locales/zh/nodeDefs.json gives every public node a Chinese name,
description and input and output names, which ComfyUI shows when its
language is set to Chinese. Cards and help pages stay English.
tests/test_locales.py keeps the entries matched to the node API, and the
preflight lets locales/ ship.
Watch the picture form one sampling step at a time and stop a run that is
going wrong. Step Preview needs no wires and shows whichever sampler is
working, with Stop and Stop all. Save Image and Save Video get a steps
switch, off by default, that shows the steps where the saved picture goes,
with a Stop button.
A queued workflow that shows its steps asks ComfyUI for the auto preview
method for that run, only when no method was chosen in the frontend or on
the command line.
The browser downloads a small copy of the LoRA's first picture from
Civitai's picture server (PG-13 or milder unless the gear menu's Civitai
picture option says any), and the server saves it beside the LoRA as
<model>.preview.jpg, never replacing a picture. The LoRA Previews add-on
is no longer needed, so its hooks and install hint are gone.
Draw boxes on a canvas and say what goes in each one: a thing, or words to
write in the picture. Wire elements to MOSS-Image Layout Prompt and the
picture puts each thing where its box is.
It gives what ComfyUI's own Create Bounding Boxes gives (preview, bboxes,
elements; same types, same order, same values from the same boxes), so it
can take that node's place, and its canvas also draws in the classic node
look. The boxes are kept as parts of the canvas in a hidden socketless
string, so a wired size never moves them.
The Registry shows each version's notes, made from CHANGELOG.md when the
version is published, and the full list stays in the repository; nothing
in the pack reads the file. The nodes are the same as in 2.12.1.
Click a thing in your picture on Mask by Touch, say what to change, and
Qwen repaints only that part. It is the workflow of its page, with the
Seed on fixed as every example here has it.
The workflow carries a note above its Workflow Note that links to the
video channel. The example check wanted every node but the Workflow Note
inside a numbered group, so that note counted as a stray node. A Callout
in the Workflow Note's own column now belongs to the note. A Callout
anywhere else outside the groups, and any other node in that column, is
still refused.
A changelog entry that opens with a node's name and a colon, as in
"Callout: links", came out as "Callout : links" in the notes sent to the
Registry: the mark after the name was taken off and its space stayed.
The Registry has shown no notes for any version since 1.2.0, when
publishing moved to the publish action: it sends none. comfy-cli takes
them from COMFY_NODE_CHANGELOG, so the publish workflow now puts this
version's CHANGELOG entries there before it publishes, one short line
each: the entry's bold opening, and for a new node or example the sentence
that says what it does.
scripts/changelog_notes.py makes the notes and prints them for any
version. The release check fails when the pyproject version has no
entries in CHANGELOG.md, so a release cannot go out blank.
A ComfyUI update can break a node without a line of the pack changing, and
until now nothing looked: CI installs no ComfyUI. A nightly workflow now
installs ComfyUI's newest release and its development head for the CPU and
runs three checks that need no model:
- tests/test_comfy_core_contract.py reads the pack's source for everything
it takes from ComfyUI (modules, functions, ComfyUI's own nodes it calls
and the inputs it passes them) and looks each one up in the real thing.
- scripts/compat_boot.py asks a running ComfyUI which nodes it offers:
every public node of the pack, and every node and required input the
example workflows use.
- scripts/dev/face_smoke.mjs puts every node on a graph in headless
Chrome, in both node views, and fails when a face does not come up or
something throws.
The full Python suite runs there too. A failure on the release opens an
issue; the development head only after two nights in a row.
A new node in the Mask group. The picture is on the node: moving over it
lights up what a click would take and names it, a click picks it, and two
arrows swap the pick for the next thing at that spot. Subject and
Background take the picture's main subject, or everything else, in one
click. Pick | Draw switches to a brush for an area painted by hand, + and -
add or take away, Undo takes a pick back, and every pick has a chip under
the picture. Fine edges follows hair and fur strand by strand, takes out
background seen between the strands, and gives a cut-out the thing's own
colour. The eye beside Undo and Clear shows the result as a cut-out or as
the mask. Outputs: the mask, the cut-out and the names of what was picked.
The search is ComfyUI's own SAM 3. Subject, Background and Fine edges use
ComfyUI's own background-removal model (ComfyUI 0.21 or newer). The pack
downloads nothing.
With it: a widget card can name its choices with a function and keeps
showing a value its list does not offer, the help page, an example
workflow with its thumbnail, the README section and the CHANGELOG entry.
