From a Bilibili comment (2026-10-13):
- Esc closes the top layer: a dialog or menu (the plugin's alert and confirm
now close on Esc, as OK / Cancel), else the Workflows / Combos workspace,
else the browser. One capture listener decides before the layers act, so a
dialog closing on the same Esc still counts as above. The shortcut and the
Extensions entry toggle the browser.
- A model's file card has Show in folder: POST /anomalous/open_model_folder
(api/model_folder.py) takes type, folder index, subfolder and file name,
never a path, and opens Explorer / Finder with the file selected; a POST,
so local_guard keeps it to this computer. The card moves out of
ui_detail.js into model_location.js.
- A gallery card's right-click menu (gallery_card_menu.js): Insert as a Load
Image node reads the output file in place ("name.png [output]"), and View
Parameters.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Found while recording in English: picture details showed "20 步" and
"定位模型", and the activity log said "Changed 1 things". Picture
details' last fixed Chinese strings (steps, Show model, copied JSON, two
empty notes) move to locales. formatTranslation learns {count|one|other},
and every English "{count} <plural noun>" uses it (49 strings; names like {engine} or {node} are left alone); two
sentences whose verb followed the count are reworded. The voice guides
name the TTS node by its English title, Character Speech (GPT-SoVITS).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The key handler ignored every <input> as a text field, so once a node's
checkbox under All parameters was ticked it kept the focus and the arrows
and A / D did nothing until a click elsewhere. Only text entry (text inputs,
textareas, contenteditable) keeps the keys now. In since 2026-09-04.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
MCP now uses local_guard.is_local (one local check). A backup upload
request that is no upload answers 400 instead of 500. tests/test_local_guard.py.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
With ComfyUI started with --listen, other devices could use most of AMB's
actions: delete and rename models, save and delete workflows and prompts,
start downloads and scans, export a backup of all data, translate with the
user's key, change settings, switch the plugin version. A probe of all
routes as a LAN device found 9 of 112 refusing.
api/local_guard.py is one middleware in front of every /anomalous/ route:
anything but GET answers only this computer unless it is a read sent as POST
(OPEN_POSTS); a GET is open unless it is more than a read (LOCAL_GETS:
backup file, GitHub releases, local folders). Local = loopback peer, no
proxy headers, loopback Host (DNS rebinding is refused too). Refusals are
403 local_only with a bilingual message; GET /anomalous/access lets the page
show a "view only" chip (remote_view.js). AGENTS.md rule 4 now names it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The editor is rebuilt (it was inline styles everywhere): the cover large
with its choices under it (the current one, Civitai's own when the user
replaced it, the newest pictures, upload, the whole gallery), Name, Source
link and Notes with a word each, Reset / Cancel / Save at the foot. Nothing
is written before Save; fields left as they were are not sent. The source
link (asked for in the "not found" list's hint, but nowhere to type it) is
kept in the user layer; update_metadata refuses one that is no http(s)
address. GET /anomalous/model_covers tells the editor Civitai's kept cover.
A model Civitai does not know: its card reads "推断 <base>", its details
open with a note on what was read from the file and a button to add a name
and link (instead of the English placeholder description), and the scan
page says an online scan infers what Civitai does not find.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The scan card opens on two rows of the models' covers, newest first, with an
empty dashed frame for each model not scanned yet (they pulse while a scan
runs): what a scan does, in a picture. The ring, which said the same as the
line under it and the state bar, is gone; narrow, nothing sits alone above
the card any more. The scan summary carries up to 48 covers of scanned models
(components left out) for it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The scan button gets a scan-frame icon (the radar read as a clock). The
models set to never be scanned and the files in other formats are quiet
links under the state chips, so "worth a look" only appears for damaged
files and voice-like models. The scan card stacks the ring above the
rest by the page's own width (docked in the sidebar too), and the More
arrow turns when unfolded.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The scan card answers "what now": a ring of the models found on Civitai,
what is left in one line, the scan button, "pick models to scan" and an
online / offline switch beside them, and what the scan does in one
sentence (Details unfolds the counts); a yellow line when a switch that
changes files is on. Below it the models' state as a bar with a chip per
state and the components' chip, then, only when there is something, what
needs a look (one row each, with its icon), the settings as tiles (the
two that change files folded under More) and the last scan in one line.
