {
|
||||
const el = document.getElementById(id);
|
||||
if (el) el.textContent = t(key);
|
||||
};
|
||||
setText("wfm-video-title-label", "videoTitle");
|
||||
setText("wfm-video-first-frame-label", "videoFirstFrame");
|
||||
setText("wfm-video-last-frame-label", "videoLastFrame");
|
||||
setText("wfm-video-first-frame-drop-label", "videoDropOrClick");
|
||||
setText("wfm-video-last-frame-drop-label", "videoDropOrClick");
|
||||
setText("wfm-video-first-frame-clear", "clear");
|
||||
setText("wfm-video-last-frame-clear", "clear");
|
||||
setText("wfm-video-prompt-label", "videoPrompt");
|
||||
setText("wfm-video-aspect-ratio-label", "videoAspectRatio");
|
||||
setText("wfm-video-megapixels-label", "videoMegapixels");
|
||||
setText("wfm-video-multiple-label", "videoMultiple");
|
||||
setText("wfm-video-duration-label", "videoDuration");
|
||||
setText("wfm-video-noise-seed-label", "videoNoiseSeed");
|
||||
setText("wfm-video-randomize-label", "videoRandomizeSeed");
|
||||
setText("wfm-video-generate-btn", "videoGenerate");
|
||||
setText("wfm-video-edit-placeholder-label", "videoEditPlaceholder");
|
||||
setText("wfm-video-source-label", "videoSourceLabel");
|
||||
setText("wfm-video-source-hint", "videoSourceHint");
|
||||
setText("wfm-video-source-drop-label", "videoSourceDropLabel");
|
||||
setText("wfm-video-source-clear", "clear");
|
||||
setText("wfm-video-preview-placeholder", "videoNoVideo");
|
||||
setText("wfm-video-source-preview-placeholder", "videoSourcePreviewPlaceholder");
|
||||
setText("wfm-video-preview-placeholder", "videoResultPreviewPlaceholder");
|
||||
setText("wfm-video-prop-tab-frame", "videoPropFrame");
|
||||
setText("wfm-video-prop-tab-gif", "videoPropGif");
|
||||
setText("wfm-video-subtab-btn-project", "videoPropProject");
|
||||
setText("wfm-video-project-hint", "videoProjectHint");
|
||||
setText("wfm-video-frame-hint", "videoFrameHint");
|
||||
setText("wfm-video-frame-capture-btn", "videoCaptureFrame");
|
||||
setText("wfm-video-frame-save-btn", "videoSaveToOutput");
|
||||
@@ -517,19 +126,19 @@ function _applyVideoI18n() {
|
||||
|
||||
// ============================================
|
||||
// Video Source panel — loads any local video into the preview frame, independent of
|
||||
// generation, so Frame/GIF tools work without running MiniMax H3 first.
|
||||
// generation, so Frame/GIF tools work without running the loaded video workflow first.
|
||||
// ============================================
|
||||
|
||||
function _wireVideoSourcePanel() {
|
||||
_wireDropZone("wfm-video-source-drop", "wfm-video-source-file", (file) => {
|
||||
if (!file.type.startsWith("video/")) return;
|
||||
const statusEl = document.getElementById("wfm-video-source-status");
|
||||
_setPreviewMedia(URL.createObjectURL(file), { kind: "local", file });
|
||||
setSourcePreview(URL.createObjectURL(file), { kind: "local", file });
|
||||
if (statusEl) { statusEl.textContent = file.name; statusEl.style.color = ""; }
|
||||
});
|
||||
|
||||
document.getElementById("wfm-video-source-clear")?.addEventListener("click", () => {
|
||||
_setPreviewMedia(null, null);
|
||||
setSourcePreview(null, null);
|
||||
const statusEl = document.getElementById("wfm-video-source-status");
|
||||
if (statusEl) statusEl.textContent = "";
|
||||
const fileInput = document.getElementById("wfm-video-source-file");
|
||||
@@ -579,7 +188,7 @@ function _initFrameTab() {
|
||||
const statusEl = document.getElementById("wfm-video-frame-status");
|
||||
|
||||
captureBtn?.addEventListener("click", () => {
|
||||
const video = document.getElementById("wfm-video-preview-video");
|
||||
const video = getActivePreviewVideoElement();
|
||||
if (!video || video.style.display === "none" || !video.videoWidth) {
|
||||
showToast(t("videoNoSourceLoaded"), "error");
|
||||
return;
|
||||
@@ -641,7 +250,7 @@ function _initGifTab() {
|
||||
const statusEl = document.getElementById("wfm-video-gif-status");
|
||||
|
||||
convertBtn?.addEventListener("click", async () => {
|
||||
if (!state.previewSource) {
|
||||
if (!getActivePreviewSource()) {
|
||||
showToast(t("videoNoSourceLoaded"), "error");
|
||||
return;
|
||||
}
|
||||
@@ -651,12 +260,12 @@ function _initGifTab() {
|
||||
if (progressText) progressText.textContent = "Uploading...";
|
||||
|
||||
try {
|
||||
let ref = state.previewSource;
|
||||
let ref = getActivePreviewSource();
|
||||
if (ref.kind === "local") {
|
||||
const result = await comfyUI.uploadImage(ref.file, ref.file.name);
|
||||
ref = { kind: "input", filename: result.name, subfolder: result.subfolder || "", type: "input" };
|
||||
// Cache the uploaded reference so a repeat conversion doesn't re-upload.
|
||||
state.previewSource = ref;
|
||||
updateActivePreviewSourceRef(ref);
|
||||
}
|
||||
|
||||
const start = Number(document.getElementById("wfm-video-gif-start")?.value) || 0;
|
||||
@@ -707,19 +316,19 @@ function _initGifTab() {
|
||||
|
||||
export function initVideoTab() {
|
||||
_applyVideoI18n();
|
||||
_populateAspectRatioOptions();
|
||||
|
||||
_wireDropZone("wfm-video-first-frame-drop", "wfm-video-first-frame-file", (file) => _handleFrameUpload("first", file));
|
||||
_wireDropZone("wfm-video-last-frame-drop", "wfm-video-last-frame-file", (file) => _handleFrameUpload("last", file));
|
||||
|
||||
document.getElementById("wfm-video-first-frame-clear")?.addEventListener("click", () => _clearFrame("first"));
|
||||
document.getElementById("wfm-video-last-frame-clear")?.addEventListener("click", () => _clearFrame("last"));
|
||||
document.getElementById("wfm-video-generate-btn")?.addEventListener("click", runGeneration);
|
||||
_initCenterSubtabToggle();
|
||||
_initSidebarSubtabToggle();
|
||||
initVideoPlanTab();
|
||||
initVideoAssetTab();
|
||||
initVideoProjectTab();
|
||||
|
||||
_wireVideoSourcePanel();
|
||||
_initPropTabs();
|
||||
_initFrameTab();
|
||||
_initGifTab();
|
||||
|
||||
loadDefaultWorkflow();
|
||||
// 保存済みの音量を適用し、以降ユーザーがネイティブコントロールで変更した音量も
|
||||
// 自動保存する(要素自体は永続的なので初期化時に一度呼べば十分)。両方のプレビュー
|
||||
// ペイン(Asset/Source用・生成結果用)の<video>要素に適用する。
|
||||
getAllPreviewVideoElements().forEach((video) => applyStoredVideoVolume(video));
|
||||
}
|
||||
|
||||
@@ -0,0 +1,276 @@
|
||||
/**
|
||||
* Video workflow helpers — model-family detection and node manipulation for
|
||||
* MiniMax H3 / LTX-2.5 (Text・Image・First&Last-Frame to Video) / Wan2.2 (Text
|
||||
* to Video) workflows. Pure functions operating on UI-format workflow JSON,
|
||||
* with no DOM/state dependency, so both the Plan tab's per-block batch loop
|
||||
* and (previously) the single-shot form can share the exact same logic.