The wheel did nothing over a preview picture, the text of a Callout or the
padding of a card, and the middle button did not pan there. Those parts of a
panel let the mouse through, so in the classic renderer the pointer lands on
the frontend's .dom-widget wrapper, which takes the mouse and hands nothing
on. The pack looked for its panel between the pointer and the wrapper and
found none. A pointer on the wrapper now counts as over the panel inside it.
scripts/dev/wheel_sweep.mjs turns the wheel at every point of every node and
reports each spot where the graph does not zoom. In the classic renderer 33
of the 41 nodes had such spots; none has one now. Nodes 2.0 had none.
Two Image nodes that take a picture past the size a model can redraw in
one go. Tiled Upscale sets the finished size in megapixels and cuts the
picture into tiles; Tiled Upscale Stitch blends the joins, keeps each
tile's colors on the picture's own and fits the result to the size asked
for. Any model can sit between the two.
Adds the tile planner with its tests, the two widget cards, help pages,
README sections, a changelog entry, the API snapshot and a new example,
Qwen Image 2.1 Upscale + Restore. The README's example count now matches
the folder.
The 2.8.0 upload was refused with "description is too long": naming
Image Folder and Callout took the description to 1024 bytes and the
Registry takes 1000. It is 989 now, and release_preflight.py fails on a
description over the limit, so this is caught before a version lands.
The Registry's scan also warned about two statements on one line in
tests/test_image_folder.py and says that becomes an error. They are two
lines now.
A new Utility node for explaining a workflow on the canvas. The text grows
to the largest size that fits the note, so it reads without zooming in, and
each point gets a thin teal line beside it.
An arrow emoji in the text (or the arrow row under the editor) becomes a
teal arrow in the line. Click a node while editing, then press an arrow, and
the arrow is linked to that node: clicking it later brings the node into
view, the way Workflow Switches does. The link is kept in the text as #id,
so editing the words never moves it.
The node has one hidden text input and no outputs, so it never runs.
A loader for many pictures. The card chooses the folder inside ComfyUI's
input or output folder, and a thumbnail gallery under it ticks the pictures
to use. All in one run sends every picked picture through as a list; one
per run loads one picture each run and moves on when a run is queued. It
gives image, mask, filename, index and count. Pictures dropped on the node
or added with Add are uploaded into the input folder.
Folder names and picked names are attacker-controlled: a folder is only
read as a path below the input or output folder, links that lead out are
refused, and picked names are compared with what the folder holds, never
opened.
Registers the node, gives it a widget card and the shared preview panel
with a FIND tool that runs the node alone, a readout of how many things
matched and how sure SAM 3 was, and the stop message on the node's own
face. A stopped run shows the plain picture, not the last find. Each name
asks SAM 3 for up to 16 matches, and Sureness starts at 0.7.
The pack's server still never contacts a host. The info card's button has the
browser ask civitai.com about one file by its SHA256, then the server saves
the answer beside the LoRA as <model>.civitai.info after checking it names the
same file (size, shape and hash). The old Python HTTP call stays gone.
release_preflight now allows a raw fetch() only in js/cache_guard and
js/lora_loader. SECURITY.md, AGENTS.md, the README and the LoRA Loader help
page describe the change.
Every image and video loader in the seven examples is saved with no file
picked, in both saved widget copies. Remove the three sample pictures the
new examples added, put the Registry archive budget back to 12 MB, and
update the README examples section and the CHANGELOG.
Replace it with the version that pads with Image Crop + Rotate + Pad,
with its sample picture and a new thumbnail. Point the README's Load
Image + Pad section at Klein 9B Outpaint, and update the example table,
the outpaint caption, the Krea 2 Outpaint Model Patch help page and the
CHANGELOG. Raise the Registry archive budget to 18 MB.
Keep Krea 2 Outpaint, Klein 9B Outpaint, LTX 2.3 Video Outpaint,
Qwen Image 2.1 Edit + Realign and Simple Video Watermark Remover, and add
Krea 2 Inpaint Masked and Krea 2 Rotate + Outpaint with their sample
pictures. Remove the other sixteen examples and the sample picture only
they used.
Update the README example table and links, the Realign to Source help
page, a test comment, the CHANGELOG and the pyproject description, and
raise the Registry archive budget to 13 MB.