Icons are scan_icons.js. The cards, chips and rules the page no longer
draws are gone.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"Pick models to scan" sits beside the scan button; the picks are named
under it and the button scans them, "clear" goes back to everything, so
the all/picked switch is gone. Under the button the page says what this
scan will do, each line with how many of its models are components.
The settings card (ui_scan_settings.js, holding the scan options and the
Civitai key prompt) unfolds in place instead of opening its own page.
The summary counts and lists models in component folders (VAE, text
encoders, CLIP, CLIP Vision, upscalers) apart. The counts at the top and
the not found / not scanned lists leave them out; a card and a list of
their own say that many are not on Civitai and that this is no fault.
The not found list looks up again just the models it shows.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The picker's models folders are sorted by type, each named with where it
is when the folder is not named after its type (Diffusion · unet) or the
type has two; models follow their folder. A row's state, base model and
size sit in fixed columns. Offline, the settings page no longer counts
models last scanned without a connection as "not on Civitai": they wait
for the next online scan.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
"All models" now lists, from the scan summary, how many models a scan
looks up, keeps, leaves for "look up again" and leaves out, following
the offline and fetch-again switches. "Only ones I pick" names the picks
with their size and says when found ones would only be read again.
The picker (ui_scan_picker.js, GET /anomalous/scan_pickable) lists the
.safetensors files a scan reads with the scan page's states, folder,
base model and size, as a list or covers, narrowed by folder, state,
search and picked-only; "pick these" picks what is shown, shift-click a
run. Picks go to the scan as targets. The old inline-styled selector and
its batch_select route are gone; setWidgetValuePath keeps its own file.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- The scan summary marks new models whose safetensors header reads but names no drawing model
kind (a voice model such as F5-TTS) as not_drawing; the scan page asks: don't scan them,
scan them, or see each. The choice lives in <model>.anomalous.json ("scan": "skip" / "scan",
model_identity.scan_choice), saved by POST /anomalous/scan_choice (api/scan_choice.py, this
computer only, at most 2000 models, only readable .safetensors layers).
- "skip": a scan of a whole folder leaves the model out (picked by hand it is still scanned),
the summary counts it apart (excluded) with its own list to change it back, the card and the
details say "不扫描"; the details have the same button.
- The unmatched count warns only for damaged files or lookups still to do; not-found rows say
the fingerprint is kept for repairing workflows.
- model_kind.inspect_file now gives format None when the header cannot be read, as its text said.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A model Civitai has no record of now has its safetensors header checked (model_identity.
safetensors_damage: too short, header longer than the file, not JSON, or a tensor ending past
the file's end; only the header is read). Such files get the unmatched reason "damaged": a red
badge on the card, a line in the details, a warning on the scan page (the summary counts them)
and first place in the unmatched list, with advice to download the model again.
Tests: header cases, a scan telling a damaged file from a whole one; the scan report fixtures
are whole safetensors files now.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
After 90 seconds closed the model grid is released. Reopened onto Current node or Prompts (a node selected on the canvas), nothing redrew it, so pressing Models showed an empty page. Showing the models now redraws an empty grid.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Opening a workflow on the canvas hid the workspace without restoring the page under it, so
opening the browser again showed an empty page. It now only hides the browser; the Workflows
list stays in place.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ComfyUI keeps widget values by the root graph's id; a picture's workflow laid on a
detached graph under the open canvas's id shared and overwrote the canvas's values.
detached_graph.js gives the copy an id of its own; image_keep and recipe_save use it.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Same fixes as feature/next 99576e6, brought into v1.58.0 (the user fixes the
released line directly while it has few users):
- Current node's model picker repaints the chosen card in place instead of
redrawing the grid, which scrolled back to the top.
- The classic combo editor no longer saves when its bilingual tags are shown nor
once per translated tag; one save follows the last translation.
- A long activity before/after pair is cut around its first difference.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- Current node's model picker redrew the whole grid to mark the chosen card, so
choosing one further down scrolled back to the top. The cards are repainted in
place (paintCard) instead.