|
||||
*/
|
||||
|
||||
// ============================================
|
||||
// 動画モデルノードの動的特定(ノードIDをハードコードしない)
|
||||
// サブグラフの内部ノード型(Wan2.2のみサブグラフ名)で対象ワークフローの種類を判定し、
|
||||
// 以降はサブグラフが公開する入力のlabel(無ければname)で意味的にスロットを特定する。
|
||||
// これによりLTX-2.5の3バリアント間で公開入力のname(text/value/value_1...)が揺れて
|
||||
// いても、label(prompt/duration/width...)は共通しているため同じロジックで処理できる。
|
||||
// ============================================
|
||||
|
||||
// ノードのinputs[]のうちwidgetキーを持つものだけを抽出した並び順で、指定した入力定義の
|
||||
// インデックスを引く。widgets_values配列はこの並び順と1:1対応する(link接続されていても
|
||||
// widgetキーを持つ入力はwidgets_valuesにスロットを持つ「legacy full」形式のため)。
|
||||
function _widgetIndexOf(node, inputDef) {
|
||||
if (!inputDef) return -1;
|
||||
const widgetInputs = (node?.inputs || []).filter((inp) => inp.widget);
|
||||
return widgetInputs.indexOf(inputDef);
|
||||
}
|
||||
|
||||
// 上と同じ並び順ルールで、名前から直接インデックスを引く版(ResolutionSelectorや
|
||||
// LoadImageなど、モデルファミリー間で入力名が揺れないノードに使う)。
|
||||
export function widgetIndex(node, name) {
|
||||
const widgetInputs = (node?.inputs || []).filter((inp) => inp.widget);
|
||||
return widgetInputs.findIndex((inp) => inp.name === name);
|
||||
}
|
||||
|
||||
// サブグラフが公開する入力は、labelがあればlabel、無ければnameが意味的な役割を表す
|
||||
// (例: MiniMax H3の"width"はlabel無しでname自体が"width"、LTX-2.5の"value_2"はlabelが
|
||||
// "width")。
|
||||
function _findInputByLabel(node, label) {
|
||||
return (node?.inputs || []).find((inp) => (inp.label || inp.name) === label) || null;
|
||||
}
|
||||
|
||||
// noise_seedはLTX-2.5のText to Videoバリアントだけlabel="seed"を持つ(他は無label)ため、
|
||||
// 意味的ラベルではなくname自体(全バリアントで"noise_seed"に統一)で検索する。
|
||||
function _findInputByName(node, name) {
|
||||
return (node?.inputs || []).find((inp) => inp.name === name) || null;
|
||||
}
|
||||
|
||||
function _detectVideoSubgraph(workflow) {
|
||||
if (!Array.isArray(workflow?.nodes) || !Array.isArray(workflow?.links)) return null;
|
||||
const subgraphs = workflow.definitions?.subgraphs || [];
|
||||
|
||||
const minimax = subgraphs.find((sg) => (sg.nodes || []).some((n) => n.type === "MiniMaxH3ImageToVideo"));
|
||||
if (minimax) return { family: "minimax", sgDef: minimax };
|
||||
|
||||
// LTX-2.5のText/Image/First&Last-Frame to Videoはいずれも内部にLTXV*系ノードを持つ
|
||||
// サブグラフとして配布される。バリアントごとにサブグラフの公開入力nameが異なるため、
|
||||
// 内部ノード型のプレフィックスで検出する。
|
||||
const ltx = subgraphs.find((sg) => (sg.nodes || []).some((n) => typeof n.type === "string" && n.type.startsWith("LTXV")));
|
||||
if (ltx) return { family: "ltx25", sgDef: ltx };
|
||||
|
||||
// Wan2.2はUNETLoader/KSamplerAdvanced/EmptyHunyuanLatentVideoなど汎用ノードのみで
|
||||
// 構成されており、MiniMax H3/LTX-2.5のような固有ノード型による検出ができない。
|
||||
// そのためサブグラフ自体の名前(公式テンプレート由来の "...(Wan2.2)" 表記)で検出する。
|
||||
const wan22 = subgraphs.find((sg) => /wan\s*2\.2/i.test(sg.name || ""));
|
||||
if (wan22) return { family: "wan22", sgDef: wan22 };
|
||||
|
||||
return null;
|
||||
}
|
||||
|
||||
export function locateVideoModelNodes(workflow) {
|
||||
const detected = _detectVideoSubgraph(workflow);
|
||||
if (!detected) return null;
|
||||
const { family, sgDef } = detected;
|
||||
|
||||
const instanceNode = workflow.nodes.find((n) => n.type === sgDef.id);
|
||||
if (!instanceNode || !Array.isArray(instanceNode.widgets_values)) return null;
|
||||
|
||||
// Wan2.2の公開入力はプロンプトが label 無しの name="text" のまま(MiniMax H3の"prompt"や
|
||||
// LTX-2.5の label="prompt" と異なる)ため、"prompt" が見つからない場合は "text" にフォール
|
||||
// バックする。
|
||||
const promptInput = _findInputByLabel(instanceNode, "prompt") || _findInputByLabel(instanceNode, "text");
|
||||
const durationInput = _findInputByLabel(instanceNode, "duration");
|
||||
const widthInput = _findInputByLabel(instanceNode, "width");
|
||||
if (!promptInput || !durationInput || !widthInput) return null;
|
||||
|
||||
const promptIdx = _widgetIndexOf(instanceNode, promptInput);
|
||||
const durationIdx = _widgetIndexOf(instanceNode, durationInput);
|
||||
if (promptIdx === -1 || durationIdx === -1) return null;
|
||||
|
||||
const widthSlot = instanceNode.inputs.indexOf(widthInput);
|
||||
|
||||
// ワークフローにより有無・意味が異なる任意項目。見つからなければ全て-1を返し、
|
||||
// 呼び出し側(UI)はその項目を無効化・非ハイライトにする。
|
||||
const heightInput = _findInputByLabel(instanceNode, "height");
|
||||
const noiseSeedInput = _findInputByName(instanceNode, "noise_seed");
|
||||
// MiniMax H3は"turbo_mode"、Wan2.2は"enable_turbo_mode" — 同じ意味のトグルをUI上は
|
||||
// 1つのフィールドとして兼用するため、どちらか見つかった方を使う。
|
||||
const turboModeInput = _findInputByLabel(instanceNode, "turbo_mode") || _findInputByLabel(instanceNode, "enable_turbo_mode");
|
||||
const turboStrengthInput = _findInputByLabel(instanceNode, "turbo_model_strength");
|
||||
const turboStepsInput = _findInputByLabel(instanceNode, "turbo_steps");
|
||||
const promptEnhanceInput = _findInputByLabel(instanceNode, "prompt_enhance");
|
||||
const noiseSeedIdx = _widgetIndexOf(instanceNode, noiseSeedInput);
|
||||
const turboModeIdx = _widgetIndexOf(instanceNode, turboModeInput);
|
||||
const turboStrengthIdx = _widgetIndexOf(instanceNode, turboStrengthInput);
|
||||
const turboStepsIdx = _widgetIndexOf(instanceNode, turboStepsInput);
|
||||
const promptEnhanceIdx = _widgetIndexOf(instanceNode, promptEnhanceInput);
|
||||
|
||||
const findLinkedNode = (targetSlot) => {
|
||||
if (targetSlot === -1) return null;
|
||||
const link = workflow.links.find((l) => l[3] === instanceNode.id && l[4] === targetSlot);
|
||||
if (!link) return null;
|
||||
return workflow.nodes.find((n) => n.id === link[1]) || null;
|
||||
};
|
||||
|
||||
// 一部のLTX-2.5バリアント(First & Last Frame to Video等)はResolutionSelectorを介さず、
|
||||
// width/heightをサブグラフの直接ウィジェット値として持つ。その場合はresolutionNode: null
|
||||
// を返し、以降の処理ではaspect_ratio等の操作をスキップする(テンプレートのwidth/height値が
|
||||
// そのまま使われる)。
|
||||
const rawResolutionNode = findLinkedNode(widthSlot);
|
||||
const resolutionNode = (rawResolutionNode && rawResolutionNode.type === "ResolutionSelector") ? rawResolutionNode : null;
|
||||
|
||||
// first_frame/last_frameはoptional入力のため、対応するLoadImageノードが接続されて
|
||||
// いないワークフロー(テキストのみで動作するT2V構成など)もサポート対象とする。
|
||||
// 未接続の場合はnullのまま返し、必要ならapplyBlockToWorkflow側で動的にノードを注入する。
|
||||
const firstFrameInput = _findInputByLabel(instanceNode, "first_frame");
|
||||
const lastFrameInput = _findInputByLabel(instanceNode, "last_frame");
|
||||
const firstFrameSlot = firstFrameInput ? instanceNode.inputs.indexOf(firstFrameInput) : -1;
|
||||
const lastFrameSlot = lastFrameInput ? instanceNode.inputs.indexOf(lastFrameInput) : -1;
|
||||
|
||||
const rawLoadImageNode = findLinkedNode(firstFrameSlot);
|
||||
const loadImageNode = (rawLoadImageNode && rawLoadImageNode.type === "LoadImage") ? rawLoadImageNode : null;
|
||||
const rawLastLoadImageNode = findLinkedNode(lastFrameSlot);
|
||||
const lastLoadImageNode = (rawLastLoadImageNode && rawLastLoadImageNode.type === "LoadImage") ? rawLastLoadImageNode : null;
|
||||
|
||||
// width/heightはResolutionSelectorがあればその出力に接続されており(widthSlotの
|
||||
// link経由)、その場合は直接ウィジェット値を書き換えても実行時にリンク元の出力で
|
||||
// 上書きされ意味がない。resolutionNodeがnullのワークフロー(LTX-2.5 First&Last-Frame,
|
||||
// Wan2.2全種)でのみ、instanceNode自身のwidth/heightウィジェットを直接編集できる。
|
||||
const widthIdx = resolutionNode ? -1 : _widgetIndexOf(instanceNode, widthInput);
|
||||
const heightIdx = resolutionNode ? -1 : _widgetIndexOf(instanceNode, heightInput);
|
||||
|
||||
return {
|
||||
family, sgDef, instanceNode, loadImageNode, lastLoadImageNode, resolutionNode,
|
||||
firstFrameSlot, lastFrameSlot, promptIdx, durationIdx,
|
||||
widthIdx, heightIdx, noiseSeedIdx, turboModeIdx, turboStrengthIdx, turboStepsIdx, promptEnhanceIdx,
|
||||
};
|
||||
}
|
||||
|
||||
// Reads the current values a freshly-loaded template workflow carries, so a UI
|
||||
// (the Plan tab's first block, previously the single-shot form) can seed its
|
||||
// fields from whatever the workflow file already had.
