Compare commits

...
1 Commits
Author SHA1 Message Date
ketle-manandClaude Sonnet 4.6 95266a20b8 v0.3.13: AI tab (Translation, VLM, Settings) for SPA and Library panel
- Add A tab to SPA (templates/index.html) with Translation, VLM, Settings sub-tabs
- Add new static/js/ai-tab.js module (Ollama / LM Studio backends, full i18n via t())
- Add A tab to Workflow Studio Library side panel (node_sets_menu.js)
- Settings shared between SPA and Library panel via localStorage (wfm_ai_settings)
- URL security: validate backend URL with new URL() before any network call
- Rename ollamaSettings to 'Ollama Settings (Prompt Tab)' in EN/JA/ZH to distinguish from AI tab
- Add AI tab help card and helpSidepanel16 to Help tab (index.html + i18n.js + app.js)
- Update docs/6_ws_library.png, README.md (v0.3.13), DEVLOG.md

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-05-19 14:42:40 +09:00
9 changed files with 1875 additions and 11 deletions
+90
View File
@@ -1,5 +1,95 @@
# DEVLOG - ComfyUI-Workflow-Studio
## 2026-05-19: v0.3.13 — AI タブ(A)追加
### 概要
SPA および Workflow Studio Library サイドパネルの両方に AI タブ(A)を追加。Ollama・LM Studio をバックエンドとして翻訳・VLM(画像解析)機能を提供する。設定は `localStorage` 経由で両インターフェース間で共有。
### 変更内容
#### `templates/index.html`
- タブバーに `<button class="wfm-tab" data-tab="ai">A</button>` を右端に追加
- `<section id="wfm-tab-ai">` を新規追加(3 サブタブ構成)
- **翻訳サブタブ** (`wfm-ai-subtab-translate`): 入力テキストエリア・言語セレクター(日/英/中/Free)・⇄ 入替ボタン・翻訳ボタン・出力テキストエリア・コピーボタン・ステータス表示
- **VLM サブタブ** (`wfm-ai-subtab-vlm`): ドロップゾーン(110px)・タスクドロップダウン(画像の解説/プロンプト作成)・実行ボタン・結果エリア・コピーボタン
- **設定サブタブ** (`wfm-ai-subtab-settings`): バックエンド選択ラジオ・API URL 入力・接続テストボタン・モデル選択+更新ボタン・Free 言語入力(入力/出力)・保存ボタン
- ヘルプタブにAI タブ説明カード追加、Sidepanel カードに `wfm-help-sidepanel-16` を追加
#### `static/js/ai-tab.js`(新規)
- `import { showToast } from "./app.js"` / `import { t } from "./i18n.js"`
- **定数**: `SETTINGS_KEY = "wfm_ai_settings"`、`LANG_NAMES`、`VLM_PROMPTS`(describe / prompt)
- **`isValidBackendUrl(url)`**: `new URL()` で `http:` / `https:` スキームのみ許可
- **`fileToBase64(file)`**: FileReader → `{ base64, mimeType }`
- **`callVLM()`**: Ollama は `images:[b64]`、LM Studio は `image_url` コンテンツブロック
- **`callLLM()`**: テキスト翻訳用 LLM 呼び出し(Ollama / LM Studio)
- **`fetchModels()`**: Ollama `/api/tags`、LM Studio `/v1/models` からモデル一覧取得
- **`buildTranslationPrompt()`**: Free 言語設定対応の翻訳プロンプト生成
- **`initSubTabs()`** / **`initTranslateTab()`** / **`initVlmTab()`** / **`initSettingsTab()`**
- すべての動的文字列を `t()` 経由で i18n 対応済み
- **`export function initAiTab()`**: 全 init 関数のエントリポイント
#### `static/js/app.js`
- `import { initAiTab } from "./ai-tab.js"` を追加
- `DOMContentLoaded` 内に `initAiTab()` を追加
- `tabMap` に `ai: "tabAi"` を追加
- `applyI18nToHtml()` に AI タブの全要素 id マッピングを追加
- サブタブボタン、言語セレクター option、placeholder、ボタンテキスト、セクションタイトル、ラベル
- ヘルプタブ新規 id(`wfm-help-sidepanel-16`、`wfm-help-ai-title`、`wfm-help-ai-1`〜`6`)
#### `static/js/i18n.js`
- `tabAi: "A"` を EN/JA/ZH に追加(タブボタンラベル)
- AI タブ全キーブロックを EN/JA/ZH に追加(計 3 言語 × 約 40 キー)
- サブタブ名、言語オプション、placeholder、ボタンテキスト、ステータス文字列、トースト文字列
- `aiToastNoText`、`aiToastNoModel`、`aiToastInvalidUrl`、`aiToastInvalidUrlInput`
- `aiStatusTranslating`、`aiStatusRunning`、`aiStatusDone`、`aiStatusConnecting`、`aiStatusConnectOk`、`aiStatusConnectFail`
- `aiToastTransFailed`、`aiToastNoCopyText`、`aiToastCopied`、`aiToastNoModels`、`aiToastModelsFailed`
- `aiToastSettingsSaved`、`aiToastNoImage`、`aiToastVlmFailed`、`aiModels`
- ヘルプキー: `helpSidepanel16`、`helpAiTitle`、`helpAi1`〜`helpAi6`
- `ollamaSettings` を EN/JA/ZH で "(プロンプトタブ)" サフィックス付きに改名
#### `static/css/main.css`
- AI サブタブナビ: `.wfm-ai-subtab-nav`、`.wfm-ai-subtab-btn`(`.active` 状態含む)、`.wfm-ai-subtab-content`
- 翻訳タブ: `.wfm-ai-trans-container`、`.wfm-ai-trans-lang-row`、`.wfm-ai-lang-select`、`.wfm-ai-swap-btn`、`.wfm-ai-trans-textarea`、`.wfm-ai-trans-output`、`.wfm-ai-trans-actions`、`.wfm-ai-trans-status`
- ステータス色: `.wfm-ai-status-working`(amber)、`.wfm-ai-status-ok`(green)、`.wfm-ai-status-error`(red)
- VLM タブ: `.wfm-ai-vlm-container`、`.wfm-ai-vlm-drop`(height: 110px、破線ボーダー、I タブと統一)、`.wfm-ai-vlm-label`、`.wfm-ai-vlm-preview`、`.wfm-ai-vlm-task-row`、`.wfm-ai-vlm-result`、`.wfm-ai-vlm-copy-btn`
- 設定タブ: `.wfm-ai-settings-*` 各セクション
#### `web/comfyui/node_sets_menu.js`
- `state` に `aiSubTab: "ai-translate"` を追加
- トップタブバーに `data-toptab="ai"` の A ボタンを I タブの右に追加
- `rebuildSubTabs()`: AI ケースを追加(翻訳/VLM/設定 サブタブ)
- `renderContent()`: `topTab === "ai"` 分岐を追加、検索バー非表示、`renderAiTab()` を呼び出し
- 追加関数:
- `isValidAiUrl()`: URL セキュリティ検証
- `loadAiCfg()` / `saveAiCfg()`: `localStorage` への設定読み書き(SPA と共有)
- `aiFileToBase64()` / `aiCallVLM()` / `aiCallLLM()` / `aiFetchModels()`: バックエンド API ラッパー
- `renderAiTab(container)`: 初回のみ HTML を構築し `setupAiHandlers()` を呼び出す
- `renderAiSubContent()`: サブタブに応じてペインを表示切替
- `setupAiHandlers(container)`: 翻訳・VLM・設定の全イベントハンドラ
- `injectStyles()`: AI タブ CSS を追加(VLM ドロップゾーン高さ 110px を含む)
#### `docs/6_ws_library.png`
- A タブ追加後の Library パネルスクリーンショットに更新
#### `README.md`
- バージョンバッジを `0.3.13` に更新
- Features に **AI Tab (A)** セクションを追加
- Workflow Studio Library のタブ説明を `W/N/P/M/I` → `W/N/P/M/I/A` に更新、A タブ説明を追加
- Requirements — Optional に LM Studio を追記
- Project Structure に `ai-tab.js` を追加
- Changelog に v0.3.13 エントリを追加
---
## 2026-05-18: v0.3.12 リリース — README スクリーンショット刷新 / workflow_analyzer 拡張
### 概要
+24 -4
View File
@@ -5,7 +5,7 @@ A comprehensive workflow management and generation UI plugin for [ComfyUI](https
Browse, organize, and execute workflows directly from a dedicated studio interface — without switching between windows or manually editing JSON.
![Workflow Studio](https://img.shields.io/badge/ComfyUI-Custom_Node-blue)
![Version](https://img.shields.io/badge/version-0.3.12-green)
![Version](https://img.shields.io/badge/version-0.3.13-green)
## Screenshots
@@ -148,8 +148,16 @@ Requires the **[comfyui-image-feeder](https://github.com/ketle-man/comfyui-image
- **Enable / Disable models** — hide models from ComfyUI by renaming the file extension (`.disabled` suffix); toggle per card (⏸ button), per group (Enable All / Disable All), or filter by status (All / Enabled / Disabled)
- **Multi-select & bulk operations** — enter selection mode to check multiple models; bulk action bar supports add/remove from groups and permanent file deletion (model file + preview images + sidecar files such as `.json` / `.info`)
### AI Tab (A) (v0.3.13)
- **Translation sub-tab** — translate text between Japanese, English, Chinese, or a custom Free language using Ollama or LM Studio; language selectors with ⇄ swap button (swaps both language and text content); selections saved automatically
- **VLM sub-tab** — drop an image into the 110px drop zone, select a task (Describe Image / Create Prompt), and click Run to analyze with a vision model; result shown in the output area with a Copy button
- **Settings sub-tab** — choose backend (Ollama / LM Studio), set the API URL, test connection, select a model (with refresh button), and configure Free language names for translation source and destination
- **Settings shared** — settings saved to `localStorage` under `wfm_ai_settings`; shared with the Library panel's A tab so configuration is consistent across both interfaces
- **Backend support** — Ollama (`/api/generate` for text, `/api/tags` for model list); LM Studio OpenAI-compatible API (`/v1/chat/completions`, `/v1/models`); VLM images sent as base64 (`images:[]` for Ollama, `image_url` content block for LM Studio)
- **URL security** — backend URL validated via `new URL()` to enforce `http://` or `https://` scheme
### Workflow Studio Library (ComfyUI Side Panel) (v0.3.9)
- **Tab layout (W / N / P / M / I)** — compact single-letter tabs with full name shown on hover
- **Tab layout (W / N / P / M / I / A)** — compact single-letter tabs with full name shown on hover
- **W — Workflows tab** — browse favorite workflows (All / ★ Favorites / Groups / By Badge sub-tabs), ★ star shown for favorites in All view
- **N — Nodes tab** — browse favorite nodes (All / ★ Favorites / Groups / Sets / 📂 Category / 🧩 Package sub-tabs), ★ star shown for favorites in All view
- **Category sub-tab** — dropdown to filter nodes by top-level category
@@ -157,6 +165,7 @@ Requires the **[comfyui-image-feeder](https://github.com/ketle-man/comfyui-image
- **M — Models tab** — browse installed models (All / ★ Favorites / Groups / By Type sub-tabs)
- **P — Prompts tab** — browse prompt presets with All / Favorites / Categories sub-tabs
- **I — Information tab** — drop a ComfyUI-generated PNG/WebP or workflow JSON in the side panel to view its metadata; supports `UnetLoaderGGUF` and `QuadrupleCLIPLoader` node types; preview area fixed at 110px
- **A — AI Tools tab** — Translation sub-tab and VLM sub-tab powered by Ollama or LM Studio; settings (backend, URL, model) shared with the SPA AI tab via `localStorage`
- **model sub-tab** — Checkpoint, VAE, Diffusion Model, and Text Encoder; drag items to canvas to place the corresponding loader node (Checkpoint → `CheckpointLoaderSimple`, VAE → `VAELoader`, Diffusion Model → `UNETLoader`, Text Encoder → `CLIPLoader`); double-click also places at canvas center
- **lora sub-tab** — LoRA names with `strength_model / strength_clip` values; drag individual LoRA to place `LoraLoader`; **Multiple LORA** section (appears for 1+ LoRAs) drags all LoRAs into a single `Lora Loader (LoraManager)` node
- **Prompts sub-tab** — POS / NEG badge list; drag a prompt to place `CLIPTextEncode` with text pre-filled; click any entry to view full text + Copy button
@@ -226,7 +235,8 @@ Click the **camera icon** (next to the W button) in ComfyUI's top bar to capture
### Optional
- **[Ollama](https://ollama.com/)** — for AI chat assistant and translation features
- **[Ollama](https://ollama.com/)** — for AI chat assistant, translation, and VLM features
- **[LM Studio](https://lmstudio.ai/)** — alternative backend for translation and VLM (OpenAI-compatible API)
- **[Eagle](https://eagle.cool/)** — for auto-saving generated images with metadata
---
@@ -243,6 +253,15 @@ Click the **camera icon** (next to the W button) in ComfyUI's top bar to capture
## Changelog
### v0.3.13
- **AI Tab (A)** — new tab added to both the SPA and the Workflow Studio Library side panel (rightmost tab)