- Qwen Image 2.1 Edit + Realign: type a short edit and Qwen3-VL 8B, the
text encoder the edit already loads, writes the full instruction. The
consistency LoRA sits in a LoRA Loader row, switched off.
- LTX 2.3 Video Outpaint: the distilled LoRA and the outpaint IC-LoRA load
in one LoRA Loader instead of two core loaders. The workflow checks now
refuse core LoRA loaders in examples.
- Realign to Source: description, tooltips and help page rewritten in
plain words, with the technical detail at the end of the help page.
- Settings menus: in a short window the rows no longer squeeze together
and overlap; the menu scrolls instead.
- AGENTS.md: text people read starts with the plainest version.
Qwen Image 2.1 draws broad edits (watercolor, anime, oil) a few percent
taller than the source, up to about 12%, differently for every seed, and
snapping sizes does not change it. Realign to Source measures that zoom
and shift against the source and warps the edit back onto the source's
frame, at the source's size. empty_mask marks the strip the model pushed
out of view; report gives the measured zoom, shift and worst corner, or
why a frame was left as it is. The display name carries EXPERIMENTAL.
Promoted from the lab node. The measurement is unchanged (the same
matrices on 166 real Qwen 2.1 renders). The warp now samples the edit
with its edge pixels extended for every fill, so the gray and source
fills no longer draw a dark line beside the strip.
New example: Qwen Image 2.1 Edit + Realign, the Qwen 2.1 Edit graph with
the realign step after decode, its report, and before and after compares.
The workflow contract now fails an example whose named widget values
disagree with the values it loads, whose id is not a random UUID, whose
saved zoom is too low to draw widget text, whose download info names a
file its loader does not select, or whose save node writes into a
folder.
The five CDP scripts looked for ComfyUI at http://127.0.0.1:8188/ only;
COMFY_URL now overrides it. cdp_nav_debug.mjs says so when no ComfyUI
tab is open instead of crashing, and cdp_drag.mjs gives up on a request
after 25 s like cdp.mjs rather than waiting forever. The live-testing
notes mention COMFY_URL, give the full path of the screenshot pairs,
and say that only CDP_RELOAD=1 reloads into a fresh tab.
Check 4 tried .comfyignore on 22 hand-picked paths with its own
gitignore matcher. With git it now lists what comfy-cli packs - tracked
files minus the ones .comfyignore matches - and fails when anything
outside the runtime allowlist ships, when .comfyignore drops a runtime
file, when an allowlist entry, js/docs/ or example_workflows/inputs/
ships empty, or when the archive grows past 12 MB (201 files and 7.1 MB
today). A copy without its own git repository keeps the sample-path
check.
The transform output check now pins the first four outputs instead of
the whole tuple: saved workflows link outputs by slot index, so those
can never move, but a fifth output appended later is compatible. Two
new checks hold today and keep holding: every public display name ends
with the pack suffix, and every public node has js/docs/<key>.md. The
docstring lists the checks in order and describes check 4 as the code
enforces it, and the never-filled warnings list is gone.
The compile check walked every .py under the checkout, gitignored
_scratch/ ports and nested checkouts included, and py_compile wrote a
__pycache__ folder next to each file it checked. It now compiles in
memory. It and the stray-mapping scan (and its test) share one file
list: tracked plus untracked-but-not-ignored files from git, or, when
git cannot answer for the tree (an installed copy), a walk that skips
dot-folders, caches and _scratch/.
The README's images and GIFs were 7.3 MB of a 14.4 MB archive, and only
GitHub shows them; nothing in the pack loads assets/. The editor
swap-file patterns and the one for a local copy of the brand skill
matched no tracked file, and comfy-cli packs tracked files only, so
they are gone.
todo2 was a finished checklist that rode along with the 2.1.0 release
commit. The ignore files listed personal note names one by one, including
several that no longer exist; local notes now follow one rule instead.
shields.io's dynamic TOML badge reads the version straight out of
pyproject.toml on main at view time, so the badge cannot go stale by
construction - no third version string to bump. Preflight check 3 flips
from comparing a hardcoded number to guarding the mechanism: the dynamic
badge must be present and a hardcoded release-X.Y.Z badge fails the
check. AGENTS.md's release step 1 goes back to two version strings.
The README badge advertised 1.0.0 through two releases, and the registry
side had two silent failure modes nobody was watching:
- release_preflight.py check 3: the README release badge must name the
pyproject version, so the three places a version lives (pyproject,
AUSBOSS_JS_VERSION, badge) can never disagree again. Badge bumped to
1.2.0; README also names the real ComfyUI-floor key (requires-comfyui).