|
||||
export function readTemplateDefaults(nodes) {
|
||||
const {
|
||||
instanceNode, resolutionNode, loadImageNode, lastLoadImageNode, promptIdx, durationIdx,
|
||||
widthIdx, heightIdx, noiseSeedIdx, turboModeIdx, turboStrengthIdx, turboStepsIdx, promptEnhanceIdx,
|
||||
} = nodes;
|
||||
const arIdx = widgetIndex(resolutionNode, "aspect_ratio");
|
||||
const mpIdx = widgetIndex(resolutionNode, "megapixels");
|
||||
const multIdx = widgetIndex(resolutionNode, "multiple");
|
||||
const fnIdx = widgetIndex(loadImageNode, "image");
|
||||
const lastFnIdx = widgetIndex(lastLoadImageNode, "image");
|
||||
return {
|
||||
prompt: instanceNode.widgets_values[promptIdx] ?? "",
|
||||
duration: instanceNode.widgets_values[durationIdx] ?? 2,
|
||||
hasResolution: !!resolutionNode,
|
||||
aspectRatio: (resolutionNode && arIdx !== -1) ? resolutionNode.widgets_values[arIdx] : null,
|
||||
megapixels: (resolutionNode && mpIdx !== -1) ? resolutionNode.widgets_values[mpIdx] : null,
|
||||
multiple: (resolutionNode && multIdx !== -1) ? resolutionNode.widgets_values[multIdx] : null,
|
||||
firstImageFilename: (loadImageNode && fnIdx !== -1) ? loadImageNode.widgets_values[fnIdx] : null,
|
||||
lastImageFilename: (lastLoadImageNode && lastFnIdx !== -1) ? lastLoadImageNode.widgets_values[lastFnIdx] : null,
|
||||
// width/heightは resolutionNode がある場合は widthIdx/heightIdx が -1 になる
|
||||
// (locateVideoModelNodes参照) ため、常にnullが返り直接入力欄は無効化される。
|
||||
hasDirectResolution: widthIdx !== -1 && heightIdx !== -1,
|
||||
width: widthIdx !== -1 ? instanceNode.widgets_values[widthIdx] : null,
|
||||
height: heightIdx !== -1 ? instanceNode.widgets_values[heightIdx] : null,
|
||||
hasNoiseSeed: noiseSeedIdx !== -1,
|
||||
noiseSeed: noiseSeedIdx !== -1 ? instanceNode.widgets_values[noiseSeedIdx] : null,
|
||||
hasTurboMode: turboModeIdx !== -1,
|
||||
turboMode: turboModeIdx !== -1 ? instanceNode.widgets_values[turboModeIdx] : null,
|
||||
hasTurboStrength: turboStrengthIdx !== -1,
|
||||
turboStrength: turboStrengthIdx !== -1 ? instanceNode.widgets_values[turboStrengthIdx] : null,
|
||||
hasTurboSteps: turboStepsIdx !== -1,
|
||||
turboSteps: turboStepsIdx !== -1 ? instanceNode.widgets_values[turboStepsIdx] : null,
|
||||
hasPromptEnhance: promptEnhanceIdx !== -1,
|
||||
promptEnhance: promptEnhanceIdx !== -1 ? instanceNode.widgets_values[promptEnhanceIdx] : null,
|
||||
};
|
||||
}
|
||||
|
||||
// first_frame/last_frameが未接続のワークフローに対して、画像が指定された時だけ
|
||||
// LoadImageノードを新規注入する共通ヘルパー。ノードID/リンクIDはclone内の実際の
|
||||
// 最大値+1で採番するため、重複ID/リンクID不整合は起きない
|
||||
// (CLAUDE.md記載の既知の落とし穴への対策)。
|
||||
export function injectFrameNode(clone, instanceNode, targetSlot, filename) {
|
||||
const maxNodeId = Math.max(clone.last_node_id || 0, ...clone.nodes.map((n) => n.id));
|
||||
const maxLinkId = Math.max(clone.last_link_id || 0, ...clone.links.map((l) => l[0]));
|
||||
const newNodeId = maxNodeId + 1;
|
||||
const newLinkId = maxLinkId + 1;
|
||||
|
||||
clone.nodes.push({
|
||||
id: newNodeId,
|
||||
type: "LoadImage",
|
||||
pos: [(instanceNode.pos?.[0] || 0) - 260, (instanceNode.pos?.[1] || 0) + 40],
|
||||
size: [280, 314],
|
||||
flags: {},
|
||||
order: clone.nodes.length,
|
||||
mode: 0,
|
||||
inputs: [
|
||||
{ localized_name: "image", name: "image", type: "COMBO", widget: { name: "image" }, link: null },
|
||||
{ localized_name: "choose file to upload", name: "upload", type: "IMAGEUPLOAD", widget: { name: "upload" }, link: null },
|
||||
],
|
||||
outputs: [
|
||||
{ localized_name: "IMAGE", name: "IMAGE", type: "IMAGE", links: [newLinkId] },
|
||||
{ localized_name: "MASK", name: "MASK", type: "MASK", links: null },
|
||||
],
|
||||
properties: { "Node name for S&R": "LoadImage" },
|
||||
widgets_values: [filename, "image"],
|
||||
});
|
||||
|
||||
clone.links.push([newLinkId, newNodeId, 0, instanceNode.id, targetSlot, "IMAGE"]);
|
||||
const targetInput = instanceNode.inputs[targetSlot];
|
||||
if (targetInput) targetInput.link = newLinkId;
|
||||
|
||||
clone.last_node_id = newNodeId;
|
||||
clone.last_link_id = newLinkId;
|
||||
}
|
||||
|
||||
// Writes one block's (or the old single-shot form's) values onto a workflow
|
||||
// clone already located via locateVideoModelNodes(clone) — `nodes`' node
|
||||
// references point into `clone` itself. First/last frame images are only
|
||||
// touched when a filename is actually given: an existing LoadImage node gets
|
||||
// its widget overwritten, a missing one gets injected on demand, and leaving
|
||||
// both unset keeps the slot disconnected (bypassed) exactly like the
|
||||
// template's own clean state.