- **Translation sub-tab** — translate text via Ollama or LM Studio between Japanese, English, Chinese, or a custom Free language; ⇄ swap button exchanges both language selectors and text content simultaneously; language selections persisted automatically
- **VLM sub-tab** — drop zone (110px, matching the I tab) accepts images via drag & drop or click; task selector (Describe Image / Create Prompt); Run button streams result into output area with Copy button; Ollama uses `images:[base64]` payload, LM Studio uses `image_url` content block
- **Settings sub-tab** — backend radio (Ollama / LM Studio), API URL input, connection test with live status, model selector with refresh, Free language name fields (source and destination); saved to `localStorage` key `wfm_ai_settings` and shared between SPA and Library panel
- **URL security** — backend URL validated via `new URL()` to enforce `http://` or `https://` scheme before any network call
- **Settings Tab — Ollama section renamed** — "Ollama 設定" → "Ollama 設定(プロンプトタブ)" to distinguish it from the new AI tab's settings
- **Help Tab updated** — added AI Tab (A) feature card and Library panel A tab entry; i18n support in EN/JA/ZH
### v0.3.12
- **GenerateUI — Raw JSON search** — always-visible search bar above the Raw JSON editor; finds all matches as you type with match count (`3/12`); navigate forward/back with ↑/↓ buttons, Enter / Shift+Enter, or Escape / ✕ to clear; current match highlighted in orange, other matches in yellow; search overlay syncs with editor scroll and stays updated while editing
- **Workflow analyzer — extended model type detection** — added CLIPLoader `type` field mapping to model family (`flux`, `hidream_i`, `wan`, `cosmos`, `lumina`, `ovis`, etc.) via `_CLIP_TYPE_TO_MODEL`; subgraph nodes (`definitions.subgraphs`) now scanned for model detection; `UnetLoaderGGUF` and similar loaders matched via `"UnetLoader" in ntype`; new families added: NewBie, Ovis, HiDream, Wan, Cosmos, Lumina; model-name detection refactored into reusable `_detect_model_type_from_name()`
@@ -446,7 +465,7 @@ ComfyUI-Workflow-Studio/
│ ├── settings_service.py # Settings persistence
│ └── png_extractor.py # PNG metadata extraction
├── templates/
│ └── index.html # SPA template (Workflow/GenerateUI/Prompt/Metadata/Gallery/Nodes/Models/Settings/Help)
│ └── index.html # SPA template (Workflow/GenerateUI/Prompt/Metadata/Gallery/Nodes/Models/Settings/Help/AI)
├── static/
│ ├── favicon.svg # Browser tab icon (W+S Wave)
│ ├── css/main.css # Styles
@@ -461,6 +480,7 @@ ComfyUI-Workflow-Studio/
│ ├── comfyui-client.js # ComfyUI WebSocket/API client
│ ├── nodes-tab.js # Node browser & node sets
│ ├── models-tab.js # Model browser & CivitAI integration
│ ├── ai-tab.js # AI tab (Translation, VLM, Settings — Ollama / LM Studio)
│ ├── comfyui-workflow.js # UI-to-API format conversion
│ ├── comfyui-editor.js # Dynamic parameter editor
│ ├── json-highlight.js # JSON syntax highlighting
Binary file not shown.

Before

Width:  |  Height:  |  Size: 24 KiB

After

Width:  |  Height:  |  Size: 16 KiB

+278
View File
@@ -4441,3 +4441,281 @@ body {
padding-top: 5px;
margin-top: 2px;
}
/* ============================================
AI Tab
============================================ */
#wfm-tab-ai {
display: none;
flex-direction: column;
height: 100%;
overflow: hidden;
}
#wfm-tab-ai.active {
display: flex;
}
/* Sub-tab navigation */
.wfm-ai-subtab-nav {
display: flex;
border-bottom: 1px solid var(--wfm-border);
flex-shrink: 0;
background: var(--wfm-surface);
}
.wfm-ai-subtab-btn {
flex: 1;
padding: 8px 12px;
font-size: 13px;
border: none;
border-bottom: 2px solid transparent;
background: transparent;
color: var(--wfm-text-secondary);
cursor: pointer;
transition: color 0.15s, border-color 0.15s;
}
.wfm-ai-subtab-btn:hover {
color: var(--wfm-text);
}
.wfm-ai-subtab-btn.active {
color: var(--wfm-text);
border-bottom-color: var(--wfm-primary);
font-weight: 600;
}
/* Sub-tab content */
.wfm-ai-subtab-content {
flex: 1;
display: none;
flex-direction: column;
overflow: hidden;
min-height: 0;
}
/* Translation tab */
.wfm-ai-trans-container {
display: flex;
flex-direction: column;
gap: 8px;
padding: 12px;
flex: 1;
overflow: hidden;
min-height: 0;
}
.wfm-ai-trans-lang-row {
display: flex;
align-items: center;
gap: 8px;
}
.wfm-ai-lang-select {
flex: 1;
}
.wfm-ai-swap-btn {
flex-shrink: 0;
padding: 6px 10px;
font-size: 16px;
}
.wfm-ai-trans-textarea {
flex: 1;
min-height: 120px;
padding: 8px 10px;
background: var(--wfm-bg);
border: 1px solid var(--wfm-border);
border-radius: var(--wfm-radius-sm);
color: var(--wfm-text);
font-size: 13px;
font-family: inherit;
resize: none;
line-height: 1.5;
transition: border-color 0.15s;
}
.wfm-ai-trans-textarea:focus {
outline: none;
border-color: var(--wfm-primary);
}
.wfm-ai-trans-output {
background: var(--wfm-bg-secondary);
color: var(--wfm-text-secondary);
}
.wfm-ai-trans-output:focus {
border-color: var(--wfm-border);
}
.wfm-ai-trans-actions {
display: flex;
align-items: center;
gap: 8px;
flex-shrink: 0;
}
.wfm-ai-trans-status {
font-size: 12px;
margin-left: 4px;
}
.wfm-ai-status-working { color: var(--wfm-warning); }
.wfm-ai-status-ok { color: var(--wfm-success); }
.wfm-ai-status-error { color: var(--wfm-danger); }
/* VLM placeholder */
.wfm-ai-placeholder-msg {
display: flex;
align-items: center;
justify-content: center;
flex: 1;
color: var(--wfm-text-secondary);
font-size: 14px;
padding: 24px;
}
/* Settings tab */
.wfm-ai-settings-container {
display: flex;
flex-direction: column;
gap: 0;
padding: 12px;
overflow-y: auto;
flex: 1;
}
.wfm-ai-settings-section {
display: flex;
flex-direction: column;
gap: 8px;
padding: 12px 0;
border-bottom: 1px solid var(--wfm-border);
}
.wfm-ai-settings-section:last-child {
border-bottom: none;
}
.wfm-ai-settings-title {
font-size: 12px;
font-weight: 600;
color: var(--wfm-text-secondary);
text-transform: uppercase;
letter-spacing: 0.05em;
}
.wfm-ai-settings-row {
display: flex;
align-items: center;
gap: 8px;
}
.wfm-ai-backend-row {
display: flex;
gap: 16px;
}
.wfm-ai-radio-label {
display: flex;
align-items: center;
gap: 6px;
cursor: pointer;
font-size: 13px;
color: var(--wfm-text);
}
.wfm-ai-label {
font-size: 12px;
color: var(--wfm-text-secondary);
white-space: nowrap;
width: 60px;
flex-shrink: 0;
}
.wfm-ai-url-input {
flex: 1;
}
.wfm-ai-model-select {
flex: 1;
}
.wfm-ai-test-result {
font-size: 12px;
margin-left: 4px;
}
/* VLM Tab */
.wfm-ai-vlm-container {
display: flex;
flex-direction: column;
gap: 8px;
padding: 12px;
flex: 1;
overflow: hidden;
min-height: 0;
}
.wfm-ai-vlm-drop {
height: 110px;
flex-shrink: 0;
display: flex;
align-items: center;
justify-content: center;
border: 2px dashed var(--wfm-border);
border-radius: var(--wfm-radius-sm);
background: var(--wfm-bg);
cursor: pointer;
overflow: hidden;
transition: border-color 0.15s, background 0.15s;
position: relative;
}
.wfm-ai-vlm-drop:hover,
.wfm-ai-vlm-drop.drag-over {
border-color: var(--wfm-primary);
background: rgba(74, 158, 255, 0.05);
}
.wfm-ai-vlm-label {
font-size: 12px;
color: var(--wfm-text-secondary);
pointer-events: none;
}
.wfm-ai-vlm-task-row {
display: flex;
align-items: center;
gap: 8px;
flex-shrink: 0;
}
.wfm-ai-vlm-task-row .wfm-select {
flex: 1;
}
.wfm-ai-vlm-result {
flex: 1;
min-height: 80px;
padding: 8px 10px;
background: var(--wfm-bg-secondary);
border: 1px solid var(--wfm-border);
border-radius: var(--wfm-radius-sm);
color: var(--wfm-text-secondary);
font-size: 13px;
font-family: inherit;
resize: none;
outline: none;
line-height: 1.5;
box-sizing: border-box;
}
.wfm-ai-vlm-copy-btn {
align-self: flex-end;
flex-shrink: 0;
}
+477
View File
@@ -0,0 +1,477 @@
/**
* AI Tab - Translation, VLM, Settings
* Supports Ollama and LM Studio as backends
*/
import { showToast } from "./app.js";
import { t } from "./i18n.js";
const SETTINGS_KEY = "wfm_ai_settings";
const LANG_NAMES = {
ja: "Japanese",
en: "English",
zh: "Chinese",
};
// ============================================
// Settings persistence
// ============================================
function loadAiSettings() {
try {
return JSON.parse(localStorage.getItem(SETTINGS_KEY) || "{}");
} catch {
return {};
}
}
function saveAiSettings(patch) {
const data = { ...loadAiSettings(), ...patch };
localStorage.setItem(SETTINGS_KEY, JSON.stringify(data));
return data;
}
const VLM_PROMPTS = {
describe: "Describe this image in detail.",
prompt: "Create a detailed Stable Diffusion image generation prompt based on this image. Output only the prompt text, nothing else.",
};
function fileToBase64(file) {
return new Promise((resolve, reject) => {
const reader = new FileReader();
reader.onload = e => {
const b64 = e.target.result.split(",")[1];
resolve({ base64: b64, mimeType: file.type });
};
reader.onerror = reject;
reader.readAsDataURL(file);
});
}
async function callVLM(url, backend, model, prompt, base64Image, mimeType) {
if (backend === "ollama") {
const res = await fetch(`${url}/api/generate`, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ model, prompt, images: [base64Image], stream: false }),
});
if (!res.ok) throw new Error(`HTTP ${res.status}`);
return (await res.json()).response || "";
} else {
const res = await fetch(`${url}/v1/chat/completions`, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model,
messages: [{ role: "user", content: [
{ type: "text", text: prompt },
{ type: "image_url", image_url: { url: `data:${mimeType};base64,${base64Image}` } },
]}],
stream: false,
}),
});
if (!res.ok) throw new Error(`HTTP ${res.status}`);
return (await res.json()).choices?.[0]?.message?.content || "";
}
}
// ============================================
// URL validation
// ============================================
function isValidBackendUrl(url) {
try {
const u = new URL(url);
return u.protocol === "http:" || u.protocol === "https:";
} catch {
return false;
}
}
// ============================================
// API helpers
// ============================================
async function fetchModels(url, backend) {
if (backend === "ollama") {