- The classic combo editor saved when its bilingual tags were shown and again for
each tag's translation as it arrived: a long prompt wrote the combo dozens of
times in a second (34 note_save entries in one user's log). Rendering no longer
saves and the translations share one save half a second after the last. Its
prompt placeholder moves into locales.js (no inline language branch).
- Activity values are capped at 400 characters from the start, so an edit late in
a long prompt logged identical before and after. A long before/after pair is now
cut around its first difference (test included).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Home's feedback band ends with "⭐ Star on GitHub" and Settings -> Help and feedback
has a "Star it on GitHub" row; both open the project page in a new tab
(feedback.js openRepoPage). No pop-up, no reminder and no request is made: the
page opens only when pressed.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A search box above the clips (ui_tts_clip_search.js) finds clips by part of their
line or file name and lists the first 30 with their lines, to hear, use as the main
voice or add as an emotion (the new row gets the clip and its line). The lines come
once per dialog from Anomalous_TTS's GET /anomalous_tts/reference_lines (interface
14, by character name only); with an older node the request fails quietly and the
search covers file names. Picking a clip now fills its line from the same lines,
so the per-clip request is gone. Lines reach the page as text only (textContent).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
With Anomalous_TTS interface 14 (GET /anomalous_tts/reference_text), picking a clip
that is not yet in use fills in the line the node finds for it (.txt / .lab /
annotation list); an older node gives no answer and the box stays blank as before.
The answer is used only while the box still holds that clip and is still blank, and
is dropped with the dialog. A blank line box shows the line the node uses for its
clip as greyed placeholder, so the settings are not changed by opening the dialog.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The audio boxes are a native datalist, which lists only files whose names contain
the box's text, so a filled box showed one or two clips. Pressing a box now empties
it to list all of them (the file shows as the placeholder) and puts the file back
when nothing is picked; Backspace or Delete really clears it.
Picking another clip kept the old clip's line next to it. The line box now follows:
the line it had for the first clip, the line the node already reads for a clip in
use, or blank, which makes the node read the clip's own .txt / .lab / list line.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- CHANGELOG: v1.59.0 Beta and older taken as they are on next; model-import's own
sections under a new v1.60.0 Beta heading (model import, Tidy, base-model filter,
version labels, settings tabs; the scanner's wider offline base-model guess moves
under the base-model filter). Stale copies of entries the v1.58.0 release reworded
are dropped.
- README badge v1.60.0 Beta.
- What's new guide (new id 2026-10-model-import-and-tidy): import, Tidy, base-model
filter with version labels, settings tabs.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- CHANGELOG: ui-shell's v1.58.0 Beta block kept as it is there; next's own sections
move to a new v1.59.0 Beta heading (model downloads, backup, share codes, recipe
packages, node combos, MCP, light theme, opening by node, header search, LoRA
insertion, DeepL key, tests; "Ctrl+Z after a scan" under Fixes).
- README badge v1.59.0 Beta.
- What's new guide (new id 2026-10-downloads-and-backup): downloads from Model Check,
backup and share codes, node combos, light theme, MCP.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
- CHANGELOG: Unreleased becomes v1.58.0 Beta (2026-10-09), its entries grouped by
subject (layout, keeping results, prompts and Current node, Model Check, scanning,
deleting, memory, activity log, voices, fixes); no entry dropped. Stale wording
fixed: the rail's real order (no toolbox), no material workspace, no help page,
Activity canvas entries do have Undo, combos instead of prompt notes.
- README: changelog badge v1.58.0 Beta.
- What's new guide: the five steps are the release's main changes (rail and Home,
☆ keep and combos, Prompt Studio, Model Check, voices); the model-types,
activity and memory steps are gone (Activity is named in the layout step).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The voices page keeps the node's status for a minute. On a fresh install
the first status said the storage place (models/gpt_sovits) was missing,
so "Import character" refused with "存放位置不能写入" until the cached
answer expired, although the folder existed by then. Before refusing, the
import asks for the status once more. (Anomalous_TTS now also creates the
folder when it starts.)
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