|
||||
export function applyBlockToWorkflow(clone, nodes, params) {
|
||||
const {
|
||||
instanceNode, resolutionNode, loadImageNode, lastLoadImageNode, promptIdx, durationIdx, firstFrameSlot, lastFrameSlot,
|
||||
widthIdx, heightIdx, turboModeIdx, turboStrengthIdx, turboStepsIdx, promptEnhanceIdx,
|
||||
} = nodes;
|
||||
|
||||
instanceNode.widgets_values[promptIdx] = params.prompt || "";
|
||||
instanceNode.widgets_values[durationIdx] = params.duration;
|
||||
|
||||
const arIdx = widgetIndex(resolutionNode, "aspect_ratio");
|
||||
const mpIdx = widgetIndex(resolutionNode, "megapixels");
|
||||
const multIdx = widgetIndex(resolutionNode, "multiple");
|
||||
if (arIdx !== -1) resolutionNode.widgets_values[arIdx] = params.aspectRatio;
|
||||
if (mpIdx !== -1) resolutionNode.widgets_values[mpIdx] = params.megapixels;
|
||||
if (multIdx !== -1) resolutionNode.widgets_values[multIdx] = params.multiple;
|
||||
|
||||
// widthIdx/heightIdxはresolutionNodeがあるワークフローでは-1固定(locateVideoModelNodes
|
||||
// 参照)なので、そちらはaspect_ratio/megapixels/multiple経由の計算値のまま変更しない。
|
||||
if (widthIdx !== -1 && params.width != null) instanceNode.widgets_values[widthIdx] = params.width;
|
||||
if (heightIdx !== -1 && params.height != null) instanceNode.widgets_values[heightIdx] = params.height;
|
||||
// noise_seedはここでは書かない — comfyUI.generate()がAPI変換後のワークフロー全体から
|
||||
// "noise_seed"/"seed"キーを持つ全ノードを一括で上書きする(applySeedToWorkflow)ため、
|
||||
// ここで書いてもその後必ず上書きされる。Plan全体のシード管理は引き続きそちら任せでよい。
|
||||
if (turboModeIdx !== -1 && params.turboMode != null) instanceNode.widgets_values[turboModeIdx] = params.turboMode;
|
||||
if (turboStrengthIdx !== -1 && params.turboStrength != null) instanceNode.widgets_values[turboStrengthIdx] = params.turboStrength;
|
||||
if (turboStepsIdx !== -1 && params.turboSteps != null) instanceNode.widgets_values[turboStepsIdx] = params.turboSteps;
|
||||
if (promptEnhanceIdx !== -1 && params.promptEnhance != null) instanceNode.widgets_values[promptEnhanceIdx] = params.promptEnhance;
|
||||
|
||||
if (params.firstImageFilename) {
|
||||
if (loadImageNode) {
|
||||
const fnIdx = widgetIndex(loadImageNode, "image");
|
||||
if (fnIdx !== -1) loadImageNode.widgets_values[fnIdx] = params.firstImageFilename;
|
||||
} else if (firstFrameSlot !== -1) {
|
||||
injectFrameNode(clone, instanceNode, firstFrameSlot, params.firstImageFilename);
|
||||
}
|
||||
}
|
||||
if (params.lastImageFilename) {
|
||||
if (lastLoadImageNode) {
|
||||
const fnIdx = widgetIndex(lastLoadImageNode, "image");
|
||||
if (fnIdx !== -1) lastLoadImageNode.widgets_values[fnIdx] = params.lastImageFilename;
|
||||
} else if (lastFrameSlot !== -1) {
|
||||
injectFrameNode(clone, instanceNode, lastFrameSlot, params.lastImageFilename);
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -1378,7 +1378,7 @@ export function initWorkflowTab() {
|
||||
}
|
||||
});
|
||||
|
||||
// Toolbar: Load in Video button (MiniMax H3専用。非対応ワークフローはloadWorkflowIntoVideoEditor内でエラートースト表示済み)
|
||||
// Toolbar: Load in Video button (MiniMax H3 / LTX-2.5 / Wan2.2対応。非対応ワークフローはloadWorkflowIntoVideoEditor内でエラートースト表示済み)
|
||||
document.getElementById("wfm-list-load-video-btn")?.addEventListener("click", async () => {
|
||||
if (!state.selectedWf) return;
|
||||
try {
|
||||
|
||||
@@ -951,12 +951,8 @@
|
||||
<div class="wfm-prompt-split-header">AI Assistant</div>
|
||||
<div class="wfm-ollama-assistant">
|
||||
<div class="wfm-ollama-controls">
|
||||
<select id="wfm-ollama-model" class="wfm-select" style="flex:1;min-width:120px;">
|
||||
<option value="">Loading models...</option>
|
||||
</select>
|
||||
<button id="wfm-ollama-refresh-btn" class="wfm-btn wfm-btn-sm">Refresh</button>
|
||||
<button id="wfm-ollama-test-btn" class="wfm-btn wfm-btn-sm">Test</button>
|
||||
<span id="wfm-ollama-status" class="wfm-ollama-status">Disconnected</span>
|
||||
<button id="wfm-ollama-settings-btn" class="wfm-btn wfm-btn-sm" style="margin-left:auto;" title="Settings">⚙</button>
|
||||
</div>
|
||||
<div class="wfm-ollama-controls" style="margin-top:6px;">
|
||||
<button id="wfm-ollama-attach-btn" class="wfm-btn wfm-btn-sm">Attach Image</button>
|
||||
@@ -1417,7 +1413,8 @@
|
||||
<li id="wfm-help-gen-5">Model tab: Checkpoint, VAE, Diffusion Model (UNETLoader / UnetLoaderGGUF / LoaderGGUF), Text Encoder (CLIPLoader / DualCLIPLoader / ClipLoaderGGUF / DualClipLoaderGGUF — type and device selectors; DualCLIP shows two clip selectors) are always shown; ControlNet and Hypernetwork (with Strength field) are collapsed by default since they're used less often — click their header to expand; LoRA (Single/Stack tabs) has its own column to the right; all selectors have a filter; LoRA Stack — Apply writes all active LoRAs to the target node and simultaneously inserts LoRA syntax and CivitAI trigger words into the Positive prompt; re-applying updates the prompt by removing inactive LoRAs and re-adding active ones</li>
|
||||
<li id="wfm-help-gen-28">Model tab — Highlight color: the label of each model type (Checkpoint, VAE, Diffusion Model, Text Encoder, ControlNet, Hypernetwork) and the LoRA column header turn a distinct color (default bright green) when the loaded workflow actually contains that type of node; this stays visible even while ControlNet/Hypernetwork are collapsed, so you can tell at a glance whether they're in use without expanding them; the color is customizable in the Settings tab</li>
|
||||
<li id="wfm-help-gen-6">Settings tab: KSampler and Latent Image side by side, each at 50% width</li>
|
||||
<li id="wfm-help-gen-7">Raw JSON always visible in the right column of each tab — edit directly and Apply to reload the workflow; if the loaded workflow has Bypass or Mute nodes, a note listing them appears above the search bar (Bypass nodes are excluded with their wires reconnected around them; Mute nodes are excluded with no reconnection, matching ComfyUI itself)</li>
|
||||
<li id="wfm-help-gen-31">LTX-2.5 and Wan2.2 video workflows also work when loaded as regular workflows in this tab (not just the dedicated Video tab): Positive/Negative Prompt detection follows LTX-2.5's LTXVDualCFGGuider / LTXVConditioning nodes to find the actual prompt text, and the Settings tab's Latent Image section recognizes Wan2.2's EmptyHunyuanLatentVideo and LTX-2.5's EmptyLTXVLatentVideo nodes (with an added Length (frames) field) instead of showing "No EmptyLatentImage node found"; generating from these workflows also gets the same extended timeout as MiniMax H3 video generations</li>
|
||||
<li id="wfm-help-gen-7">Raw JSON always visible in the right column of each tab — edit directly and Apply to reload the workflow; if the loaded workflow has Bypass or Mute nodes, a note listing them appears above the search bar (Bypass nodes are excluded with their wires reconnected around them; Mute nodes are excluded with no reconnection, matching ComfyUI itself); the search bar highlights matches and scrolls to them without moving the cursor into the editor, so typing right after a search can't accidentally overwrite the JSON — click into the editor first to actually edit</li>
|
||||
<li id="wfm-help-gen-30">The <b>Save</b> button (right end of the subtab bar) is hidden while the <b>Batch</b> or <b>Lab</b> subtab is active, since those work on workflow copies / their own Plan files rather than the currently loaded workflow; it reappears on Input/Model/Settings/Feeder</li>
|
||||
</ul>
|
||||
</div>
|
||||
@@ -1571,7 +1568,7 @@
|
||||
<div class="wfm-help-card">
|
||||
<h3 id="wfm-help-prompt-card-ai-title">AI Assistant & Translation</h3>
|
||||
<ul>
|
||||
<li id="wfm-help-prompt-1">AI assistant (Ollama): model selection, chat for prompt consultation, image attachment (vision models)</li>
|
||||
<li id="wfm-help-prompt-1">AI assistant (Ollama / LM Studio / Lemonade / Unsloth): chat for prompt consultation, image attachment (vision models); click the ⚙ Settings button to choose backend, connection URL, model, Thinking mode, Max tokens, and unload the loaded model — settings are independent from the AI TOOL and Tagger tabs</li>