const res = await fetch(`${url}/api/tags`);
if (!res.ok) throw new Error(`HTTP ${res.status}`);
const data = await res.json();
return (data.models || []).map((m) => m.name);
} else {
// LM Studio (OpenAI-compatible)
const res = await fetch(`${url}/v1/models`);
if (!res.ok) throw new Error(`HTTP ${res.status}`);
const data = await res.json();
return (data.data || []).map((m) => m.id);
}
}
async function testConnection(url, backend) {
const models = await fetchModels(url, backend);
return models.length;
}
async function callLLM(url, backend, model, prompt) {
if (backend === "ollama") {
const res = await fetch(`${url}/api/generate`, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ model, prompt, stream: false }),
});
if (!res.ok) throw new Error(`HTTP ${res.status}`);
const data = await res.json();
return data.response || "";
} else {
// LM Studio (OpenAI-compatible)
const res = await fetch(`${url}/v1/chat/completions`, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model,
messages: [{ role: "user", content: prompt }],
stream: false,
}),
});
if (!res.ok) throw new Error(`HTTP ${res.status}`);
const data = await res.json();
return data.choices?.[0]?.message?.content || "";
}
}
// ============================================
// Translation prompt builder
// ============================================
function buildTranslationPrompt(text, srcLang, dstLang, settings) {
const srcName = srcLang === "free" ? (settings.freeSrcLang || "Auto") : LANG_NAMES[srcLang];
const dstName = dstLang === "free" ? (settings.freeDstLang || "English") : LANG_NAMES[dstLang];
const fromPart = srcLang === "free" ? "" : `from ${srcName} `;
return `Translate the following text ${fromPart}to ${dstName}. Output only the translated text, nothing else.\n\n${text}`;
}
// ============================================
// Sub-tab switching
// ============================================
function initSubTabs() {
document.querySelectorAll(".wfm-ai-subtab-btn").forEach((btn) => {
btn.addEventListener("click", () => {
document.querySelectorAll(".wfm-ai-subtab-btn").forEach((b) => b.classList.remove("active"));
btn.classList.add("active");
const tabId = btn.dataset.aiSubtab;
document.querySelectorAll(".wfm-ai-subtab-content").forEach((c) => {
c.style.display = "none";
});
const target = document.getElementById(`wfm-ai-subtab-${tabId}`);
if (target) target.style.display = "flex";
});
});
// Show first sub-tab on init
const first = document.getElementById("wfm-ai-subtab-translate");
if (first) first.style.display = "flex";
}
// ============================================
// Translation tab
// ============================================
function initTranslateTab() {
const srcLangSel = document.getElementById("wfm-ai-src-lang");
const dstLangSel = document.getElementById("wfm-ai-dst-lang");
const swapBtn = document.getElementById("wfm-ai-trans-swap-btn");
const inputEl = document.getElementById("wfm-ai-trans-input");
const outputEl = document.getElementById("wfm-ai-trans-output");
const transBtn = document.getElementById("wfm-ai-trans-btn");
const copyBtn = document.getElementById("wfm-ai-trans-copy-btn");
const statusEl = document.getElementById("wfm-ai-trans-status");
if (!transBtn) return;
// Restore saved language selections
const saved = loadAiSettings();
if (saved.srcLang && srcLangSel) srcLangSel.value = saved.srcLang;
if (saved.dstLang && dstLangSel) dstLangSel.value = saved.dstLang;
// Persist language selections
srcLangSel?.addEventListener("change", () => saveAiSettings({ srcLang: srcLangSel.value }));
dstLangSel?.addEventListener("change", () => saveAiSettings({ dstLang: dstLangSel.value }));
// Swap languages
swapBtn?.addEventListener("click", () => {
const tmp = srcLangSel.value;
srcLangSel.value = dstLangSel.value;
dstLangSel.value = tmp;
saveAiSettings({ srcLang: srcLangSel.value, dstLang: dstLangSel.value });
// Swap text content too
const tmpText = inputEl.value;
inputEl.value = outputEl.value;
outputEl.value = tmpText;
});
// Translate
transBtn.addEventListener("click", async () => {
const text = inputEl.value.trim();
if (!text) {
showToast(t("aiToastNoText"), "error");
return;
}
const settings = loadAiSettings();
const { backend = "ollama", backendUrl, model } = settings;
const url = backendUrl || (backend === "ollama" ? "http://localhost:11434" : "http://localhost:1234");
if (!isValidBackendUrl(url)) {
showToast(t("aiToastInvalidUrl"), "error");
return;
}
if (!model) {
showToast(t("aiToastNoModel"), "error");
return;
}
transBtn.disabled = true;
statusEl.textContent = t("aiStatusTranslating");
statusEl.className = "wfm-ai-trans-status wfm-ai-status-working";
outputEl.value = "";
try {
const prompt = buildTranslationPrompt(text, srcLangSel.value, dstLangSel.value, settings);
const result = await callLLM(url, backend, model, prompt);
outputEl.value = result.trim();
statusEl.textContent = t("aiStatusDone");
statusEl.className = "wfm-ai-trans-status wfm-ai-status-ok";
} catch (err) {
statusEl.textContent = `${t("aiStatusConnectFail")}${err.message}`;
statusEl.className = "wfm-ai-trans-status wfm-ai-status-error";
showToast(t("aiToastTransFailed") + err.message, "error");
} finally {
transBtn.disabled = false;
}
});
// Copy translated text
copyBtn?.addEventListener("click", () => {
const text = outputEl.value;
if (!text) {
showToast(t("aiToastNoCopyText"), "error");
return;
}
navigator.clipboard.writeText(text).then(() => {
showToast(t("aiToastCopied"), "success");
});
});
}
// ============================================
// Settings tab
// ============================================
async function refreshModels() {
const settings = loadAiSettings();
const backend = document.querySelector("input[name='wfm-ai-backend']:checked")?.value || "ollama";
const url = document.getElementById("wfm-ai-backend-url")?.value?.trim() || "";
const modelSel = document.getElementById("wfm-ai-model-select");
const refreshBtn = document.getElementById("wfm-ai-model-refresh-btn");
if (!modelSel) return;
if (refreshBtn) refreshBtn.disabled = true;
try {
const models = await fetchModels(url, backend);
modelSel.innerHTML = `<option value="">-- ${t("aiSettingsModelPlaceholder")} --</option>`;
models.forEach((name) => {
const opt = document.createElement("option");
opt.value = name;
opt.textContent = name;
if (name === settings.model) opt.selected = true;
modelSel.appendChild(opt);
});
if (models.length === 0) showToast(t("aiToastNoModels"), "error");
} catch (err) {
showToast(t("aiToastModelsFailed") + err.message, "error");
} finally {
if (refreshBtn) refreshBtn.disabled = false;
}
}
function initSettingsTab() {
const saved = loadAiSettings();
// Restore saved values
const backendRadios = document.querySelectorAll("input[name='wfm-ai-backend']");
backendRadios.forEach((r) => {
if (r.value === (saved.backend || "ollama")) r.checked = true;
});
const urlInput = document.getElementById("wfm-ai-backend-url");
if (urlInput && saved.backendUrl) urlInput.value = saved.backendUrl;
// Update URL placeholder when backend changes
backendRadios.forEach((r) => {
r.addEventListener("change", () => {
if (!urlInput) return;
const defaultUrl = r.value === "ollama" ? "http://localhost:11434" : "http://localhost:1234";
if (!saved.backendUrl) urlInput.value = defaultUrl;
});
});
// Connection test
document.getElementById("wfm-ai-test-btn")?.addEventListener("click", async () => {
const testBtn = document.getElementById("wfm-ai-test-btn");
const resultEl = document.getElementById("wfm-ai-test-result");
const backend = document.querySelector("input[name='wfm-ai-backend']:checked")?.value || "ollama";
const url = urlInput?.value?.trim() || "";
if (!isValidBackendUrl(url)) {
if (resultEl) {
resultEl.textContent = t("aiToastInvalidUrlInput");
resultEl.className = "wfm-ai-test-result wfm-ai-status-error";
}
return;
}
if (testBtn) testBtn.disabled = true;
if (resultEl) {
resultEl.textContent = t("aiStatusConnecting");
resultEl.className = "wfm-ai-test-result wfm-ai-status-working";
}
try {
const count = await testConnection(url, backend);
if (resultEl) {
resultEl.textContent = `${t("aiStatusConnectOk")} (${count} ${t("aiModels")})`;
resultEl.className = "wfm-ai-test-result wfm-ai-status-ok";
}
await refreshModels();
} catch (err) {
if (resultEl) {
resultEl.textContent = `${t("aiStatusConnectFail")}${err.message}`;
resultEl.className = "wfm-ai-test-result wfm-ai-status-error";
}
} finally {
if (testBtn) testBtn.disabled = false;
}
});
// Model refresh
document.getElementById("wfm-ai-model-refresh-btn")?.addEventListener("click", () => refreshModels());
// Free language inputs
const freeSrcInput = document.getElementById("wfm-ai-free-src-lang");
const freeDstInput = document.getElementById("wfm-ai-free-dst-lang");
if (freeSrcInput && saved.freeSrcLang) freeSrcInput.value = saved.freeSrcLang;
if (freeDstInput && saved.freeDstLang) freeDstInput.value = saved.freeDstLang;
// Save settings
document.getElementById("wfm-ai-settings-save-btn")?.addEventListener("click", () => {
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 || "";
const freeSrcLang = freeSrcInput?.value?.trim() || "";
const freeDstLang = freeDstInput?.value?.trim() || "";
if (url && !isValidBackendUrl(url)) {
showToast(t("aiToastInvalidUrl"), "error");
return;
}
saveAiSettings({ backend, backendUrl: url, model, freeSrcLang, freeDstLang });
showToast(t("aiToastSettingsSaved"), "success");
});
// Load models on init if settings exist
if (saved.backendUrl && saved.backend) {
refreshModels().catch(() => {});
}
}
// ============================================
// VLM tab
// ============================================
function initVlmTab() {
const dropEl = document.getElementById("wfm-ai-vlm-drop");
const previewEl = document.getElementById("wfm-ai-vlm-preview");
const labelEl = document.getElementById("wfm-ai-vlm-label");
const fileInput = document.getElementById("wfm-ai-vlm-file");
const taskSel = document.getElementById("wfm-ai-vlm-task");
const runBtn = document.getElementById("wfm-ai-vlm-run");
const statusEl = document.getElementById("wfm-ai-vlm-status");
const resultEl = document.getElementById("wfm-ai-vlm-result");