- AGENTS.md release step 4: the push-triggered publish run has failed
before (1.2.0's run died; the version only shipped via a manual
dispatch) - a red run is an unpublished release until re-run.
- AGENTS.md release step 5: verify the version AND its status on the
registry. Every version this pack has published sits in
NodeVersionStatusFlagged - the automated scan holding it for human
review - and flagged versions are invisible in Manager's Select
Version picker and set no last-update, which is exactly the empty
picker on the live install. Ask the Comfy team for review; do not
re-publish.
- New node: Save Image - PNG or lossless JPEG XL (optional
pillow-jxl-plugin, the pack's new jxl extra), workflow embedding on or
off (honoring --disable-metadata), an exact_name mode that saves under
exactly that filename with no counter suffix, overwrite/skip/error
collision policy, output_dir up to absolute dataset paths, a caption
.txt sidecar sharing the basename, file_path and IMAGE passthrough
outputs, and always-re-run semantics so a deleted file re-saves.
- Image Resize now only invents pixels on an explicit width+height pad
request: scale-derived modes resolve divisible_by snaps with a
sub-half-step resize instead of padding a sliver; the tour workflow
switched to an explicit 512x512 letterbox so its mask lane demonstrates
real bars.
- Registry-facing metadata: the description now names every node family
(Manager search matches against it) and the keyword list grew to match.
- Release 1.2.0: version bump, frontend version constant synced,
changelog dated, and a publish workflow (Comfy-Org/publish-node-action)
that releases to the registry whenever pyproject.toml changes on main.
- New nodes: Image Resize plus the Utility group (Text, Integer, Float,
Show Text, Math Expression, Select Every Nth, Split Batch, Merge
Batches, Free Memory) - the dependency-free gaps that let shared
workflows drop heavy packs.
- Replace with AusBoss nodes (prototype): preview-then-confirm graph
rewrite swapping known third-party nodes for pack equivalents, with a
tested translation map, per-node opt-out, and refuse-with-reason for
nodes the pack cannot stand in for.
- Load Video: single-frame FRAME picker, an honest "what will load"
label from the probed source rate, drop-a-video-to-restore. Save
Video: format-aware widgets and a file_path output. Stitch Inpaint
gained a blend_mask output, Select Frame negative from-the-end
indexing, Image Size a batch count - all appended, saved workflows
load unchanged.
- LoRA Loader: drag-to-reorder rows, hover thumbnails on rows, file
size and date in the info card.
- Appearance: flagship scheme deepened to slate-teal; the retired
bright-teal pair upgrades automatically via LEGACY_SCHEME_PAIRS.
Optional queue-completion chime, off by default.
- Image Resize invariant: pixels are only invented on an explicit
width+height pad request - scale-derived modes resolve divisible_by
snaps with a sub-half-step resize, never bars.
- Docs refreshed for six stale pages, stale text and metadata fixed
across the pack, the panel-height rule codified in AGENTS.md and the
brand skill, and ausboss_node_tour.json added - a model-free example
exercising 17 node types in one graph.
Validated: scripts/validate_nodes.py (24 files), 300 JS tests, all
Python suites under the ComfyUI embedded interpreter.
Pausing the graph for an interactive pick is a bigger surface than
anything else here - a server route, a resumable pause, a panel that has
to survive a reload - and it has open issues that are not worth holding a
release for. The lab is where that belongs until they are fixed.
Removes the node, its helpers, its panel, its shared DOM-free module,
its docs and its tests, and drops it from NODE_MODULES, PUBLIC_NODE_IDS,
the panel guard list and the README. _execution_helpers stays: Load Video
and Save Video use it too.
The port lives in ComfyUI-AusBoss-Lab as AUSBOSS_LAB_FrameChooser, with
its routes moved from /ausboss/frame_chooser to /ausboss_lab/ so both
packs can be installed at once. A saved workflow using the public id
reports it as missing.
Krea 2 accepts reference latents, but they arrive with no position, so the
model treats them as a loose style hint: it borrows the look and reinvents
the content. That is the whole reason an outpaint drifts instead of
continuing the photo.
Krea 2 Encode attaches the reference latents and emits the negative from
the same node, so a turbo graph at CFG 1.0 stops carrying a second text
encode that does nothing. Krea 2 Outpaint Model Patch registers those
reference tokens into the target grid at the rectangle the stitcher
records, on frame axis 1.