|
||||
<li id="wfm-help-prompt-2">Apply AI responses to GenerateUI prompts</li>
|
||||
<li id="wfm-help-prompt-3">Translation: JA↔EN, ZH↔EN</li>
|
||||
</ul>
|
||||
@@ -1666,7 +1663,7 @@
|
||||
<h3 id="wfm-help-settings-card-connections-title">Connections</h3>
|
||||
<ul>
|
||||
<li id="wfm-help-settings-4">ComfyUI connection URL and test</li>
|
||||
<li id="wfm-help-settings-5">Ollama URL, default model, and connection test</li>
|
||||
<li id="wfm-help-settings-5">AI Assistant settings have moved out of this tab — the Prompt tab, Tagger tab, and AI TOOL tab each have their own ⚙ Settings button (backend, URL, model, Thinking mode, Max tokens, unload model), saved independently</li>
|
||||
<li id="wfm-help-settings-7">Eagle integration URL and auto-save toggle</li>
|
||||
</ul>
|
||||
</div>
|
||||
@@ -1922,7 +1919,7 @@
|
||||
</div>
|
||||
<div class="wfm-help-card">
|
||||
<h3 id="wfm-help-ai-card-settings-title">Settings pane</h3>
|
||||
<p id="wfm-help-ai-6">Settings pane: choose backend (Ollama / LM Studio / Lemonade / Unsloth), set API URL, test connection, select model; Unsloth always requires an API key even for local access — set UNSLOTH_API_KEY in a .env file in the plugin folder (copy .env.example) and restart ComfyUI, the key is read server-side and never sent to the browser; Unsloth also requires "Auto model switching (OpenAI API)" to be turned ON in the Unsloth Desktop app itself (its own Settings screen) — without it, requests fail with HTTP 404 unless a model was already manually loaded in the Unsloth Studio UI; Unsloth reasoning models return their thinking in a separate reasoning_content field rather than inline <think> tags, so a low Max tokens can make the model spend its whole budget reasoning and return an empty reply — increase Max tokens (2048+) if replies come back blank; Generation section — Thinking mode toggle (off by default; Ollama receives a `think` flag, and regardless of backend any <think>...</think> block is stripped from the output when off, so reasoning models don't clutter Translation/Chat/TOOLS results) and Max tokens (Ollama: num_predict, LM Studio/Lemonade/Unsloth: max_tokens; 0 = unlimited); configure Free language names; Chat Image Generation section lets you enable a dedicated workflow for Chat-triggered text-to-image generation instead of the one currently loaded in GenerateUI; Chat I2I Generation section is the same but for image-to-image generation when an image is attached; settings are shared with the Library panel's A tab via localStorage</p>
|
||||
<p id="wfm-help-ai-6">Settings pane: choose backend (Ollama / LM Studio / Lemonade / Unsloth), set API URL, test connection, select model, and use the Unload Model button (next to Test connection) to free the loaded model from VRAM/memory — Ollama uses keep_alive:0, LM Studio uses /api/v1/models/unload, Lemonade uses /api/v1/unload; Unsloth has no unload API, so this shows an unsupported message for it; Unsloth always requires an API key even for local access — set UNSLOTH_API_KEY in a .env file in the plugin folder (copy .env.example) and restart ComfyUI, the key is read server-side and never sent to the browser; Unsloth also requires "Auto model switching (OpenAI API)" to be turned ON in the Unsloth Desktop app itself (its own Settings screen) — without it, requests fail with HTTP 404 unless a model was already manually loaded in the Unsloth Studio UI; Unsloth reasoning models return their thinking in a separate reasoning_content field rather than inline <think> tags, so a low Max tokens can make the model spend its whole budget reasoning and return an empty reply — increase Max tokens (2048+) if replies come back blank; Generation section — Thinking mode toggle (off by default; Ollama receives a `think` flag, and regardless of backend any <think>...</think> block is stripped from the output when off, so reasoning models don't clutter Translation/Chat/TOOLS results) and Max tokens (Ollama: num_predict, LM Studio/Lemonade/Unsloth: max_tokens; 0 = unlimited); configure Free language names; Chat Image Generation section lets you enable a dedicated workflow for Chat-triggered text-to-image generation instead of the one currently loaded in GenerateUI; Chat I2I Generation section is the same but for image-to-image generation when an image is attached; settings are shared with the Library panel's A tab via localStorage</p>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
@@ -1934,7 +1931,7 @@
|
||||
<div class="wfm-help-card">
|
||||
<h3 id="wfm-help-tagger-card-overview-title">Overview & Setup</h3>
|
||||
<ul>
|
||||
<li id="wfm-help-tagger-1">Automatic image tagging using WD Tagger (ONNX), SwinV2, DeepDanbooru (.h5), and Ollama VLM — 3 sub-tabs: Single / Batch / DB</li>
|
||||
<li id="wfm-help-tagger-1">Automatic image tagging using WD Tagger (ONNX), SwinV2, DeepDanbooru (.h5), and VLM (Ollama / LM Studio / Lemonade / Unsloth) — 3 sub-tabs: Single / Batch / DB</li>
|
||||
<li id="wfm-help-tagger-2">Model placement: put each model in its own subfolder under ComfyUI/models/tagger/<model-name>/; the folder must contain a .onnx file + selected_tags.csv (or .h5 + label file for DeepDanbooru)</li>
|
||||
<li id="wfm-help-tagger-9">Install dependencies into ComfyUI's embedded Python: python_embeded\python.exe -m pip install -r requirements.txt; for GPU ONNX inference install onnxruntime-gpu instead of onnxruntime; TensorFlow (for DeepDanbooru) is commented out by default due to size</li>
|
||||
</ul>
|
||||
@@ -1944,7 +1941,7 @@
|
||||
<ul>
|
||||
<li id="wfm-help-tagger-3">Single tab: drag & drop an image onto the preview area, or click Upload to pick a file; the Tagger button in the Gallery detail panel opens the selected image directly here</li>
|
||||
<li id="wfm-help-tagger-4">Threshold slider: minimum confidence score for general tags (default 0.35); Character Threshold: separate threshold for character: prefix tags (default 0.85)</li>
|
||||
<li id="wfm-help-tagger-5">Ollama VLM: enable the checkbox to run a vision model alongside WD Tagger; set API URL, select model (click ↻ to refresh), and customize the prompt; results from both models are merged</li>
|
||||
<li id="wfm-help-tagger-5">VLM Tagging: enable the checkbox to run a vision model alongside WD Tagger; click the ⚙ Settings button to choose backend (Ollama / LM Studio / Lemonade / Unsloth), URL, model, Thinking mode, Max tokens, and unload the model — independent from the Prompt tab's own AI settings; customize the prompt and Max Tags inline; results from both models are merged</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="wfm-help-card">
|
||||
@@ -1956,7 +1953,7 @@
|
||||
<div class="wfm-help-card">
|
||||
<h3 id="wfm-help-tagger-card-batch-title">Batch & DB Tabs</h3>
|
||||
<ul>
|
||||
<li id="wfm-help-tagger-7">Batch tab: enter a folder path, configure WD Tagger and Ollama settings; output options: Save to DB (default on), Write to File (EXIF/PNG metadata), Write .txt (creates <filename>.txt alongside each image); click Start Batch to process all images in the folder; progress bar and log are updated in real time; Stop cancels after the current image</li>
|
||||
<li id="wfm-help-tagger-7">Batch tab: enter a folder path, configure WD Tagger and enable VLM tagging (uses the same ⚙ Settings as the Single tab); output options: Save to DB (default on), Write to File (EXIF/PNG metadata), Write .txt (creates <filename>.txt alongside each image); click Start Batch to process all images in the folder; progress bar and log are updated in real time; Stop cancels after the current image</li>
|
||||
<li id="wfm-help-tagger-8">DB tab: searchable database of all tagged images; click a row to open the edit panel and modify WD Tags / VLM Tags; Save updates the record, Delete removes it; Export CSV downloads all records as a CSV file</li>
|
||||
</ul>
|
||||
</div>
|
||||
@@ -2093,16 +2090,19 @@
|
||||
|
||||
<div class="wfm-help-page" id="wfm-help-page-video">
|
||||
<h2 id="wfm-help-video-title">Video Tab</h2>