const copyBtn = document.getElementById("wfm-ai-vlm-copy");
if (!dropEl) return;
let vlmImage = null; // { base64, mimeType }
const loadImage = async (file) => {
if (!file || !file.type.startsWith("image/")) return;
vlmImage = await fileToBase64(file);
previewEl.src = `data:${vlmImage.mimeType};base64,${vlmImage.base64}`;
previewEl.style.display = "block";
labelEl.style.display = "none";
};
dropEl.addEventListener("click", () => fileInput.click());
fileInput.addEventListener("change", e => { if (e.target.files[0]) loadImage(e.target.files[0]); });
dropEl.addEventListener("dragover", e => { e.preventDefault(); dropEl.classList.add("drag-over"); });
dropEl.addEventListener("dragleave", () => dropEl.classList.remove("drag-over"));
dropEl.addEventListener("drop", e => {
e.preventDefault();
dropEl.classList.remove("drag-over");
if (e.dataTransfer.files[0]) loadImage(e.dataTransfer.files[0]);
});
runBtn.addEventListener("click", async () => {
if (!vlmImage) { showToast(t("aiToastNoImage"), "error"); return; }
const settings = loadAiSettings();
const { backend = "ollama", backendUrl, model } = settings;
const url = backendUrl || (backend === "ollama" ? "http://localhost:11434" : "http://localhost:1234");
if (!isValidBackendUrl(url)) {
showToast(t("aiToastInvalidUrl"), "error");
return;
}
if (!model) { showToast(t("aiToastNoModel"), "error"); return; }
const task = taskSel?.value || "describe";
runBtn.disabled = true;
statusEl.textContent = t("aiStatusRunning");
statusEl.className = "wfm-ai-trans-status wfm-ai-status-working";
resultEl.value = "";
try {
const result = await callVLM(url, backend, model, VLM_PROMPTS[task], vlmImage.base64, vlmImage.mimeType);
resultEl.value = result.trim();
statusEl.textContent = t("aiStatusDone");
statusEl.className = "wfm-ai-trans-status wfm-ai-status-ok";
} catch (err) {
statusEl.textContent = `${t("aiStatusConnectFail")}${err.message}`;
statusEl.className = "wfm-ai-trans-status wfm-ai-status-error";
showToast(t("aiToastVlmFailed") + err.message, "error");
} finally {
runBtn.disabled = false;
}
});
copyBtn.addEventListener("click", () => {
const text = resultEl.value;
if (!text) { showToast(t("aiToastNoCopyText"), "error"); return; }
navigator.clipboard.writeText(text).then(() => showToast(t("aiToastCopied"), "success"));
});
}
// ============================================
// Export
// ============================================
export function initAiTab() {
initSubTabs();
initTranslateTab();
initVlmTab();
initSettingsTab();
}
+68 -1
View File
@@ -90,7 +90,7 @@ function initTabs() {
function applyI18nToHtml() {
// Tab labels
const tabMap = { workflow: "tabWorkflow", nodes: "tabNodes", models: "tabModels", generate: "tabGenerate", prompt: "tabPrompt", metadata: "tabMetadata", gallery: "tabGallery", settings: "tabSettings", help: "tabHelp" };
const tabMap = { workflow: "tabWorkflow", nodes: "tabNodes", models: "tabModels", generate: "tabGenerate", prompt: "tabPrompt", metadata: "tabMetadata", gallery: "tabGallery", settings: "tabSettings", help: "tabHelp", ai: "tabAi" };
document.querySelectorAll(".wfm-tab").forEach((tab) => {
const key = tabMap[tab.dataset.tab];
if (key) tab.textContent = t(key);
@@ -224,6 +224,67 @@ function applyI18nToHtml() {
const presetCopyNegBtn = document.getElementById("wfm-preset-copy-neg-btn");
if (presetCopyNegBtn) presetCopyNegBtn.textContent = t("copyNegativePrompt");
// AI tab
document.querySelectorAll(".wfm-ai-subtab-btn").forEach(btn => {
if (btn.dataset.aiSubtab === "translate") btn.textContent = t("aiSubTabTranslate");
if (btn.dataset.aiSubtab === "vlm") btn.textContent = t("aiSubTabVlm");
if (btn.dataset.aiSubtab === "ai-settings") btn.textContent = t("aiSubTabSettings");
});
const aiLangMap = { ja: "aiLangJa", en: "aiLangEn", zh: "aiLangZh", free: "aiLangFree" };
[document.getElementById("wfm-ai-src-lang"), document.getElementById("wfm-ai-dst-lang")].forEach(sel => {
if (!sel) return;
sel.querySelectorAll("option").forEach(opt => {
const key = aiLangMap[opt.value];
if (key) opt.textContent = t(key);
});
});
const aiTransInput = document.getElementById("wfm-ai-trans-input");
if (aiTransInput) aiTransInput.placeholder = t("aiTransInputPlaceholder");
const aiTransOutput = document.getElementById("wfm-ai-trans-output");
if (aiTransOutput) aiTransOutput.placeholder = t("aiTransOutputPlaceholder");
const aiTransBtn = document.getElementById("wfm-ai-trans-btn");
if (aiTransBtn) aiTransBtn.textContent = t("aiTranslateBtn");
const aiTransCopyBtn = document.getElementById("wfm-ai-trans-copy-btn");
if (aiTransCopyBtn) aiTransCopyBtn.textContent = t("aiCopyBtn");
const aiVlmLabel = document.getElementById("wfm-ai-vlm-label");
if (aiVlmLabel) aiVlmLabel.textContent = t("aiVlmDropLabel");
const aiVlmTask = document.getElementById("wfm-ai-vlm-task");
if (aiVlmTask) {
aiVlmTask.querySelectorAll("option").forEach(opt => {
if (opt.value === "describe") opt.textContent = t("aiVlmDescribe");
if (opt.value === "prompt") opt.textContent = t("aiVlmPromptCreate");
});
}
const aiVlmRunBtn = document.getElementById("wfm-ai-vlm-run");
if (aiVlmRunBtn) aiVlmRunBtn.textContent = t("aiVlmRunBtn");
const aiVlmResult = document.getElementById("wfm-ai-vlm-result");
if (aiVlmResult) aiVlmResult.placeholder = t("aiVlmResultPlaceholder");
const aiVlmCopyBtn = document.getElementById("wfm-ai-vlm-copy");
if (aiVlmCopyBtn) aiVlmCopyBtn.textContent = t("aiCopyBtn");
const aiBackendTitle = document.getElementById("wfm-ai-settings-backend-title");
if (aiBackendTitle) aiBackendTitle.textContent = t("aiSettingsBackend");
const aiConnTitle = document.getElementById("wfm-ai-settings-conn-title");
if (aiConnTitle) aiConnTitle.textContent = t("aiSettingsConnection");
const aiTestBtn = document.getElementById("wfm-ai-test-btn");
if (aiTestBtn) aiTestBtn.textContent = t("aiSettingsTestBtn");
const aiModelTitle = document.getElementById("wfm-ai-settings-model-title");
if (aiModelTitle) aiModelTitle.textContent = t("aiSettingsModelSection");
const aiModelSel = document.getElementById("wfm-ai-model-select");
if (aiModelSel) {
const firstOpt = aiModelSel.querySelector("option[value='']");
if (firstOpt) firstOpt.textContent = t("aiSettingsModelPlaceholder");
}
const aiModelRefreshBtn = document.getElementById("wfm-ai-model-refresh-btn");
if (aiModelRefreshBtn) aiModelRefreshBtn.textContent = t("aiSettingsRefreshBtn");
const aiFreeLangTitle = document.getElementById("wfm-ai-settings-freelang-title");
if (aiFreeLangTitle) aiFreeLangTitle.textContent = t("aiSettingsFreeLang");
const aiFreeSrcLabel = document.getElementById("wfm-ai-free-src-label");
if (aiFreeSrcLabel) aiFreeSrcLabel.textContent = t("aiSettingsInputLang");
const aiFreeDstLabel = document.getElementById("wfm-ai-free-dst-label");
if (aiFreeDstLabel) aiFreeDstLabel.textContent = t("aiSettingsOutputLang");
const aiSaveBtn = document.getElementById("wfm-ai-settings-save-btn");
if (aiSaveBtn) aiSaveBtn.textContent = t("aiSettingsSaveBtn");
// Group panel labels
const propTitle = document.querySelector("#wfm-side-tab-group .wfm-group-section-title");
if (propTitle) propTitle.textContent = t("properties");
@@ -308,6 +369,10 @@ function applyI18nToHtml() {
"wfm-help-sidepanel-11": "helpSidepanel11", "wfm-help-sidepanel-12": "helpSidepanel12",
"wfm-help-sidepanel-13": "helpSidepanel13",
"wfm-help-sidepanel-14": "helpSidepanel14", "wfm-help-sidepanel-15": "helpSidepanel15",
"wfm-help-sidepanel-16": "helpSidepanel16",
"wfm-help-ai-title": "helpAiTitle",
"wfm-help-ai-1": "helpAi1", "wfm-help-ai-2": "helpAi2", "wfm-help-ai-3": "helpAi3",
"wfm-help-ai-4": "helpAi4", "wfm-help-ai-5": "helpAi5", "wfm-help-ai-6": "helpAi6",
"wfm-help-shortcuts-title": "helpShortcutsTitle",
"wfm-help-shortcuts-1": "helpShortcuts1", "wfm-help-shortcuts-2": "helpShortcuts2",
"wfm-help-shortcuts-3": "helpShortcuts3", "wfm-help-shortcuts-4": "helpShortcuts4",
@@ -365,6 +430,7 @@ import { initSettingsTab, applyTheme, getSavedTheme, applyTextareaFontSize } fro
import { initModelsTab } from "./models-tab.js";
import { initGalleryTab } from "./gallery-tab.js";
import { initMetadataTab } from "./metadata-tab.js";
import { initAiTab } from "./ai-tab.js";
// Apply saved theme immediately to prevent flash of default theme
applyTheme(getSavedTheme());
@@ -387,6 +453,7 @@ document.addEventListener("DOMContentLoaded", () => {
initPromptTab();
initMetadataTab();
initGalleryTab();
initAiTab();
console.log("Workflow Studio: App initialized");
});
+165 -3
View File
@@ -324,6 +324,52 @@ const LANGUAGES = {
galleryOutputDirLabel: "Output Folder Path",
galleryOutputDirHint: "Set the ComfyUI output folder to browse in the Gallery tab. Leave blank to use ComfyUI's default output directory.",
tabAi: "A",
// -- AI Tab --
aiSubTabTranslate: "Translate",
aiSubTabVlm: "VLM",
aiSubTabSettings: "Settings",
aiLangJa: "Japanese", aiLangEn: "English", aiLangZh: "Chinese", aiLangFree: "Free",
aiTransInputPlaceholder: "Enter text to translate...",
aiTransOutputPlaceholder: "Translation result will appear here...",
aiTranslateBtn: "Translate",
aiCopyBtn: "Copy",
aiVlmDropLabel: "Drop PNG / JPG / WebP here or click",
aiVlmDescribe: "Describe Image",
aiVlmPromptCreate: "Create Prompt",
aiVlmRunBtn: "Run",
aiVlmResultPlaceholder: "Result will appear here...",
aiSettingsBackend: "Backend",
aiSettingsConnection: "Connection",
aiSettingsTestBtn: "Test Connection",
aiSettingsModelSection: "Model",
aiSettingsRefreshBtn: "Refresh",
aiSettingsModelPlaceholder: "-- Select Model --",
aiSettingsFreeLang: "Free Language",
aiSettingsInputLang: "Input",
aiSettingsOutputLang: "Output",
aiSettingsSaveBtn: "Save Settings",
aiToastNoText: "Please enter text",
aiToastNoModel: "Please select a model in the Settings tab",
aiToastInvalidUrl: "URL must start with http:// or https://",
aiToastInvalidUrlInput: "Please enter a URL starting with http:// or https://",
aiStatusTranslating: "Translating...",
aiStatusRunning: "Running...",
aiStatusDone: "Done",
aiStatusConnecting: "Connecting...",
aiStatusConnectOk: "Connected",
aiStatusConnectFail: "Connection failed: ",
aiToastTransFailed: "Translation failed: ",