Load Image + Pad gained a `reference` output - the unpadded source, fitted
to a 384px long edge and a multiple of 16, because the VAE downsamples by
8 and the DiT patchifies by 2. It is APPENDED after `stitcher`, never
inserted: a workflow stores links by output slot index, so any other
position silently rewires every saved graph.
The stitcher now records where the source sits, as source_bbox in pixels
and bbox_normalized in 0..1. Padding knows the rectangle exactly, so it
rides with the canvas instead of a parallel wire that can be left
unplugged. apply_stitch reads neither key, so an older stitcher stitches
identically.
Ported from the lab rather than copied: the lab's _krea2_helpers had its
own pad_image, feather_pad_mask, plan_pad_canvas, parse_fill_color and
build_canvas_stitcher. Duplicating the padding engine here would let the
outpaint path and the inpaint path disagree about what a stitcher is, so
the public module keeps only what is specific to Krea 2 and uses the
existing helpers for the rest.
Two departures from the lab version. The model patch declared a kv_cache
input and never read it - the cache was always on - so it is wired up now.
And it imports comfy's flux internals when you run it rather than at
startup: a core release that moves one then surfaces as an error on that
node, instead of deleting it from the menu and leaving saved workflows
reporting it missing.
Load Image + Pad does the same job from the same stage and starts from
the file, so the only thing the second node added was taking an IMAGE
wire - one idea holding two slots in the menu.
Deletes the node, its panel, its help doc and its stage-only shared
helpers (padEmptyStateText, findPadPreview), and drops it from
NODE_MODULES, PUBLIC_NODE_IDS, the README and the panel guard list.
The padding helpers are untouched; Load Image + Pad and Align Image both
use them. Two console labels there named the removed node, so
_fill_tensor now takes the source name - Align Image passes its own
pad_color, and a colour it cannot read is no longer reported against
padding. The BHWC and mode errors read "Padding"/"Pad mode" instead.
The on-node pad stage moves to ComfyUI-AusBoss-Lab, which has its own
AUSBOSS_LAB_PadImage.
The node produced a mask offset, grown and blurred - no contact
darkening, no perspective - so it read as a sticker halo rather than a
shadow in the scene. That is the approach, not a tuning problem, so it
comes out rather than shipping under the pack's name.
Deletes the node, its helper module, its test file and its help doc, and
drops it from NODE_MODULES, PUBLIC_NODE_IDS and the README. The colour
helper tests keep their two-callers case using Pad Image and Transform,
the real remaining call sites.
blur_mask and grow_shrink_mask stay in _mask_helpers - Crop For Inpaint
and Pad Image use both.
PUBLIC_NODE_IDS only checked that every listed id was still registered. A
brand-new id could register and validation stayed green, so the release gate
could not tell when a node reached the public pack without anyone deciding it
should ship.
Also pins SimpleWatermarkRemover in its own LEGACY_NODE_IDS set. It is the
pre-convention id kept so already-published workflows keep loading, and it was
never listed - so the new check now asserts the compatibility shim is present
rather than flagging it as a stray.
The audit compared every node against ComfyUI core and the major packs;
this lands its outcomes in one branch.
On-node visual editing (the old Codex-pack interaction, rebuilt):
- New Load Image + Pad: image loader with whole-edge pad dragging on the
node canvas, align-to-multiple rounding, and a megapixel target that
rescales the source before padding so the mask seam stays binary.
- Pad Image gains the same handle canvas, fed by an execution-time
snapshot of its input; wireframe with diagnostic empty states before
the first run. Widgets, outputs, and saved workflows unchanged.
- Image Crop + Rotate + Pad's compact panel is now a live stage - crop,
pad, and rotate handles on the node, one shared implementation with
the full-screen editor so the two surfaces cannot drift.
Feature gaps closed against the ecosystem:
- Crop For Inpaint: target_megapixels, selectable rescale_algorithm
(recorded in the stitcher for the paste-back), and extend_* inputs
that grow the frame itself for outpainting.
- Save Video: format choice - mp4 h264, mp4 h265, webm vp9 with Opus
(resampled to 48 kHz); CRF drives all three.
- Load Video: every_nth thinning (fps output divides to match) and a
max_frames cap that ends the decode early.
- LoRA Loader: saved stack templates behind a bar button, and a console
warning when a LoRA's base-model family disagrees with the checkpoint.