|
||||
<p id="wfm-help-video-desc">A dedicated video generation tab for the MiniMax H3 (Image to Video) workflow, independent of the GenerateUI tab.</p>
|
||||
<p id="wfm-help-video-desc">A dedicated video generation tab for MiniMax H3 (Image to Video), LTX-2.5 (Text / Image / First & Last Frame to Video), and Wan2.2 (Text to Video) workflows, independent of the GenerateUI tab. The center panel's Plan / Edit subtabs handle batch generation and (future) editing; the sidebar's Asset / Project subtabs handle browsing generated videos and saved plans.</p>
|
||||
<div class="wfm-help-card">
|
||||
<ul>
|
||||
<li id="wfm-help-video-1">Set first_frame (optional) / last_frame (optional) images, prompt, aspect_ratio / megapixels / multiple (resolution), duration (seconds), and noise_seed, then click Generate. Leaving first_frame empty runs the workflow text-only (bypassed), and workflows with no LoadImage node at all are also supported.</li>
|
||||
<li id="wfm-help-video-2">Model selection (UNet / CLIP / VAE / Audio VAE) is fixed to the loaded workflow's defaults and cannot be changed from this tab.</li>
|
||||
<li id="wfm-help-video-3">Use the "Load in Video" button in the Workflow tab's detail modal to load a workflow containing a MiniMax H3 Image-to-Video node. Unsupported workflows show an error instead.</li>
|
||||
<li id="wfm-help-video-4">Generated videos (mp4) can also be browsed and played back in the Gallery tab.</li>
|
||||
<li id="wfm-help-video-5">The Video Source panel next to the preview lets you drop or pick any local video (not just a generated one) to use the Frame/GIF tools below without running MiniMax H3 first; Clear resets it back to empty.</li>
|
||||
<li id="wfm-help-video-1">Plan subtab: the topbar's settings row holds Aspect Ratio / Megapixels / Multiple / Duration (seconds) / Noise Seed as this plan's base settings — Duration always reflects the currently selected block (each block keeps its own value), the rest are plan-wide. A second row below adds Width / Height / Turbo Mode / Strength / Steps / Prompt Enhance, each enabled only for workflows that actually support it (see helpVideo2). Split the timeline into blocks with the + Split / + Block / Delete buttons — each block has its own Prompt, Duration, and First/Last Image — First Image can be None, an explicit image, or "use previous block's last frame" (an explicit Last Image on the previous block always wins over extracting one from its generated video). Click Run to generate every block in order; Pause/Cancel work mid-run.</li>
|
||||
<li id="wfm-help-video-2">A plan with a single block behaves exactly like the old one-shot form. Model selection (UNet / CLIP / VAE / Audio VAE) is fixed to the loaded workflow's defaults. For workflows with no ResolutionSelector node (e.g. Wan2.2, LTX-2.5 First & Last Frame to Video), the Aspect Ratio / Megapixels / Multiple fields are disabled and the workflow's own Width / Height become directly editable instead. Turbo Mode / Strength / Steps only apply to MiniMax H3's turbo LoRA, and Prompt Enhance only to LTX-2.5 — both stay disabled for other model families. Noise Seed is disabled for the one workflow that doesn't expose it: Wan2.2 Text-to-Video.</li>
|
||||
<li id="wfm-help-video-3">Use the "Load in Video" button in the Workflow tab's detail modal to load a workflow containing a MiniMax H3 Image-to-Video node, an LTX-2.5 Text/Image/First&Last-Frame-to-Video node, or a Wan2.2 Text-to-Video node — this starts a fresh single-block plan seeded from the workflow's own current values. Unsupported workflows show an error instead.</li>
|
||||
<li id="wfm-help-video-4">Generated videos (mp4) automatically appear in the Asset subtab's Video Temp group, and can also be browsed and played back in the Gallery tab. Organizing keepers into Video Assets is entirely up to you, on your own schedule.</li>
|
||||
<li id="wfm-help-video-5">The center panel shows two previews: the left one shows either the video you select in the Asset subtab or whatever you drop/pick in the Video Source panel on its left (Clear resets it to empty), letting you use the Frame/GIF tools without running the loaded video workflow first; the right one always shows the most recently generated clip.</li>
|
||||
<li id="wfm-help-video-6">Frame tab (right panel): play/seek the preview video to the position you want, click Capture Frame to grab that frame client-side, then Save to Output to write it as a PNG into ComfyUI's output folder.</li>
|
||||
<li id="wfm-help-video-7">GIF tab (right panel): set Start/End (seconds), FPS, and an optional Max Width, then Convert to GIF — the server decodes the video and encodes an animated GIF into ComfyUI's output folder.</li>
|
||||
<li id="wfm-help-video-8">Chaining: setting a block's First Image to "use previous block's last frame" continues smoothly from the previous clip — if that previous block has its own explicit Last Image, that image is used directly; otherwise the actual last frame of its generated video is extracted automatically.</li>
|
||||
<li id="wfm-help-video-9">Project tab (sidebar, next to Asset): browse every saved plan file (thumbnail, block count, last updated), click one to load it into the Plan editor, or delete it with the × button; clicking the same tab again collapses the panel.</li>
|
||||
<li id="wfm-help-video-10">Highlight color: the Prompt / Duration / First Image / Last Image / Aspect Ratio / Megapixels / Multiple / Noise Seed / Width / Height / Turbo Mode / Strength / Steps / Prompt Enhance labels turn the same highlight color as the GenerateUI Model tab (customizable in the Settings tab) when the loaded workflow actually supports that field — e.g. for a Wan2.2 workflow (no ResolutionSelector node), the Aspect Ratio / Megapixels / Multiple labels stay unhighlighted while Width / Height light up instead.</li>
|
||||
</ul>
|
||||
</div>
|
||||
<button class="wfm-help-jump-btn wfm-btn wfm-btn-sm" data-jump-tab="video">Go to Video Tab</button>
|
||||
@@ -2687,99 +2687,42 @@
|
||||
</div>
|
||||
</section>
|
||||
|
||||
<!-- Video Tab (MiniMax H3専用・GenerateUIタブとは独立) -->
|
||||
<!-- Video Tab (Plan[バッチ動画生成]/Asset[素材管理]/Edit[将来機能]の3サブタブ。
|
||||
中央のプレビュー+右のFrame/GIFプロパティパネルはサブタブ切替と独立した常時表示) -->
|
||||
<section id="wfm-tab-video" class="wfm-tab-content">
|
||||
<div class="wfm-video-layout">
|
||||
<div class="wfm-video-form-panel">
|
||||
<div class="wfm-video-header">
|
||||
<h3 id="wfm-video-title-label">Video (MiniMax H3)</h3>
|
||||
<span id="wfm-video-wf-name" class="wfm-video-wf-name">No workflow loaded</span>
|
||||
<div class="wfm-video-subtab-nav">
|
||||
<button type="button" class="wfm-video-subtab-btn" data-video-subtab="asset" id="wfm-video-subtab-btn-asset">Asset</button>
|
||||
<button type="button" class="wfm-video-subtab-btn" data-video-subtab="project" id="wfm-video-subtab-btn-project">Project</button>
|
||||
</div>
|
||||
|
||||
<div class="wfm-video-frame-slots">
|
||||
<div class="wfm-video-frame-slot">
|
||||
<label id="wfm-video-first-frame-label">First Frame (optional)</label>
|
||||
<div class="wfm-i2i-preview-wrap" id="wfm-video-first-frame-wrap" style="display:none;">
|
||||
<img class="wfm-i2i-preview-img" id="wfm-video-first-frame-preview">
|
||||
</div>
|
||||
<div class="wfm-i2i-drop-zone" id="wfm-video-first-frame-drop">
|
||||
<label class="wfm-i2i-drop-label">
|
||||
<span id="wfm-video-first-frame-drop-label">Drop image or click to select</span>
|
||||
<input type="file" accept="image/*" id="wfm-video-first-frame-file" style="display:none;">
|
||||
</label>
|
||||
</div>
|
||||
<div style="display:flex;gap:6px;align-items:center;">
|
||||
<span class="wfm-i2i-status" id="wfm-video-first-frame-status" style="flex:1;"></span>
|
||||
<button type="button" class="wfm-btn wfm-btn-sm" id="wfm-video-first-frame-clear">Clear</button>
|
||||
</div>
|
||||
<!-- Asset: このPlanが生成した動画の素材管理(Galleryのグループ機能を再利用) -->
|
||||
<div id="wfm-video-subtab-asset" class="wfm-video-subtab-panel" data-video-subtab-panel="asset" style="display:none;">