aiToastNoCopyText: "No text to copy",
aiToastCopied: "Copied",
aiToastNoModels: "No models found",
aiToastModelsFailed: "Failed to fetch models: ",
aiToastSettingsSaved: "Settings saved",
aiToastNoImage: "Please drop an image",
aiToastVlmFailed: "VLM failed: ",
aiModels: "models",
// -- Help & Support --
tabHelp: "Help",
helpManualTitle: "Features",
@@ -424,6 +470,14 @@ const LANGUAGES = {
helpSidepanel13: "I tab (Information): drop a ComfyUI PNG/WebP/JSON to inspect model, LoRA, and prompt metadata in the side panel — sub-tabs: model / lora / Prompts; supports UnetLoaderGGUF and QuadrupleCLIPLoader node types",
helpSidepanel14: "Information tab — drag items to canvas: model sub-tab places the loader node (Checkpoint → CheckpointLoaderSimple, VAE → VAELoader, Diffusion Model → UNETLoader, Text Encoder → CLIPLoader); double-click also places at canvas center",
helpSidepanel15: "Information tab — LoRA sub-tab: drag individual LoRA to place LoraLoader; \"Multiple LORA\" section at bottom places all LoRAs in a single Lora Loader (LoraManager) node; Prompts sub-tab: drag a prompt to place CLIPTextEncode node with text pre-filled; click prompt to view full text and copy",
helpSidepanel16: "A tab (AI Tools): Translation and VLM sub-tabs powered by Ollama or LM Studio; settings (backend, URL, model) are shared with the SPA AI tab via localStorage",
helpAiTitle: "AI Tab (A)",
helpAi1: "Translation sub-tab: translate text between Japanese, English, Chinese, or a custom Free language using Ollama or LM Studio",
helpAi2: "Language selectors for source and destination with ⇄ swap button; text content is also swapped; selections are saved automatically",
helpAi3: "VLM sub-tab: drop an image into the drop zone and select a task — Describe Image or Create Prompt — then click Run to analyze with a vision model",
helpAi4: "VLM result is displayed in the output area with a Copy button",
helpAi5: "Settings sub-tab: choose backend (Ollama / LM Studio), set the API URL, test connection, select model, and configure Free language names for translation",
helpAi6: "Settings are saved to localStorage and shared with the Library panel's A tab",
helpShortcutsTitle: "Keyboard Shortcuts",
helpShortcuts1: "Escape: Close modal/panel",
helpShortcuts2: "Enter: Confirm rename, send chat",
@@ -459,7 +513,7 @@ const LANGUAGES = {
comfyuiUrlHint: "When running as ComfyUI plugin, leave empty to use same origin. Only set if ComfyUI is on a different server.",
connectedCheck: "Connected \u2713",
failedConnect: "Failed to connect \u2717",
ollamaSettings: "Ollama Settings",
ollamaSettings: "Ollama Settings (Prompt Tab)",
ollamaUrl: "Ollama API URL",
ollamaDefaultModel: "Default Model",
selectModel: "Select model...",
@@ -897,6 +951,52 @@ const LANGUAGES = {
galleryOutputDirLabel: "Outputフォルダのパス",
galleryOutputDirHint: "ギャラリータブで参照するComfyUIのoutputフォルダを設定します。空欄の場合はComfyUIのデフォルトoutputディレクトリを使用します。",
tabAi: "A",
// -- AI Tab --
aiSubTabTranslate: "翻訳",
aiSubTabVlm: "VLM",
aiSubTabSettings: "設定",
aiLangJa: "日本語", aiLangEn: "英語", aiLangZh: "中国語", aiLangFree: "Free",
aiTransInputPlaceholder: "翻訳するテキストを入力...",
aiTransOutputPlaceholder: "翻訳結果がここに表示されます...",
aiTranslateBtn: "翻訳",
aiCopyBtn: "コピー",
aiVlmDropLabel: "PNG / JPG / WebP をドロップまたはクリック",
aiVlmDescribe: "画像の解説",
aiVlmPromptCreate: "プロンプト作成",
aiVlmRunBtn: "実行",
aiVlmResultPlaceholder: "実行結果がここに表示されます...",
aiSettingsBackend: "バックエンド",
aiSettingsConnection: "接続設定",
aiSettingsTestBtn: "接続テスト",
aiSettingsModelSection: "モデル選択",
aiSettingsRefreshBtn: "更新",
aiSettingsModelPlaceholder: "-- モデルを選択 --",
aiSettingsFreeLang: "Free 言語設定",
aiSettingsInputLang: "入力言語",
aiSettingsOutputLang: "翻訳言語",
aiSettingsSaveBtn: "設定を保存",
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",
aiToastInvalidUrlInput: "http:// または https:// で始まるURLを入力してください",
aiStatusTranslating: "翻訳中...",
aiStatusRunning: "実行中...",
aiStatusDone: "完了",
aiStatusConnecting: "接続中...",
aiStatusConnectOk: "接続成功",
aiStatusConnectFail: "接続失敗: ",
aiToastTransFailed: "翻訳に失敗しました: ",
aiToastNoCopyText: "コピーするテキストがありません",
aiToastCopied: "コピーしました",
aiToastNoModels: "モデルが見つかりません",
aiToastModelsFailed: "モデル取得失敗: ",
aiToastSettingsSaved: "設定を保存しました",
aiToastNoImage: "画像をドロップしてください",
aiToastVlmFailed: "VLM実行失敗: ",
aiModels: "モデル",
// -- Help & Support --
tabHelp: "ヘルプ",
helpManualTitle: "機能一覧",
@@ -997,6 +1097,14 @@ const LANGUAGES = {
helpSidepanel13: "I タブ(Information):ComfyUI の PNG / WebP / JSON をドロップするとサイドパネル内でモデル・LoRA・プロンプトのメタデータを確認可能 — サブタブ: model / lora / Prompts;UnetLoaderGGUF・QuadrupleCLIPLoader ノードタイプに対応",
helpSidepanel14: "Information タブ — キャンバスへドラッグ:model サブタブのアイテムをドラッグすると対応ローダーノードを配置(Checkpoint → CheckpointLoaderSimple、VAE → VAELoader、Diffusion Model → UNETLoader、Text Encoder → CLIPLoader);ダブルクリックでもキャンバス中央に配置可能",
helpSidepanel15: "Information タブ — lora サブタブ:個別 LoRA をドラッグで LoraLoader を配置;下部の「Multiple LORA」セクションをドラッグすると全 LoRA を一括で Lora Loader (LoraManager) に配置;Prompts サブタブ:プロンプトをドラッグするとテキスト入力済みの CLIPTextEncode ノードを配置;クリックで全文表示・コピー可能",
helpSidepanel16: "A タブ(AI ツール):翻訳・VLM サブタブ;設定(バックエンド・URL・モデル)は SPA の AI タブと localStorage で共有される",
helpAiTitle: "AI タブ(A)",
helpAi1: "翻訳サブタブ:Ollama または LM Studio 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",
helpAi2: "入力言語・出力言語セレクターと ⇄ 入替ボタン付き;テキスト内容も同時に入替;選択は自動保存",
helpAi3: "VLM サブタブ:画像をドロップゾーンにドロップしてタスクを選択(画像の解説 / プロンプト作成)し、実行ボタンでビジョンモデルに解析させる",
helpAi4: "VLM の結果は出力エリアに表示され、コピーボタンでクリップボードに取得可能",
helpAi5: "設定サブタブ:バックエンド(Ollama / LM Studio)・API URL・接続テスト・モデル選択・翻訳の Free 言語名を設定",
helpAi6: "設定は localStorage に保存され、Library パネルの A タブと共有される",
helpShortcutsTitle: "キーボード操作",
helpShortcuts1: "Escape:モーダル・パネルを閉じる",
helpShortcuts2: "Enter:名前変更の確定、チャット送信",
@@ -1032,7 +1140,7 @@ const LANGUAGES = {
comfyuiUrlHint: "ComfyUIプラグインとして動作する場合は空欄(同一オリジン推奨)。別サーバーの場合のみ設定してください。",
connectedCheck: "接続成功 \u2713",
failedConnect: "接続失敗 \u2717",
ollamaSettings: "Ollama 設定",
ollamaSettings: "Ollama 設定(プロンプトタブ)",
ollamaUrl: "Ollama API URL",
ollamaDefaultModel: "デフォルトモデル",
selectModel: "モデルを選択...",
@@ -1466,6 +1574,52 @@ const LANGUAGES = {
galleryOutputDirLabel: "输出文件夹路径",
galleryOutputDirHint: "设置图库标签页浏览的ComfyUI输出文件夹。留空则使用ComfyUI默认输出目录。",
tabAi: "A",
// -- AI Tab --
aiSubTabTranslate: "翻译",
aiSubTabVlm: "VLM",
aiSubTabSettings: "设置",
aiLangJa: "日语", aiLangEn: "英语", aiLangZh: "中文", aiLangFree: "Free",
aiTransInputPlaceholder: "输入要翻译的文字...",
aiTransOutputPlaceholder: "翻译结果将显示在这里...",
aiTranslateBtn: "翻译",
aiCopyBtn: "复制",
aiVlmDropLabel: "拖放 PNG / JPG / WebP 或点击",
aiVlmDescribe: "图像说明",
aiVlmPromptCreate: "生成提示词",
aiVlmRunBtn: "执行",
aiVlmResultPlaceholder: "执行结果将显示在这里...",
aiSettingsBackend: "后端",
aiSettingsConnection: "连接设置",
aiSettingsTestBtn: "连接测试",
aiSettingsModelSection: "选择模型",
aiSettingsRefreshBtn: "刷新",
aiSettingsModelPlaceholder: "-- 请选择模型 --",
aiSettingsFreeLang: "Free 语言设置",
aiSettingsInputLang: "输入语言",
aiSettingsOutputLang: "翻译语言",
aiSettingsSaveBtn: "保存设置",
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",
aiToastInvalidUrlInput: "请输入以 http:// 或 https:// 开头的URL",
aiStatusTranslating: "翻译中...",
aiStatusRunning: "执行中...",
aiStatusDone: "完成",
aiStatusConnecting: "连接中...",
aiStatusConnectOk: "连接成功",
aiStatusConnectFail: "连接失败:",
aiToastTransFailed: "翻译失败:",
aiToastNoCopyText: "没有可复制的文字",
aiToastCopied: "已复制",
aiToastNoModels: "未找到模型",
aiToastModelsFailed: "获取模型失败:",
aiToastSettingsSaved: "设置已保存",
aiToastNoImage: "请拖放图像",
aiToastVlmFailed: "VLM执行失败:",
aiModels: "个模型",
// -- Help & Support --
tabHelp: "帮助",
helpManualTitle: "功能列表",
@@ -1566,6 +1720,14 @@ const LANGUAGES = {
helpSidepanel13: "I 标签(Information):拖放 ComfyUI PNG/WebP/JSON 即可在侧面板内查看模型、LoRA 和提示词元数据 — 子标签:model / lora / Prompts;支持 UnetLoaderGGUF 和 QuadrupleCLIPLoader 节点类型",
helpSidepanel14: "Information 标签 — 拖拽到画布:model 子标签拖拽可放置对应加载节点(Checkpoint → CheckpointLoaderSimple、VAE → VAELoader、Diffusion Model → UNETLoader、Text Encoder → CLIPLoader);双击也可放置到画布中央",
helpSidepanel15: "Information 标签 — lora 子标签:拖拽单个 LoRA 放置 LoraLoader;底部「Multiple LORA」区域可将全部 LoRA 一次性放入 Lora Loader (LoraManager) 节点;Prompts 子标签:拖拽提示词放置预填文本的 CLIPTextEncode 节点;点击可查看全文并复制",
helpSidepanel16: "A 标签(AI 工具):翻译子标签和 VLM 子标签;设置(后端、URL、模型)通过 localStorage 与 SPA 的 AI 标签共享",
helpAiTitle: "AI 标签页(A)",
helpAi1: "翻译子标签:使用 Ollama 或 LM Studio 在日语、英语、中文或自定义语言(Free)之间翻译文本",
helpAi2: "源语言和目标语言选择器,带 ⇄ 互换按钮;文本内容也同时互换;选择自动保存",
helpAi3: "VLM 子标签:将图像拖放到投放区域,选择任务(图像描述 / 提示词生成),点击执行按钮用视觉模型进行分析",
helpAi4: "VLM 结果显示在输出区域,可通过复制按钮复制到剪贴板",
helpAi5: "设置子标签:选择后端(Ollama / LM Studio)、设置 API URL、测试连接、选择模型、配置翻译的 Free 语言名称",
helpAi6: "设置保存至 localStorage,并与 Library 面板的 A 标签共享",
helpShortcutsTitle: "键盘操作",
helpShortcuts1: "Escape:关闭弹窗/面板",
helpShortcuts2: "Enter:确认重命名、发送聊天",
@@ -1601,7 +1763,7 @@ const LANGUAGES = {
comfyuiUrlHint: "作为ComfyUI插件运行时留空(推荐同源)。仅在不同服务器时设置。",
connectedCheck: "已连接 \u2713",
failedConnect: "连接失败 \u2717",
ollamaSettings: "Ollama 设置",
ollamaSettings: "Ollama 设置(提示词标签页)",
ollamaUrl: "Ollama API URL",
ollamaDefaultModel: "默认模型",
selectModel: "选择模型...",
+138
View File
@@ -24,6 +24,7 @@
<button class="wfm-tab" data-tab="gallery">Gallery</button>
<button class="wfm-tab" data-tab="settings">Settings</button>
<button class="wfm-tab" data-tab="help">Help</button>
<button class="wfm-tab" data-tab="ai">A</button>
</nav>
</header>
@@ -957,6 +958,19 @@
<li id="wfm-help-sidepanel-13">I tab (Information): drop a ComfyUI PNG/WebP/JSON to inspect model, LoRA, and prompt metadata in the side panel — sub-tabs: model / lora / Prompts; supports UnetLoaderGGUF and QuadrupleCLIPLoader node types</li>
<li id="wfm-help-sidepanel-14">Information tab — drag items to canvas: model sub-tab places the loader node (Checkpoint → CheckpointLoaderSimple, VAE → VAELoader, Diffusion Model → UNETLoader, Text Encoder → CLIPLoader); double-click also places at canvas center</li>
<li id="wfm-help-sidepanel-15">Information tab — LoRA sub-tab: drag individual LoRA to place LoraLoader; "Multiple LORA" section at bottom places all LoRAs in a single Lora Loader (LoraManager) node; Prompts sub-tab: drag a prompt to place CLIPTextEncode node with text pre-filled; click prompt to view full text and copy</li>
