Inserting took a round per LoRA. The picker now gathers them: click to add,
click again to drop, the number on a card is the order they go in. They go in
as a chain of ComfyUI's loaders, or through one Power Lora Loader or Easy-Use
stack where installed, all or nothing and as one undo step. Third-party nodes
change height just after they appear, so they are placed, and the step taken,
once they have settled. New nodes stand in one column and the view goes to
them when a crowded canvas leaves them out of sight.
Fixes the CLIP line going missing for a LoRA inserted before a sampler with a
LoRA already there: that LoRA counted as a prompt node, so there seemed to be
two CLIP sources.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Three fixes from the user's use of the current-node panel:
- ⇄ Compare on a saved set listed the whole workflow's values. It now
compares that node alone: a copy of the node holding the set's values,
nothing wired, against the canvas, under the node's id so the two pair
(a set's workflow numbered otherwise, with two prompt nodes, paired
neither). compareParams takes `only` for this; the comparison window
takes `nodeId` and leaves out the structure badge. Every set can now be
compared; the unused "could not read the set's workflow" text is gone.
- The Change model picker drew cards of its own: full-size covers and
videos without a still, so most showed blank, and only file names. It
now shows the models page's card face (modelCardFace, split out of
ui_grid.js): the cover thumbnail, a video's still until pointed at, the
base badge, version, readable name and file name; "current" and the
chosen outline stay. Versions are not folded. Its type and base chips
and their texts are gone.
- In the generated-pictures gallery (current node, View all), once
scrolled, "Close gallery" opened the picture scrolled up under it:
Chrome's hit-testing again (lessons.md). Its scroll box and the
picker's card area get clip-path: inset(0).
Checked in an isolated ComfyUI: the prompt node's compare lists only its
text; the picker shows covers and names, selects, replaces; the models
page's cards keep their buttons and open the details; a 13-step scroll
of the gallery leaves every click on the close button. Full suite and
structure check pass.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Opened from the canvas's right-click menu the browser is closed, so the floating button
(topmost on purpose) sat on the picker's head.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A node's menu offers Open in AMB, change model by picture, insert a LoRA before / after,
saved values, the model's pictures and details, save values and save as combo, each where
it applies; the empty canvas's menu opens AMB's pages. Entries can be switched off, moved,
and put in one AMB submenu or right in the menu. The model picker's Esc closes only the
picker, wherever the focus is.
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>
Settings -> Appearance -> Theme (and the ComfyUI setting
Anomalous.ModelBrowser.Theme, which replaces the Abyssal Scarlet switch)
picks Follow ComfyUI (default), Dark, Light or Abyssal Scarlet. Following
ComfyUI watches the dark-theme class ComfyUI sets on <html> for a dark
palette and repaints at once; an older Abyssal switch reads as Abyssal.
The light theme is html.amb-theme-light with its own --amb-* values. Hard
coded colors were turned into tokens whose dark values are the colors they
replace (checked: every stylesheet resolves to the same dark values):
rgba(var(--amb-ink-rgb), a) for tints, status shades, tooltip, float,
dialog, sunken, scrim and note tokens. Older rules and inline styles that
wrote a dark color now write var(--amb-lt-<role>, <that color>); the
--amb-lt-* tokens exist only in the light theme. Inside the plugin's
windows ComfyUI's palette variables (--bg-color, --fg-color ...) follow the
plugin's theme when the two differ. Surfaces over images stay dark, and the
image viewer gets the dark tokens back. The ready banner on a recipe reads
green instead of pink. Stylesheet cache versions are bumped.
Checked on a test ComfyUI in light and dark: home, models, gallery and its
viewer, workflows and a recipe's tabs, combos and a combo, prompts and the
docked drawer, voices, audio library, settings, scan, Model Check, current
node and its model picker, a model's detail with notes, share, save
recipe, update guide, versions, GPT-SoVITS settings and the prompt dialog;
light with a dark ComfyUI, and Abyssal Scarlet.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Current node's "Insert LoRA before / after" refused the most common workflows: a
checkpoint whose CLIP feeds both prompts (one link per output only) and UNet workflows
with their own CLIP loader (MODEL and CLIP had to come from one node).
- graph_splice.js: planLoraInsertion decides the links (after a node: every link of its
MODEL output; before one: only its own MODEL input) and, for LoRAs that train the text
encoder, the CLIP line (same node, a UNet workflow's one CLIP source, or before a
sampler the source its prompts share); spliceLora wires it, all or nothing. The old
analyzeModelChainInsertion / spliceModelChainNode / spliceAfterOutputs are gone.
- api/lora_info.py: GET /anomalous/lora_info reads the LoRA's safetensors header; the
picker asks it on confirm and inserts a model-only loader when there are no
text-encoder weights. The MCP add_lora uses the same helper.
- Insertion messages speak of the MODEL line; the fan-out ones are removed.
- tests/graph_splice.mjs (local) covers checkpoint, UNet + CLIP loader, before a
sampler, and the rollback.
Verified on 8199 through the Current node picker: after a checkpoint feeding two prompts
(full LoRA, both prompts moved) and before a sampler (model-only Flux LoRA).
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Pages made at different times used their own greys (slate here, neutral
there) and accents (sky, violet, indigo), and most ignored the Abyssal
Scarlet theme. About 1,850 literal colours in web/styles and in CSS and
inline styles written from JS now use the --amb-* tokens by what they are
for: surfaces, text (new --amb-text-soft and --amb-text-dim), borders (new
--amb-border-strong), the primary button, and one accent (new --amb-link,
tinted with color-mix). Both themes define the new tokens.
Literal colours stay where the colour is the meaning: status, prompt
roles, voice emotions, canvas node colours, shadows and overlays; theme
override rules are untouched. The share-code dialogs move from inline
styles to .anomalous-share-* classes. Stylesheet versions are bumped.
Checked: text contrast on every rail page, Prompt Studio, Prompt Notes,
Model Sources, settings, model detail and editor, share codes, in both
themes; structure check and JS tests pass.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
ComfyUI takes undo steps on mouse-up and key-up; a drag-and-drop ends in
neither, and writes made in click handlers or after a fetch landed in no
step, so Ctrl+Z could undo the step before instead. canvas_history.js asks
for a step after each write (applied values, drops, created or inserted
nodes, recipes, prompt notes).
A drop's receipt also pops up at the top right with Undo (shared with the
receipt's own button); prompt nodes made by a drop on empty canvas can be
undone there. canvas_undo.js keeps what each canvas activity entry did, in
full, while the page is open; the log offers Undo while nothing changed it
since. Entries that removed nodes or rewired existing ones, seeds, and
choices this computer no longer has are never offered.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A bar over the canvas appears when an opened workflow uses models this
computer does not have: how many, and how many are here under another
name or folder (same hash), with one press to put those in. The doctor
page is redone on the scan page's layout: what needs you first, why in
plain words, and a button per row (put in, use a same-size file, pick
one, look it up on Civitai); models that are fine fold away.
- model_check.js: the check (no DOM, changes nothing) and the fixes,
which call the node's widget hooks so ComfyUI drops its red mark;
the node picker does the same now.
- Opening the doctor no longer rewrites the workflow by itself.
- Removed: the auto-detect switch (nothing read it), the doctor's own
deep hash scan and its routes (the resolver hashes same-size files on
demand; the page points to the scan page), the hash dialog, the old
resolver in hash_resolver.js, the unused pick-for-node path in
ui_detail.js, 45 old strings.
- Node Assistant's diagnoseNode and LoRA insertion moved to
ui_node_assistant.js.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