|
||||
<div style="display:flex;gap:6px;align-items:center;">
|
||||
<select id="wfm-video-asset-group" class="wfm-input" style="flex:1;"></select>
|
||||
<button type="button" id="wfm-video-asset-refresh" class="wfm-btn wfm-btn-sm" title="Refresh">↻</button>
|
||||
</div>
|
||||
<div class="wfm-video-frame-slot">
|
||||
<label id="wfm-video-last-frame-label">Last Frame (optional)</label>
|
||||
<div class="wfm-i2i-preview-wrap" id="wfm-video-last-frame-wrap" style="display:none;">
|
||||
<img class="wfm-i2i-preview-img" id="wfm-video-last-frame-preview">
|
||||
</div>
|
||||
<div class="wfm-i2i-drop-zone" id="wfm-video-last-frame-drop">
|
||||
<label class="wfm-i2i-drop-label">
|
||||
<span id="wfm-video-last-frame-drop-label">Drop image or click to select</span>
|
||||
<input type="file" accept="image/*" id="wfm-video-last-frame-file" style="display:none;">
|
||||
</label>
|
||||
</div>
|
||||
<div style="display:flex;gap:6px;align-items:center;">
|
||||
<span class="wfm-i2i-status" id="wfm-video-last-frame-status" style="flex:1;"></span>
|
||||
<button type="button" class="wfm-btn wfm-btn-sm" id="wfm-video-last-frame-clear">Clear</button>
|
||||
</div>
|
||||
<span id="wfm-video-asset-status" class="wfm-i2i-status"></span>
|
||||
<div class="wfm-video-asset-grid" id="wfm-video-asset-grid"></div>
|
||||
<div class="wfm-video-asset-detail" id="wfm-video-asset-detail">
|
||||
<span class="wfm-placeholder">Select a video</span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<label for="wfm-video-prompt" id="wfm-video-prompt-label">Prompt</label>
|
||||
<textarea id="wfm-video-prompt" class="wfm-textarea" rows="6"></textarea>
|
||||
|
||||
<div class="wfm-video-resolution-row">
|
||||
<div>
|
||||
<label for="wfm-video-aspect-ratio" id="wfm-video-aspect-ratio-label">Aspect Ratio</label>
|
||||
<select id="wfm-video-aspect-ratio" class="wfm-input"></select>
|
||||
<!-- Project: 保存済みVideo Plan一覧(クリックでPlanエディタへ読み込み) -->
|
||||
<div id="wfm-video-subtab-project" class="wfm-video-subtab-panel" data-video-subtab-panel="project" style="display:none;">
|
||||
<div style="display:flex;gap:6px;align-items:center;">
|
||||
<p class="wfm-video-prop-hint" id="wfm-video-project-hint" style="flex:1;margin:0;">Saved plans</p>
|
||||
<button type="button" id="wfm-video-project-refresh" class="wfm-btn wfm-btn-sm" title="Refresh">↻</button>
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-megapixels" id="wfm-video-megapixels-label">Megapixels</label>
|
||||
<input type="number" id="wfm-video-megapixels" class="wfm-input" step="0.01" min="0.01" value="0.2">
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-multiple" id="wfm-video-multiple-label">Multiple</label>
|
||||
<input type="number" id="wfm-video-multiple" class="wfm-input" step="8" min="8" value="32">
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="wfm-video-resolution-row">
|
||||
<div>
|
||||
<label for="wfm-video-duration" id="wfm-video-duration-label">Duration (seconds)</label>
|
||||
<input type="number" id="wfm-video-duration" class="wfm-input" step="0.5" min="0.5" value="2">
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-noise-seed" id="wfm-video-noise-seed-label">Noise Seed</label>
|
||||
<input type="number" id="wfm-video-noise-seed" class="wfm-input" value="0">
|
||||
</div>
|
||||
<div class="wfm-video-seed-randomize-wrap">
|
||||
<label><input type="checkbox" id="wfm-video-seed-randomize" checked> <span id="wfm-video-randomize-label">Randomize</span></label>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div style="display:flex;align-items:center;gap:10px;margin-top:10px;">
|
||||
<button id="wfm-video-generate-btn" class="wfm-btn wfm-btn-primary" style="flex:1;">Generate</button>
|
||||
</div>
|
||||
<div class="wfm-gen-progress-container">
|
||||
<div class="wfm-gen-progress-track">
|
||||
<div id="wfm-video-progress-bar" class="wfm-gen-progress-bar"></div>
|
||||
</div>
|
||||
<span id="wfm-video-progress-text" class="wfm-gen-progress-text">Ready</span>
|
||||
<div class="wfm-video-project-list" id="wfm-video-project-list"></div>
|
||||
</div>
|
||||
</div>
|
||||
<!-- 中央ペイン: プレビュー(生成結果 or ドロップされた任意の動画) + 編集(将来機能用プレースホルダー) -->
|
||||
<!-- 中央ペイン: プレビュー(常時表示) + Plan/Editタブ(バッチ生成編集・将来の動画編集機能)。
|
||||
左のAssetサブタブ切替とは独立して常に表示される -->
|
||||
<div class="wfm-video-center-panel">
|
||||
<div class="wfm-video-preview-row">
|
||||
<div class="wfm-video-preview-frame" id="wfm-video-preview-frame">
|
||||
<span class="wfm-placeholder" id="wfm-video-preview-placeholder">No video</span>
|
||||
<video id="wfm-video-preview-video" class="wfm-video-preview-el" controls style="display:none;"></video>
|
||||
</div>
|
||||
<div class="wfm-video-source-panel">
|
||||
<div class="wfm-video-pane-header" id="wfm-video-source-label">Video Source</div>
|
||||
<p class="wfm-video-prop-hint" id="wfm-video-source-hint">Load any video here to use Frame/GIF tools without generating one.</p>
|
||||
@@ -2794,12 +2737,142 @@
|
||||
<button type="button" class="wfm-btn wfm-btn-sm" id="wfm-video-source-clear">Clear</button>
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-video-preview-frame" id="wfm-video-source-preview-frame">
|
||||
<span class="wfm-placeholder" id="wfm-video-source-preview-placeholder">Asset / Source Preview</span>
|
||||
<video id="wfm-video-source-preview-video" class="wfm-video-preview-el" controls style="display:none;"></video>
|
||||
</div>
|
||||
<div class="wfm-video-preview-frame" id="wfm-video-preview-frame">
|
||||
<span class="wfm-placeholder" id="wfm-video-preview-placeholder">Generated Video Preview</span>
|
||||
<video id="wfm-video-preview-video" class="wfm-video-preview-el" controls style="display:none;"></video>
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-video-edit-panel">
|
||||
|
||||
<div class="wfm-video-subtab-nav wfm-video-center-subtab-nav">
|
||||
<button type="button" class="wfm-video-subtab-btn active" data-video-subtab="plan">Plan</button>
|
||||
<button type="button" class="wfm-video-subtab-btn" data-video-subtab="edit">Edit</button>
|
||||
</div>
|
||||
|
||||
<!-- Plan: バッチ動画生成のタイムライン編集・実行(中央下部、Planタブ選択時のみ表示) -->
|
||||
<div id="wfm-video-plan-content" class="wfm-video-subtab-panel wfm-video-plan-content" data-video-subtab-panel="plan">
|
||||
<div class="wfm-video-plan-topbar">
|
||||
<div class="wfm-video-wf-row">
|
||||
<span id="wfm-video-wf-name" class="wfm-video-wf-name">No workflow loaded</span>
|
||||
<div class="wfm-lab-plan-workflow-row" id="wfm-video-plan-workflow-row" style="display:none;">
|
||||
<span id="wfm-video-plan-workflow-name" class="wfm-lab-plan-workflow-name"></span>
|
||||
<button type="button" id="wfm-video-plan-workflow-load-btn" class="wfm-btn wfm-btn-xs" title="Load this plan's recorded workflow">Open Workflow</button>
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-video-plan-basesettings">
|
||||
<div>
|
||||
<label for="wfm-video-plan-aspect-ratio" id="wfm-video-plan-aspect-ratio-label">Aspect Ratio</label>
|
||||
<select id="wfm-video-plan-aspect-ratio" class="wfm-input"></select>
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-plan-megapixels" id="wfm-video-plan-megapixels-label">Megapixels</label>
|
||||
<input type="number" id="wfm-video-plan-megapixels" class="wfm-input" step="0.01" min="0.01" value="0.2">
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-plan-multiple" id="wfm-video-plan-multiple-label">Multiple</label>
|
||||
<input type="number" id="wfm-video-plan-multiple" class="wfm-input" step="8" min="8" value="32">
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-block-duration" id="wfm-video-block-duration-label">Duration (seconds)</label>
|
||||
<input type="number" id="wfm-video-block-duration" class="wfm-input" step="0.5" min="0.5" value="2">
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-plan-seed-value" id="wfm-video-plan-seed-value-label">Noise Seed</label>
|
||||
<div class="wfm-video-seed-inline">
|
||||
<input type="number" id="wfm-video-plan-seed-value" class="wfm-input" value="0">