<li id="wfm-help-sidepanel-16">A tab (AI Tools): Translation and VLM sub-tabs powered by Ollama or LM Studio; settings (backend, URL, model) are shared with the SPA AI tab via localStorage</li>
</ul>
</div>
<div class="wfm-help-card">
<h3 id="wfm-help-ai-title">AI Tab (A)</h3>
<ul>
<li id="wfm-help-ai-1">Translation sub-tab: translate text between Japanese, English, Chinese, or a custom Free language using Ollama or LM Studio</li>
<li id="wfm-help-ai-2">Language selectors for source and destination with ⇄ swap button; text content is also swapped; selections are saved automatically</li>
<li id="wfm-help-ai-3">VLM sub-tab: drop an image into the drop zone and select a task — Describe Image or Create Prompt — then click Run to analyze with a vision model</li>
<li id="wfm-help-ai-4">VLM result is displayed in the output area with a Copy button</li>
<li id="wfm-help-ai-5">Settings sub-tab: choose backend (Ollama / LM Studio), set the API URL, test connection, select model, and configure Free language names for translation</li>
<li id="wfm-help-ai-6">Settings are saved to localStorage and shared with the Library panel's A tab</li>
</ul>
</div>
@@ -1138,6 +1152,130 @@
</div>
</div>
</section>
<!-- AI Tab -->
<section id="wfm-tab-ai" class="wfm-tab-content">
<!-- サブタブナビ -->
<div class="wfm-ai-subtab-nav">
<button class="wfm-ai-subtab-btn active" data-ai-subtab="translate">翻訳</button>
<button class="wfm-ai-subtab-btn" data-ai-subtab="vlm">VLM</button>
<button class="wfm-ai-subtab-btn" data-ai-subtab="ai-settings">設定</button>
</div>
<!-- 翻訳サブタブ -->
<div id="wfm-ai-subtab-translate" class="wfm-ai-subtab-content">
<div class="wfm-ai-trans-container">
<!-- 言語選択行 -->
<div class="wfm-ai-trans-lang-row">
<select id="wfm-ai-src-lang" class="wfm-select wfm-ai-lang-select">
<option value="ja">日本語</option>
<option value="en">英語</option>
<option value="zh">中国語</option>
<option value="free">Free</option>
</select>
<button id="wfm-ai-trans-swap-btn" class="wfm-btn wfm-ai-swap-btn" title="言語を入れ替え">⇄</button>
<select id="wfm-ai-dst-lang" class="wfm-select wfm-ai-lang-select">
<option value="en">英語</option>
<option value="ja">日本語</option>
<option value="zh">中国語</option>
<option value="free">Free</option>
</select>
</div>
<!-- 入力テキストエリア -->
<textarea id="wfm-ai-trans-input" class="wfm-ai-trans-textarea" placeholder="翻訳するテキストを入力..."></textarea>
<!-- アクションボタン行 -->
<div class="wfm-ai-trans-actions">
<button id="wfm-ai-trans-btn" class="wfm-btn wfm-btn-primary">翻訳</button>
<button id="wfm-ai-trans-copy-btn" class="wfm-btn">コピー</button>
<span id="wfm-ai-trans-status" class="wfm-ai-trans-status"></span>
</div>
<!-- 出力テキストエリア -->
<textarea id="wfm-ai-trans-output" class="wfm-ai-trans-textarea wfm-ai-trans-output" placeholder="翻訳結果がここに表示されます..." readonly></textarea>
</div>
</div>
<!-- VLM サブタブ -->
<div id="wfm-ai-subtab-vlm" class="wfm-ai-subtab-content" style="display:none">
<div class="wfm-ai-vlm-container">
<!-- ドロップゾーン -->
<div class="wfm-ai-vlm-drop" id="wfm-ai-vlm-drop">
<img id="wfm-ai-vlm-preview" style="display:none;max-width:100%;max-height:100%;object-fit:contain;pointer-events:none;">
<span id="wfm-ai-vlm-label" class="wfm-ai-vlm-label">PNG / JPG / WebP をドロップまたはクリック</span>
<input type="file" id="wfm-ai-vlm-file" accept="image/png,image/jpeg,image/webp" style="display:none;">
</div>
<!-- タスク選択行 -->
<div class="wfm-ai-vlm-task-row">
<select id="wfm-ai-vlm-task" class="wfm-select">
<option value="describe">画像の解説</option>
<option value="prompt">プロンプト作成</option>
</select>
<button id="wfm-ai-vlm-run" class="wfm-btn wfm-btn-primary">実行</button>
</div>
<!-- ステータス -->
<span id="wfm-ai-vlm-status" class="wfm-ai-trans-status"></span>
<!-- 結果表示 -->
<textarea id="wfm-ai-vlm-result" class="wfm-ai-vlm-result" placeholder="実行結果がここに表示されます..." readonly></textarea>
<!-- コピーボタン -->
<button id="wfm-ai-vlm-copy" class="wfm-btn wfm-ai-vlm-copy-btn">コピー</button>
</div>
</div>
<!-- 設定サブタブ -->
<div id="wfm-ai-subtab-ai-settings" class="wfm-ai-subtab-content" style="display:none">
<div class="wfm-ai-settings-container">
<!-- バックエンド選択 -->
<div class="wfm-ai-settings-section">
<div class="wfm-ai-settings-title" id="wfm-ai-settings-backend-title">バックエンド</div>
<div class="wfm-ai-backend-row">
<label class="wfm-ai-radio-label">
<input type="radio" name="wfm-ai-backend" value="ollama" checked> Ollama
</label>
<label class="wfm-ai-radio-label">
<input type="radio" name="wfm-ai-backend" value="lmstudio"> LM Studio
</label>
</div>
</div>
<!-- 接続設定 -->
<div class="wfm-ai-settings-section">
<div class="wfm-ai-settings-title" id="wfm-ai-settings-conn-title">接続設定</div>
<div class="wfm-ai-settings-row">
<label class="wfm-ai-label">URL</label>
<input type="text" id="wfm-ai-backend-url" class="wfm-input wfm-ai-url-input" value="http://localhost:11434">
</div>
<div class="wfm-ai-settings-row">
<button id="wfm-ai-test-btn" class="wfm-btn">接続テスト</button>
<span id="wfm-ai-test-result" class="wfm-ai-test-result"></span>
</div>
</div>
<!-- モデル選択 -->
<div class="wfm-ai-settings-section">
<div class="wfm-ai-settings-title" id="wfm-ai-settings-model-title">モデル選択</div>
<div class="wfm-ai-settings-row">
<select id="wfm-ai-model-select" class="wfm-select wfm-ai-model-select">
<option value="">-- モデルを選択 --</option>
</select>
<button id="wfm-ai-model-refresh-btn" class="wfm-btn">更新</button>
</div>
</div>
<!-- Free 言語設定 -->
<div class="wfm-ai-settings-section">
<div class="wfm-ai-settings-title" id="wfm-ai-settings-freelang-title">Free 言語設定</div>
<div class="wfm-ai-settings-row">
<label class="wfm-ai-label" id="wfm-ai-free-src-label">入力言語</label>
<input type="text" id="wfm-ai-free-src-lang" class="wfm-input" placeholder="例: French">
</div>
<div class="wfm-ai-settings-row">
<label class="wfm-ai-label" id="wfm-ai-free-dst-label">翻訳言語</label>
<input type="text" id="wfm-ai-free-dst-lang" class="wfm-input" placeholder="例: German">
</div>
</div>
<!-- 保存 -->
<div class="wfm-ai-settings-section">
<button id="wfm-ai-settings-save-btn" class="wfm-btn wfm-btn-primary">設定を保存</button>
</div>
</div>
</div>
</section>
</main>
<!-- Workflow Detail Modal -->
+635 -3
View File
@@ -58,6 +58,8 @@ const state = {
// Info (Metadata) tab
infoSubTab: "info-model", // "info-model" | "info-lora" | "info-prompt"
infoMeta: null, // parsed metadata from dropped file
// AI tab
aiSubTab: "ai-translate", // "ai-translate" | "ai-vlm" | "ai-settings"
};
// ============================================
@@ -693,6 +695,7 @@ const createPanel = () => {
<button class="wfm-nlp-tab wfm-nlp-top-tab" data-toptab="prompts" title="Prompts">P</button>
<button class="wfm-nlp-tab wfm-nlp-top-tab" data-toptab="models" title="Models">M</button>
<button class="wfm-nlp-tab wfm-nlp-top-tab" data-toptab="info" title="Information (Metadata)">I</button>
<button class="wfm-nlp-tab wfm-nlp-top-tab" data-toptab="ai" title="AI Tools (Translation)">A</button>
</div>
<div class="wfm-nlp-subtabs"></div>
<div class="wfm-nlp-subtabs wfm-nlp-subtabs-row2"></div>
@@ -715,7 +718,7 @@ const createPanel = () => {
const searchInput = panel.querySelector(".wfm-nlp-search-input");
if (searchInput) {
searchInput.value = "";
const placeholders = { workflows: "Search workflows...", nodes: "Search nodes...", prompts: "Search prompts...", models: "Search models...", info: "" };
const placeholders = { workflows: "Search workflows...", nodes: "Search nodes...", prompts: "Search prompts...", models: "Search models...", info: "", ai: "" };
searchInput.placeholder = placeholders[tab] ?? "Search...";
}
panel.querySelectorAll(".wfm-nlp-top-tab").forEach(b => b.classList.remove("active"));
@@ -804,7 +807,27 @@ const rebuildSubTabs = () => {
row2.querySelectorAll(".wfm-nlp-sub-tab").forEach(b => b.classList.remove("active"));
};
if (state.topTab === "info") {
if (state.topTab === "ai") {
const row1Tabs = [
{ key: "ai-translate", label: "翻訳" },
{ key: "ai-vlm", label: "VLM" },
{ key: "ai-settings", label: "設定" },
];
const activeKey = state.aiSubTab;
for (const t of row1Tabs) {
const btn = document.createElement("button");
btn.className = "wfm-nlp-tab wfm-nlp-sub-tab" + (activeKey === t.key ? " active" : "");
btn.dataset.subtab = t.key;
btn.textContent = t.label;
btn.addEventListener("click", () => {
state.aiSubTab = t.key;
updateAllActive();
btn.classList.add("active");
renderAiSubContent();
});
row1.appendChild(btn);
}
} else if (state.topTab === "info") {
const row1Tabs = [
{ key: "info-model", label: "model" },
{ key: "info-lora", label: "lora" },
@@ -980,7 +1003,7 @@ const renderContent = () => {
// Remove filter dropdowns from previous category/package views
panelEl.querySelectorAll(".wfm-nlp-filter-row").forEach(e => e.remove());
// Show/hide search bar and adjust overflow for info tab
// Show/hide search bar and adjust overflow for info/ai tab
const searchEl = panelEl?.querySelector(".wfm-nlp-search");
if (state.topTab === "info") {
if (searchEl) searchEl.style.display = "none";
@@ -988,6 +1011,12 @@ const renderContent = () => {
content.style.padding = "0";
renderInfoTab(content);
return;
} else if (state.topTab === "ai") {
if (searchEl) searchEl.style.display = "none";
content.style.overflowY = "hidden";
content.style.padding = "0";
renderAiTab(content);
return;
} else {
if (searchEl) searchEl.style.display = "";
content.style.overflowY = "auto";
@@ -2726,6 +2755,423 @@ const renderInfoTab = (container) => {
renderInfoSubContent();
};
// ============================================
// AI Tab
// ============================================
const AI_SETTINGS_KEY = "wfm_ai_settings";
const AI_LANG_NAMES = { ja: "Japanese", en: "English", zh: "Chinese" };
function isValidAiUrl(url) {
try {
const u = new URL(url);
return u.protocol === "http:" || u.protocol === "https:";
} catch {
return false;
}
}
function loadAiCfg() {
try { return JSON.parse(localStorage.getItem(AI_SETTINGS_KEY) || "{}"); } catch { return {}; }
}
function saveAiCfg(patch) {
const d = { ...loadAiCfg(), ...patch };
localStorage.setItem(AI_SETTINGS_KEY, JSON.stringify(d));
return d;
}
async function aiCallLLM(url, backend, model, prompt) {
if (backend === "ollama") {
const r = await fetch(`${url}/api/generate`, {