- LM Studio Chat: history in/out for multi-turn chains and a json_schema
widget for structured replies.
- Drop Shadow: multiply blend and a shadow_mask output. Align Image:
offset outputs for un-aligning after sampling. Color Match:
first_frame reference mode as a one-node video flicker fix.
Removed (backed up in git history): Select Frame Range and the Video
Bundle family - core ImageFromBatch and the core VIDEO wire now cover
both jobs. Dead NODE_ID module variables cleaned out of every node file.
455 Python tests, 216 JS tests, validate_nodes.py green on 19 node files.
Align Image snaps width and height to a clean multiple - 16, 32,
whatever the model wants - because Qwen image models, VAEs and plenty of
samplers only behave on cleanly divisible sizes. Each mode implies its
own rounding, so there is no separate direction widget: resize rescales
to the nearest multiple, crop center-crops down, pad replicate-pads up,
and a side smaller than one multiple always grows to exactly one rather
than erroring. The new size comes out as INTs for wiring into latents.
Image Size reads width, height, longest edge and shortest edge off the
wire so resizes and latents key off the actual image instead of retyped
numbers that drift.
LM Studio Chat posts a prompt - and optionally one image - to a local
LM Studio server, or anything else speaking the OpenAI-compatible chat
API. The interface is the middle ground the installed ecosystem packs
miss on either side: endpoint string, model string where EMPTY means
whatever the server has loaded (a dropdown fetched at ComfyUI startup
goes stale whenever LM Studio was not running yet), optional system
prompt, prompt required unless an image is connected, temperature,
max_tokens, seed as the re-roll knob, a timeout, and an image downscale
cap. Reasoning-model think blocks land on their own output so the text
stays clean for conditioning. Stdlib urllib only - no new dependencies -
and the POST runs off the executor thread. Every error names what to
fix, with the server's own words when it had any.
Verified live against a running LM Studio: a JIT-loaded qwen3.5-9b
answered a text round trip in 7.6 s through the real node; the
no-model-loaded 400 and a dead port both surfaced their actionable
messages. The vision payload shape is unit-tested; the two local VL
quants refused images server-side (missing projector / failed load), so
the live vision check stays on the deployment checklist.
48 offline tests cover the alignment math, both size nodes, the URL and
payload builders, think-splitting, image encoding, and every mocked
network error path.
Frame Chooser, mostly. A pause did not survive a workflow load: LiteGraph
clears a graph by removing every node, so undo, a tab switch, Clear
Workflow and opening another file all fired the teardown a deleted node
uses to release its pause, and killed a run that was still going. That
now only fires for a real deletion. Answering "keep all" wrote the batch
out as 1,2,...,N into pick_list, so the next run dropped whatever the
enumeration did not reach or failed outright on a shorter clip; it
writes the empty answer it was given. And pick_list is only written back
under "keep last selection" - it pre-answers the node, so filling it in
automatically meant a chooser left at the default paused exactly once.
Refine Mask: smooth applies only the change it made to the jaggy edge
rather than binarizing everything, so an already-soft matte keeps its
alpha (binary masks stay bit-identical), and blur now reaches the
matting solve instead of being thresholded back out of the trimap.
Frame Interpolate's copy path honours batch_size; it gathered every
copied frame at once, which on a long clip at an integer multiple was a
multi-gigabyte allocation on the frames device that no setting bounded.
Subgraph execution ids are resolved by walking the chain instead of
stripping the prefix, which could match an unrelated node with the same
number. Status and runtime badges appear inside subgraphs again, and a
subgraph pause renders on the node that actually paused.
Also: the Custom colour scheme no longer strips every node's colour when
its stored colour is unreadable; Drop Shadow and Pad Image name their
own widget for an unreadable colour instead of blaming Transform; a
non-ASCII token and a non-object JSON body answer 400 rather than
throwing a 500 and stranding the pause; pick_list rejects Unicode
digits, which used to raise during validation or silently read as a
frame nobody typed.
Tooling: validate_nodes parses NODE_MODULES rather than matching it
anywhere in the text, and an unregistered module is an error - it used
to exit 0 printing nothing. It also refuses mapping keys declared
outside nodes/, which is how the registry fixtures came to be advertised
to ComfyUI-Manager as installable nodes; they are .py.txt now. And the
video test no longer leaves ComfyUI on sys.path, which was flipping
every fail-soft seam for whatever ran next.
ausboss