Found in a sweep of the pack against ComfyUI's own nodes: things the normal
node does that the pack's node did not.
- Every number box takes a sum. Click a number, type 1024*1.5 or
(1920-64)/2 and press Enter, as in ComfyUI's own number boxes: + - * / %,
brackets and a sign. The reader is the pack's own (sumValue in
js/shared/scrub_input.mjs) and is only asked when the text is not a plain
number.
- Show Text takes any wire. Its input was STRING only. A number, an on/off
value or a list is shown too; a picture or a latent is shown by its size.
The output stays STRING and carries the text that is shown, so text
passes through unchanged and a number comes out as text.
- Save Image takes name tokens in the file name, as ComfyUI's own Save
Image does: %date:yyyy-MM-dd% and %Node.setting% are filled in the
browser when a run is sent (js/shared/name_tokens.mjs, now shared with
Save Video), %width% %height% and the time tokens on the server. The
path preview shows them. A linked filename is never read for tokens.
- Ctrl + Up and Ctrl + Down change a word's weight in the pack's prompt
boxes (Text, Krea 2 Encode). The card's text box stopped the key before
ComfyUI's own listener saw it; those two keys now go on from a multiline
box, and from nowhere else.
- Image Size shows what it measured beside its outputs after a run
("width: 1024"). The numbers go into the output labels, so the node keeps
its size. ComfyUI says nothing about a node whose answer came from its
cache, so the numbers are kept in the node's properties and come back
when a workflow is opened again; a changed picture wire clears them.
No input was added, renamed or reordered. Help pages, README lines, tests
and CHANGELOG entries are included.
- 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.
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.
ausboss