method: "POST", headers: { "Content-Type": "application/json" },
body: JSON.stringify({ model, prompt, stream: false }),
});
if (!r.ok) throw new Error(`HTTP ${r.status}`);
return (await r.json()).response || "";
} else {
const r = await fetch(`${url}/v1/chat/completions`, {
method: "POST", headers: { "Content-Type": "application/json" },
body: JSON.stringify({ model, messages: [{ role: "user", content: prompt }], stream: false }),
});
if (!r.ok) throw new Error(`HTTP ${r.status}`);
const d = await r.json();
return d.choices?.[0]?.message?.content || "";
}
}
function aiFileToBase64(file) {
return new Promise((resolve, reject) => {
const reader = new FileReader();
reader.onload = e => {
const b64 = e.target.result.split(",")[1];
resolve({ base64: b64, mimeType: file.type });
};
reader.onerror = reject;
reader.readAsDataURL(file);
});
}
async function aiCallVLM(url, backend, model, prompt, base64Image, mimeType) {
if (backend === "ollama") {
const r = await fetch(`${url}/api/generate`, {
method: "POST", headers: { "Content-Type": "application/json" },
body: JSON.stringify({ model, prompt, images: [base64Image], stream: false }),
});
if (!r.ok) throw new Error(`HTTP ${r.status}`);
return (await r.json()).response || "";
} else {
const r = await fetch(`${url}/v1/chat/completions`, {
method: "POST", headers: { "Content-Type": "application/json" },
body: JSON.stringify({
model,
messages: [{ role: "user", content: [
{ type: "text", text: prompt },
{ type: "image_url", image_url: { url: `data:${mimeType};base64,${base64Image}` } },
]}],
stream: false,
}),
});
if (!r.ok) throw new Error(`HTTP ${r.status}`);
return (await r.json()).choices?.[0]?.message?.content || "";
}
}
async function aiFetchModels(url, backend) {
if (backend === "ollama") {
const r = await fetch(`${url}/api/tags`);
if (!r.ok) throw new Error(`HTTP ${r.status}`);
return ((await r.json()).models || []).map(m => m.name);
} else {
const r = await fetch(`${url}/v1/models`);
if (!r.ok) throw new Error(`HTTP ${r.status}`);
return ((await r.json()).data || []).map(m => m.id);
}
}
const renderAiTab = (container) => {
if (!container.querySelector(".wfm-nlp-ai-layout")) {
container.innerHTML = `
<div class="wfm-nlp-ai-layout">
<!-- 翻訳サブ -->
<div id="wfm-nlp-ai-translate" class="wfm-nlp-ai-pane">
<div class="wfm-nlp-ai-lang-row">
<select id="wfm-nlp-ai-src" class="wfm-nlp-ai-sel">
<option value="ja">日本語</option>
<option value="en">英語</option>
<option value="zh">中国語</option>
<option value="free">Free</option>
</select>
<button id="wfm-nlp-ai-swap" class="wfm-nlp-ai-swap" title="入替">⇄</button>
<select id="wfm-nlp-ai-dst" class="wfm-nlp-ai-sel">
<option value="en">英語</option>
<option value="ja">日本語</option>
<option value="zh">中国語</option>
<option value="free">Free</option>
</select>
</div>
<textarea id="wfm-nlp-ai-input" class="wfm-nlp-ai-textarea" placeholder="翻訳するテキストを入力..."></textarea>
<div class="wfm-nlp-ai-actions">
<button id="wfm-nlp-ai-trans-btn" class="wfm-nlp-ai-btn wfm-nlp-ai-btn-primary">翻訳</button>
<button id="wfm-nlp-ai-copy-btn" class="wfm-nlp-ai-btn">コピー</button>
<span id="wfm-nlp-ai-status" class="wfm-nlp-ai-status"></span>
</div>
<textarea id="wfm-nlp-ai-output" class="wfm-nlp-ai-textarea wfm-nlp-ai-output" placeholder="翻訳結果..." readonly></textarea>
</div>
<!-- VLM サブ -->
<div id="wfm-nlp-ai-vlm" class="wfm-nlp-ai-pane" style="display:none;">
<div class="wfm-nlp-ai-vlm-drop" id="wfm-nlp-ai-vlm-drop">
<img id="wfm-nlp-ai-vlm-preview" style="display:none;max-width:100%;max-height:100%;object-fit:contain;pointer-events:none;">
<span id="wfm-nlp-ai-vlm-label" class="wfm-nlp-ai-vlm-label">PNG / JPG / WebP をドロップ</span>
<input type="file" id="wfm-nlp-ai-vlm-file" accept="image/png,image/jpeg,image/webp" style="display:none;">
</div>
<div class="wfm-nlp-ai-row">
<select id="wfm-nlp-ai-vlm-task" class="wfm-nlp-ai-sel" style="flex:1;">
<option value="describe">画像の解説</option>
<option value="prompt">プロンプト作成</option>
</select>
<button id="wfm-nlp-ai-vlm-run" class="wfm-nlp-ai-btn wfm-nlp-ai-btn-primary">実行</button>
</div>
<span id="wfm-nlp-ai-vlm-status" class="wfm-nlp-ai-status"></span>
<textarea id="wfm-nlp-ai-vlm-result" class="wfm-nlp-ai-textarea wfm-nlp-ai-output" style="flex:1;min-height:60px;" placeholder="実行結果がここに表示されます..." readonly></textarea>
<button id="wfm-nlp-ai-vlm-copy" class="wfm-nlp-ai-btn" style="align-self:flex-end;">コピー</button>
</div>
<!-- 設定サブ -->
<div id="wfm-nlp-ai-settings" class="wfm-nlp-ai-pane wfm-nlp-ai-settings-pane" style="display:none;">
<div class="wfm-nlp-ai-sec">
<div class="wfm-nlp-ai-sec-title">バックエンド</div>
<div class="wfm-nlp-ai-radio-row">
<label class="wfm-nlp-ai-radio"><input type="radio" name="wfm-nlp-ai-backend" value="ollama"> Ollama</label>
<label class="wfm-nlp-ai-radio"><input type="radio" name="wfm-nlp-ai-backend" value="lmstudio"> LM Studio</label>
</div>
</div>
<div class="wfm-nlp-ai-sec">
<div class="wfm-nlp-ai-sec-title">接続設定</div>
<input type="text" id="wfm-nlp-ai-url" class="wfm-nlp-ai-input" placeholder="http://localhost:11434">
<div class="wfm-nlp-ai-row">
<button id="wfm-nlp-ai-test" class="wfm-nlp-ai-btn">接続テスト</button>
<span id="wfm-nlp-ai-test-result" class="wfm-nlp-ai-status"></span>
</div>
</div>
<div class="wfm-nlp-ai-sec">
<div class="wfm-nlp-ai-sec-title">モデル選択</div>
<div class="wfm-nlp-ai-row">
<select id="wfm-nlp-ai-model" class="wfm-nlp-ai-sel" style="flex:1;">
<option value="">-- モデルを選択 --</option>
</select>
<button id="wfm-nlp-ai-model-refresh" class="wfm-nlp-ai-btn">↻</button>
</div>
</div>
<div class="wfm-nlp-ai-sec">
<div class="wfm-nlp-ai-sec-title">Free 言語設定</div>
<div class="wfm-nlp-ai-row">
<span class="wfm-nlp-ai-lbl">入力</span>
<input type="text" id="wfm-nlp-ai-free-src" class="wfm-nlp-ai-input" placeholder="例: French" style="flex:1;">
</div>
<div class="wfm-nlp-ai-row">
<span class="wfm-nlp-ai-lbl">翻訳</span>
<input type="text" id="wfm-nlp-ai-free-dst" class="wfm-nlp-ai-input" placeholder="例: German" style="flex:1;">
</div>
</div>
<div class="wfm-nlp-ai-sec">
<button id="wfm-nlp-ai-save" class="wfm-nlp-ai-btn wfm-nlp-ai-btn-primary" style="width:100%;">設定を保存</button>
</div>
</div>
</div>
`;
setupAiHandlers(container);
}
renderAiSubContent();
};
const renderAiSubContent = () => {
if (!panelEl) return;
const panes = { "ai-translate": "wfm-nlp-ai-translate", "ai-vlm": "wfm-nlp-ai-vlm", "ai-settings": "wfm-nlp-ai-settings" };
for (const [key, id] of Object.entries(panes)) {
const el = panelEl.querySelector(`#${id}`);
if (el) el.style.display = state.aiSubTab === key ? "flex" : "none";
}
};
const setupAiHandlers = (container) => {
const cfg = loadAiCfg();
// Restore settings
const backendRadios = container.querySelectorAll("input[name='wfm-nlp-ai-backend']");
backendRadios.forEach(r => { if (r.value === (cfg.backend || "ollama")) r.checked = true; });
const urlInput = container.querySelector("#wfm-nlp-ai-url");
if (urlInput && cfg.backendUrl) urlInput.value = cfg.backendUrl;
else if (urlInput) urlInput.value = "http://localhost:11434";
const freeSrcInput = container.querySelector("#wfm-nlp-ai-free-src");
const freeDstInput = container.querySelector("#wfm-nlp-ai-free-dst");
if (freeSrcInput && cfg.freeSrcLang) freeSrcInput.value = cfg.freeSrcLang;
if (freeDstInput && cfg.freeDstLang) freeDstInput.value = cfg.freeDstLang;
const srcSel = container.querySelector("#wfm-nlp-ai-src");
const dstSel = container.querySelector("#wfm-nlp-ai-dst");
if (srcSel && cfg.srcLang) srcSel.value = cfg.srcLang;
if (dstSel && cfg.dstLang) dstSel.value = cfg.dstLang;
// Swap
container.querySelector("#wfm-nlp-ai-swap")?.addEventListener("click", () => {
const tmp = srcSel.value; srcSel.value = dstSel.value; dstSel.value = tmp;
const inputEl = container.querySelector("#wfm-nlp-ai-input");
const outputEl = container.querySelector("#wfm-nlp-ai-output");
const tmpTxt = inputEl.value; inputEl.value = outputEl.value; outputEl.value = tmpTxt;
saveAiCfg({ srcLang: srcSel.value, dstLang: dstSel.value });
});
srcSel?.addEventListener("change", () => saveAiCfg({ srcLang: srcSel.value }));
dstSel?.addEventListener("change", () => saveAiCfg({ dstLang: dstSel.value }));
// Translate
container.querySelector("#wfm-nlp-ai-trans-btn")?.addEventListener("click", async () => {
const text = container.querySelector("#wfm-nlp-ai-input")?.value?.trim();
if (!text) { showToast("テキストを入力してください", "error"); return; }
const c = loadAiCfg();
const backend = c.backend || "ollama";
const url = c.backendUrl || (backend === "ollama" ? "http://localhost:11434" : "http://localhost:1234");
const model = c.model;
if (!isValidAiUrl(url)) { showToast("URLは http:// または https:// で始まる必要があります", "error"); return; }
if (!model) { showToast("設定タブでモデルを選択してください", "error"); return; }
const srcLang = srcSel?.value || "ja";
const dstLang = dstSel?.value || "en";
const srcName = srcLang === "free" ? (c.freeSrcLang || "Auto") : AI_LANG_NAMES[srcLang];
const dstName = dstLang === "free" ? (c.freeDstLang || "English") : AI_LANG_NAMES[dstLang];
const fromPart = srcLang === "free" ? "" : `from ${srcName} `;
const prompt = `Translate the following text ${fromPart}to ${dstName}. Output only the translated text, nothing else.\n\n${text}`;
const transBtn = container.querySelector("#wfm-nlp-ai-trans-btn");
const statusEl = container.querySelector("#wfm-nlp-ai-status");
const outputEl = container.querySelector("#wfm-nlp-ai-output");
transBtn.disabled = true;
statusEl.textContent = "翻訳中...";
statusEl.className = "wfm-nlp-ai-status wfm-nlp-ai-working";
outputEl.value = "";
try {
const result = await aiCallLLM(url, backend, model, prompt);
outputEl.value = result.trim();
statusEl.textContent = "完了";
statusEl.className = "wfm-nlp-ai-status wfm-nlp-ai-ok";
} catch (err) {
statusEl.textContent = `エラー: ${err.message}`;
statusEl.className = "wfm-nlp-ai-status wfm-nlp-ai-err";
} finally {
transBtn.disabled = false;
}
});
// Copy
container.querySelector("#wfm-nlp-ai-copy-btn")?.addEventListener("click", () => {
const text = container.querySelector("#wfm-nlp-ai-output")?.value;
if (!text) { showToast("コピーするテキストがありません", "error"); return; }
navigator.clipboard.writeText(text).then(() => showToast("コピーしました", "success"));