|
||||
<label class="wfm-video-seed-randomize-inline"><input type="checkbox" id="wfm-video-plan-seed-randomize" checked> Rand</label>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<div class="wfm-video-plan-extrasettings">
|
||||
<div>
|
||||
<label for="wfm-video-plan-width" id="wfm-video-plan-width-label">Width</label>
|
||||
<input type="number" id="wfm-video-plan-width" class="wfm-input" step="16" min="16" value="1280">
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-plan-height" id="wfm-video-plan-height-label">Height</label>
|
||||
<input type="number" id="wfm-video-plan-height" class="wfm-input" step="16" min="16" value="720">
|
||||
</div>
|
||||
<div>
|
||||
<label id="wfm-video-plan-turbo-mode-label">Turbo Mode</label>
|
||||
<label class="wfm-video-checkbox-inline"><input type="checkbox" id="wfm-video-plan-turbo-mode"> Enabled</label>
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-plan-turbo-strength" id="wfm-video-plan-turbo-strength-label">Strength</label>
|
||||
<input type="number" id="wfm-video-plan-turbo-strength" class="wfm-input" step="0.05" min="0" value="1">
|
||||
</div>
|
||||
<div>
|
||||
<label for="wfm-video-plan-turbo-steps" id="wfm-video-plan-turbo-steps-label">Steps</label>
|
||||
<input type="number" id="wfm-video-plan-turbo-steps" class="wfm-input" step="1" min="1" value="8">
|
||||
</div>
|
||||
<div>
|
||||
<label id="wfm-video-plan-prompt-enhance-label">Prompt Enhance</label>
|
||||
<label class="wfm-video-checkbox-inline"><input type="checkbox" id="wfm-video-plan-prompt-enhance"> Enabled</label>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="wfm-video-timeline-wrap">
|
||||
<div class="wfm-video-timeline-track" id="wfm-video-timeline-track"></div>
|
||||
<div class="wfm-video-timeline-toolbar">
|
||||
<button type="button" id="wfm-video-block-split-btn" class="wfm-btn wfm-btn-xs">+ Split</button>
|
||||
<button type="button" id="wfm-video-block-add-btn" class="wfm-btn wfm-btn-xs">+ Block</button>
|
||||
<button type="button" id="wfm-video-block-delete-btn" class="wfm-btn wfm-btn-xs">Delete</button>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div class="wfm-video-plan-main-row">
|
||||
<div class="wfm-video-block-editor" id="wfm-video-block-editor"></div>
|
||||
|
||||
<div class="wfm-video-runplan-panel">
|
||||
<div class="wfm-video-runplan-tabnav">
|
||||
<button type="button" class="wfm-video-runplan-tab active" data-runplan-tab="run">Run</button>
|
||||
<button type="button" class="wfm-video-runplan-tab" data-runplan-tab="plan">Plan</button>
|
||||
</div>
|
||||
|
||||
<div id="wfm-video-runplan-run" class="wfm-video-runplan-content active">
|
||||
<div style="display:flex;gap:6px;">
|
||||
<button id="wfm-video-plan-run-btn" class="wfm-btn wfm-btn-primary" style="flex:1;">Run</button>
|
||||
<button id="wfm-video-plan-cancel-btn" class="wfm-btn wfm-btn-danger" style="display:none;">Cancel</button>
|
||||
</div>
|
||||
<button id="wfm-video-plan-pause-btn" class="wfm-btn" style="width:100%;margin-top:6px;" disabled>Pause</button>
|
||||
|
||||
<div class="wfm-gen-progress-container" style="margin-top:8px;">
|
||||
<div class="wfm-gen-progress-track">
|
||||
<div id="wfm-video-plan-progress-bar" class="wfm-gen-progress-bar"></div>
|
||||
</div>
|
||||
<span id="wfm-video-plan-progress-text" class="wfm-gen-progress-text">Ready</span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<div id="wfm-video-runplan-plan" class="wfm-video-runplan-content" style="display:none;">
|
||||
<label>Note</label>
|
||||
<textarea id="wfm-video-plan-note" class="wfm-input wfm-lab-note" rows="3"></textarea>
|
||||
|
||||
<button id="wfm-video-plan-save-btn" class="wfm-btn wfm-btn-primary" style="width:100%;margin-top:8px;">Plan Save</button>
|
||||
<button id="wfm-video-plan-saveas-btn" class="wfm-btn" style="width:100%;margin-top:6px;">Save As</button>
|
||||
<button id="wfm-video-plan-clear-btn" class="wfm-btn" style="width:100%;margin-top:6px;">Plan Clear</button>
|
||||
|
||||
<div class="wfm-i2i-drop-zone" id="wfm-video-plan-drop-zone" style="margin-top:10px;">
|
||||
<label class="wfm-i2i-drop-label">
|
||||
<input type="file" id="wfm-video-plan-file-input" accept="application/json,.json,image/png,.png" style="display:none;">
|
||||
Drop plan (.json/.png) here or click to select
|
||||
</label>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
|
||||
<!-- Edit: 将来の動画編集機能用プレースホルダー -->
|
||||
<div id="wfm-video-subtab-edit" class="wfm-video-subtab-panel wfm-video-edit-panel" data-video-subtab-panel="edit" style="display:none;">
|
||||
<span id="wfm-video-edit-placeholder-label" class="wfm-placeholder">Editing tools coming soon</span>
|
||||
</div>
|
||||
</div>
|
||||
<!-- 右ペイン: プロパティ(Frame抽出 / GIF変換の2タブ) -->
|
||||
<!-- 右ペイン: プロパティ(Frame抽出 / GIF変換の2タブ)。中央ペインと同様に常時表示 -->
|
||||
<div class="wfm-video-properties-panel">
|
||||
<div class="wfm-video-prop-tabnav">
|
||||
<button type="button" class="wfm-video-prop-tab active" data-prop-tab="frame" id="wfm-video-prop-tab-frame">Frame</button>
|
||||
@@ -2907,13 +2980,8 @@
|
||||
</div>
|
||||
<div id="wfm-tagger-ollama-settings" style="display:none">
|
||||
<div class="wfm-form-row wfm-tagger-form-row">
|
||||
<label class="wfm-tagger-label" id="wfm-tagger-ollama-url-label"></label>
|
||||
<input type="text" id="wfm-tagger-ollama-url" class="wfm-search-input" value="http://127.0.0.1:11434" style="flex:1;">
|
||||
</div>
|
||||
<div class="wfm-form-row wfm-tagger-form-row">
|
||||
<label class="wfm-tagger-label" id="wfm-tagger-ollama-model-label"></label>
|
||||
<select id="wfm-tagger-ollama-model" class="wfm-select wfm-tagger-select"></select>
|
||||
<button id="wfm-tagger-ollama-refresh-btn" class="wfm-btn wfm-btn-sm" title="Refresh models">↻</button>
|
||||
<span id="wfm-tagger-ollama-backend-value" style="flex:1;color:var(--wfm-text-secondary);font-size:12px;"></span>
|
||||
<button id="wfm-tagger-ollama-settings-btn" class="wfm-btn wfm-btn-sm" title="Settings">⚙</button>
|
||||
</div>
|
||||
<div class="wfm-form-row wfm-tagger-form-row" style="align-items:flex-start">
|
||||
<label class="wfm-tagger-label" id="wfm-tagger-ollama-prompt-label" style="padding-top:4px;"></label>
|
||||
@@ -2975,18 +3043,13 @@
|
||||
<div class="wfm-tagger-section-header">
|
||||
<label style="display:flex;align-items:center;gap:6px;cursor:pointer;font-weight:600;">
|
||||
<input type="checkbox" id="wfm-tagger-batch-ollama-enable">
|
||||
Ollama VLM
|
||||
<span id="wfm-tagger-batch-ollama-header-label">VLM Tagging</span>
|
||||
</label>
|
||||
</div>
|
||||
<div id="wfm-tagger-batch-ollama-settings">
|
||||
<div class="wfm-form-row wfm-tagger-form-row">
|
||||
<label class="wfm-tagger-label" id="wfm-tagger-batch-url-label"></label>
|
||||
<input type="text" id="wfm-tagger-batch-ollama-url" class="wfm-search-input" value="http://127.0.0.1:11434" style="flex:1;">
|
||||
</div>
|
||||
<div class="wfm-form-row wfm-tagger-form-row">
|
||||
<label class="wfm-tagger-label" id="wfm-tagger-batch-model-label"></label>
|
||||
<select id="wfm-tagger-batch-ollama-model" class="wfm-select wfm-tagger-select"></select>
|
||||
<button id="wfm-tagger-batch-ollama-refresh-btn" class="wfm-btn wfm-btn-sm">↻</button>
|
||||
<span id="wfm-tagger-batch-backend-value" style="flex:1;color:var(--wfm-text-secondary);font-size:12px;"></span>
|
||||
<button id="wfm-tagger-batch-ollama-settings-btn" class="wfm-btn wfm-btn-sm" title="Settings">⚙</button>
|
||||
</div>
|
||||
<div class="wfm-form-row wfm-tagger-form-row" style="align-items:flex-start">
|
||||
<label class="wfm-tagger-label" id="wfm-tagger-batch-prompt-label" style="padding-top:4px;"></label>
|
||||
@@ -3214,6 +3277,7 @@
|
||||
</div>
|
||||
<div class="wfm-ai-settings-row">
|
||||
<button id="wfm-ai-test-btn" class="wfm-btn">Test connection</button>
|
||||
<button id="wfm-ai-unload-btn" class="wfm-btn">Unload Model</button>
|
||||
<span id="wfm-ai-test-result" class="wfm-ai-test-result"></span>
|
||||
</div>
|
||||
</div>
|
||||
|
||||