});
// Model refresh helper
const refreshModels = async () => {
const c = loadAiCfg();
const backend = container.querySelector("input[name='wfm-nlp-ai-backend']:checked")?.value || "ollama";
const url = container.querySelector("#wfm-nlp-ai-url")?.value?.trim() || "";
const modelSel = container.querySelector("#wfm-nlp-ai-model");
try {
const models = await aiFetchModels(url, backend);
modelSel.innerHTML = '<option value="">-- モデルを選択 --</option>';
models.forEach(name => {
const opt = document.createElement("option");
opt.value = name; opt.textContent = name;
if (name === c.model) opt.selected = true;
modelSel.appendChild(opt);
});
if (!models.length) showToast("モデルが見つかりません", "error");
} catch (err) {
showToast("モデル取得失敗: " + err.message, "error");
}
};
// Connection test
container.querySelector("#wfm-nlp-ai-test")?.addEventListener("click", async () => {
const testBtn = container.querySelector("#wfm-nlp-ai-test");
const resultEl = container.querySelector("#wfm-nlp-ai-test-result");
const backend = container.querySelector("input[name='wfm-nlp-ai-backend']:checked")?.value || "ollama";
const url = container.querySelector("#wfm-nlp-ai-url")?.value?.trim() || "";
if (!isValidAiUrl(url)) {
resultEl.textContent = "http:// または https:// で始まるURLを入力してください";
resultEl.className = "wfm-nlp-ai-status wfm-nlp-ai-err";
return;
}
testBtn.disabled = true;
resultEl.textContent = "接続中...";
resultEl.className = "wfm-nlp-ai-status wfm-nlp-ai-working";
try {
const models = await aiFetchModels(url, backend);
resultEl.textContent = `OK (${models.length} モデル)`;
resultEl.className = "wfm-nlp-ai-status wfm-nlp-ai-ok";
await refreshModels();
} catch (err) {
resultEl.textContent = `失敗: ${err.message}`;
resultEl.className = "wfm-nlp-ai-status wfm-nlp-ai-err";
} finally {
testBtn.disabled = false;
}
});
// Model refresh button
container.querySelector("#wfm-nlp-ai-model-refresh")?.addEventListener("click", () => refreshModels());
// Save settings
container.querySelector("#wfm-nlp-ai-save")?.addEventListener("click", () => {
const backend = container.querySelector("input[name='wfm-nlp-ai-backend']:checked")?.value || "ollama";
const url = container.querySelector("#wfm-nlp-ai-url")?.value?.trim() || "";
const model = container.querySelector("#wfm-nlp-ai-model")?.value || "";
const freeSrcLang = container.querySelector("#wfm-nlp-ai-free-src")?.value?.trim() || "";
const freeDstLang = container.querySelector("#wfm-nlp-ai-free-dst")?.value?.trim() || "";
if (url && !isValidAiUrl(url)) {
showToast("URLは http:// または https:// で始まる必要があります", "error");
return;
}
saveAiCfg({ backend, backendUrl: url, model, freeSrcLang, freeDstLang });
showToast("設定を保存しました", "success");
});
// Auto-load models if settings exist
if (cfg.backendUrl && cfg.backend) refreshModels().catch(() => {});
// ---- VLM handlers ----
let vlmImage = null; // { base64, mimeType }
const vlmDrop = container.querySelector("#wfm-nlp-ai-vlm-drop");
const vlmPreview = container.querySelector("#wfm-nlp-ai-vlm-preview");
const vlmLabel = container.querySelector("#wfm-nlp-ai-vlm-label");
const vlmFile = container.querySelector("#wfm-nlp-ai-vlm-file");
const vlmRunBtn = container.querySelector("#wfm-nlp-ai-vlm-run");
const vlmStatus = container.querySelector("#wfm-nlp-ai-vlm-status");
const vlmResult = container.querySelector("#wfm-nlp-ai-vlm-result");
const vlmCopy = container.querySelector("#wfm-nlp-ai-vlm-copy");
const loadVlmImage = async (file) => {
if (!file || !file.type.startsWith("image/")) return;
const data = await aiFileToBase64(file);
vlmImage = data;
vlmPreview.src = `data:${data.mimeType};base64,${data.base64}`;
vlmPreview.style.display = "block";
vlmLabel.style.display = "none";
};
vlmDrop?.addEventListener("click", () => vlmFile?.click());
vlmFile?.addEventListener("change", e => { if (e.target.files[0]) loadVlmImage(e.target.files[0]); });
vlmDrop?.addEventListener("dragover", e => { e.preventDefault(); vlmDrop.classList.add("drag-over"); });
vlmDrop?.addEventListener("dragleave", () => vlmDrop.classList.remove("drag-over"));
vlmDrop?.addEventListener("drop", e => {
e.preventDefault();
vlmDrop.classList.remove("drag-over");
const file = e.dataTransfer.files[0];
if (file) loadVlmImage(file);
});
const VLM_PROMPTS = {
describe: "Describe this image in detail.",
prompt: "Create a detailed Stable Diffusion image generation prompt based on this image. Output only the prompt text, nothing else.",
};
vlmRunBtn?.addEventListener("click", async () => {
if (!vlmImage) { showToast("画像をドロップしてください", "error"); return; }
const c = loadAiCfg();
const backend = c.backend || "ollama";
const url = c.backendUrl || (backend === "ollama" ? "http://localhost:11434" : "http://localhost:1234");
const model = c.model;
if (!isValidAiUrl(url)) { showToast("URLは http:// または https:// で始まる必要があります", "error"); return; }
if (!model) { showToast("設定タブでモデルを選択してください", "error"); return; }
const task = container.querySelector("#wfm-nlp-ai-vlm-task")?.value || "describe";
vlmRunBtn.disabled = true;
vlmStatus.textContent = "実行中...";
vlmStatus.className = "wfm-nlp-ai-status wfm-nlp-ai-working";
vlmResult.value = "";
try {
const result = await aiCallVLM(url, backend, model, VLM_PROMPTS[task], vlmImage.base64, vlmImage.mimeType);
vlmResult.value = result.trim();
vlmStatus.textContent = "完了";
vlmStatus.className = "wfm-nlp-ai-status wfm-nlp-ai-ok";
} catch (err) {
vlmStatus.textContent = `エラー: ${err.message}`;
vlmStatus.className = "wfm-nlp-ai-status wfm-nlp-ai-err";
} finally {
vlmRunBtn.disabled = false;
}
});
vlmCopy?.addEventListener("click", () => {
const text = vlmResult?.value;
if (!text) { showToast("コピーするテキストがありません", "error"); return; }
navigator.clipboard.writeText(text).then(() => showToast("コピーしました", "success"));
});
};
// ============================================
// Save selected nodes as Node Set (context menu)
// ============================================
@@ -3371,6 +3817,192 @@ const injectStyles = () => {
color: var(--descrip-text, #aaa);
}
.wfm-nlp-theme-reset-btn:hover { color: var(--input-text, #ddd); }
/* AI Tab */
.wfm-nlp-ai-layout {
display: flex;
flex-direction: column;
height: 100%;
overflow: hidden;
}
.wfm-nlp-ai-pane {
display: flex;
flex-direction: column;
flex: 1;
overflow: hidden;
gap: 6px;
padding: 8px;
}
.wfm-nlp-ai-settings-pane {
overflow-y: auto;
}
.wfm-nlp-ai-lang-row {
display: flex;
align-items: center;
gap: 4px;
flex-shrink: 0;
}
.wfm-nlp-ai-sel {
flex: 1;
padding: 4px 6px;
background: var(--comfy-input-bg, #2a2a2a);
border: 1px solid var(--border-color, #4e4e4e);
border-radius: 3px;
color: var(--input-text, #ddd);
font-size: 11px;
outline: none;
}
.wfm-nlp-ai-swap {
flex-shrink: 0;
padding: 4px 6px;
font-size: 14px;
}
.wfm-nlp-ai-textarea {
flex: 1;
min-height: 80px;
padding: 6px 8px;
background: var(--comfy-input-bg, #2a2a2a);
border: 1px solid var(--border-color, #4e4e4e);
border-radius: 3px;
color: var(--input-text, #ddd);
font-size: 11px;
font-family: inherit;
resize: none;
outline: none;
line-height: 1.5;
box-sizing: border-box;
}
.wfm-nlp-ai-textarea:focus {
border-color: var(--p-button-background, #4a9eff);
}
.wfm-nlp-ai-output {
background: var(--comfy-menu-bg, #1e1e1e);
color: var(--descrip-text, #aaa);
}
.wfm-nlp-ai-output:focus { border-color: var(--border-color, #4e4e4e); }
.wfm-nlp-ai-actions {
display: flex;
align-items: center;
gap: 6px;
flex-shrink: 0;
}
.wfm-nlp-ai-status {
font-size: 10px;
flex: 1;
overflow: hidden;
text-overflow: ellipsis;
white-space: nowrap;
}
.wfm-nlp-ai-working { color: var(--wfm-warning, #ffa502); }
.wfm-nlp-ai-ok { color: #2ed573; }
.wfm-nlp-ai-err { color: #ff4757; }
.wfm-nlp-ai-btn {
padding: 4px 10px;
font-size: 11px;
font-weight: 600;
cursor: pointer;
border: 1px solid var(--border-color, #555);
border-radius: 3px;
background: none;
color: var(--descrip-text, #aaa);
transition: background 0.15s, color 0.15s;
white-space: nowrap;
}
.wfm-nlp-ai-btn:hover {
background: rgba(74,158,255,0.2);
color: #4a9eff;
border-color: #4a9eff;
}
.wfm-nlp-ai-btn:disabled { opacity: 0.4; cursor: not-allowed; }
.wfm-nlp-ai-btn-primary {
background: var(--p-button-background, #4a9eff);
color: #fff;
border-color: var(--p-button-background, #4a9eff);
}
.wfm-nlp-ai-btn-primary:hover { background: #3a8eef; border-color: #3a8eef; color: #fff; }
.wfm-nlp-ai-coming {
display: flex;
flex: 1;
align-items: center;
justify-content: center;
font-size: 11px;
color: var(--descrip-text, #888);
text-align: center;
padding: 16px;
}
.wfm-nlp-ai-sec {
display: flex;
flex-direction: column;
gap: 5px;
padding: 8px 0;
border-bottom: 1px solid var(--border-color, #3a3a3a);
}
.wfm-nlp-ai-sec:last-child { border-bottom: none; }
.wfm-nlp-ai-sec-title {
font-size: 9px;
font-weight: 700;
color: var(--descrip-text, #888);
text-transform: uppercase;
letter-spacing: 0.05em;
}
.wfm-nlp-ai-radio-row {
display: flex;
gap: 12px;
}
.wfm-nlp-ai-radio {
display: flex;
align-items: center;
gap: 4px;
font-size: 11px;
color: var(--input-text, #ddd);
cursor: pointer;
}
.wfm-nlp-ai-input {
padding: 5px 8px;
background: var(--comfy-input-bg, #2a2a2a);
border: 1px solid var(--border-color, #4e4e4e);
border-radius: 3px;
color: var(--input-text, #ddd);
font-size: 11px;
outline: none;
box-sizing: border-box;
}
.wfm-nlp-ai-input:focus { border-color: var(--p-button-background, #4a9eff); }
.wfm-nlp-ai-row {
display: flex;
align-items: center;
gap: 6px;
}
.wfm-nlp-ai-lbl {
font-size: 10px;
color: var(--descrip-text, #888);
white-space: nowrap;
width: 28px;
flex-shrink: 0;
}
/* VLM drop zone */
.wfm-nlp-ai-vlm-drop {
height: 110px;
flex-shrink: 0;
display: flex;
align-items: center;
justify-content: center;
border: 2px dashed var(--border-color, #4e4e4e);
border-radius: 6px;
cursor: pointer;
overflow: hidden;
transition: border-color 0.15s, background 0.15s;
position: relative;
}
.wfm-nlp-ai-vlm-drop:hover,
.wfm-nlp-ai-vlm-drop.drag-over {
border-color: var(--p-button-background, #4a9eff);
background: rgba(74,158,255,0.04);
}
.wfm-nlp-ai-vlm-label {
font-size: 11px;
color: var(--descrip-text, #999);
pointer-events: none;
}
`;
document.head.appendChild(style);
};