Commit Graph
247 Commits
Author SHA1 Message Date
digital-garbage 5f6ed35929 Matrix: every modifier is listed or exempt with a reason, must report active, and must wire in; crossed with samplers and Two stages
Brownian leaves the stock sampler alone when torchsde internals differ. LoRA: unwrapped refiner layout, absent blocks, LoKr.
2026-11-05 15:58:29 +02:00
digital-garbage 4b306ae65f Round 3: Brownian noise equals stock noise at any sigma height; every LoRA wrapper reaches every Diffusers module
Queries are limited as plain numbers inside the sampler call. Tests for 11 wrappers and sigma 14.6.
2026-11-05 15:44:24 +02:00
digital-garbage 478fb835dd Round 2: Brownian clamp survives the CPU tree's float32 cast; Stop per module; block map handles a paired input
Stop only reaches jobs that check for it; a failure landing with Stop counts as a stop. Hint for imported workflows corrected.
2026-11-05 15:29:32 +02:00
digital-garbage 1b9f1cb6aa Review: Brownian noise is the stock noise again; block map profile survives audio+video blocks and cancel
Queries are clamped into torchsde's span instead of moving the span. A cancelled profile saves nothing.
Attention explorer temperature stays above zero under the map; unmeasured groups are not given 3x.
2026-11-05 15:10:18 +02:00
digital-garbageandClaude Sonnet 5.5 015ec6aa55 Test: the update status test no longer assumes the repo folder is called FunUI-v5
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjV3UWsHHjJiAXix29B
2026-11-05 14:48:36 +02:00
Claude 374cf3de29 Forget a stale namespace 'app' after a failed ComfyUI logger import
Fixes the 'cannot import name governance from app' collection error when pytest loads the root package before ComfyUI is on sys.path.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjV3UWsHHjJiAXix29B
2026-11-05 12:03:30 +00:00
Claude 06692cf79c Media bin: pin a picture as the aspect ratio source for all scenes (new scenes inherit it), and add a reference to all scenes
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjXTnZcw5grg6FUn3DV
2026-11-02 13:17:44 +00:00
Claude 344d554a71 Brownian noise: widen the tree past torchsde's 6-decimal rounding so SDE samplers stop warning about ta>=t0
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjUxS9c6hheZ8nePUYf
2026-11-02 13:07:27 +00:00
Claude 5eabca5839 LoRA loader: Apply to stage (First/Second/Both) for Two stages, and Diffusers-layout H3 LoRAs now load
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjVKTwSL4mCUi3hd811
2026-11-02 12:56:50 +00:00
Claude a0234fa01b Frozen node list: Save Video has the optional quality input
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
2026-11-01 12:00:07 +00:00
Claude 47f2bd7ca4 Settings: a value that is wrong for a setting hidden by another's choice no longer stops the run; its default stands
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjWzZx5QzcqkheSuhsy
2026-10-30 17:50:35 +00:00
Claude 3862f3ec36 LoRA Loader: up to eight LoRAs in one node, applied in order; slot 1 keeps its inputs
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjU1A5dzqoK4stWcmzk
2026-10-29 19:23:48 +00:00
Claude 0f36445830 Interpolate runs as a FunUI background job, not a ComfyUI prompt (an extra prompt without loaders made ComfyUI drop the workflow's models); the NVIDIA effect stays loaded between jobs
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
2026-10-29 13:18:07 +00:00
Claude 97b85a3f09 Interpolate: RTX Frame Generation as its own module and add-on, button and modes like Upscale
Shared video stream and NVIDIA helpers move to core (video_pipe, nvidia); the add-on needs nvidia-vfx 0.2+, moves an older one up and never moves a newer one back; Upscale and Interpolate cannot feed each other in Always mode.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
2026-10-29 13:00:01 +00:00
Claude 5df050a7f2 Project settings: Resolution is the Short side / Long side / Pixel count; H3 sizes with FunUIAspectSize, old projects keep Pixel count
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjYcwzhZeJZAD6ujMjA
2026-10-29 11:47:13 +00:00
Claude 373f0ea1ab Two stages: register as a modifier (it was never installed), test that every install() is provided
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjWwkXVabCNSQ53xaW1
2026-10-29 11:04:16 +00:00
Claude 3837d585e0 VAE Loader: optional decode-only VAE (Sol-H3-VAE, X2 Detail) while the main VAE encodes
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
2026-10-29 10:59:06 +00:00
Claude a80e58490c Two stages as a sampling setting (a model wrapper, any sampler) instead of a preset
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
2026-10-29 10:05:19 +00:00
Claude 791bb6ca48 H3: two-stage preset (first steps on a smaller picture), Sampler denoised output, Resample to an exact size without an upscaler file, Stage Size node
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
2026-10-29 09:55:37 +00:00
Claude b108d4f4f5 H3 loader: MXFP8 option for the middle blocks (Sol-H3 recipe), credit in README
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjW75aYB8UyVRZo6fCr
2026-10-29 09:44:49 +00:00
Claude 8e22f17b00 LTX: Image to Video from References saved before the aspect source is upgraded on load
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
2026-10-27 10:46:18 +00:00
Claude 5d84c71056 LTX Image to Video: the timeline picture is the aspect source (new FunUI Aspect Size node), the project size is the budget
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
2026-10-27 10:43:45 +00:00
Claude a17484a9aa Freeze the Guide Frames node's inputs
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Tw9fjYZhHqk196LykrWy3T
2026-10-27 10:38:06 +00:00
Claude a63bedfd5f Tests: route tests get stand-in model files so a machine without models still sees a deleted file; optional-slot list follows the two LTX presets
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
2026-10-27 10:34:49 +00:00
Claude c70c74f01f LTX: two tested presets (Image to Video from References, Video to Video direct) with text to video as the fallback in both; docs say LTX 2.3 is tested
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
2026-10-27 09:45:04 +00:00
Claude d4641450c8 Reapply "Direct v2v saved before the video-only flag keeps taking its video from references; render polls survive one unanswered reply; LTX project HTTP test"
This reverts commit 5a2f9c5999.
2026-10-27 09:14:20 +00:00
Claude d277ebc76c Log: a console that cannot print a file name no longer fails the run that mentioned it
A clip called in Japanese on a machine with an ASCII console raised UnicodeEncodeError out of log.info, inside Load Media.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
2026-10-27 09:12:39 +00:00
Claude f8955c2ef2 Keep ComfyUI's console on disk (Previous run in the Log window) and log memory at LoRA load and sampler start
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
2026-10-27 09:03:30 +00:00
Claude 5a2f9c5999 Revert "Direct v2v saved before the video-only flag keeps taking its video from references; render polls survive one unanswered reply; LTX project HTTP test"
This reverts commit ed4de1e8af.
2026-10-27 08:52:11 +00:00
Claude ed4de1e8af Direct v2v saved before the video-only flag keeps taking its video from references; render polls survive one unanswered reply; LTX project HTTP test
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
2026-10-27 08:48:01 +00:00
Claude a4eaabc20e Video input: prepare reference videos (size, crop, rate, skip, cut, every Nth, cap) per project or per scene
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BzJLJWVu7RZnbRqm3nYAnX
2026-10-27 01:04:58 +00:00
Claude b5656db6b8 Timing: the sampler line gives the time of every step, not just the first two
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01VmbxSsiiz8wmt226dtbFXe
2026-10-25 17:03:07 +00:00
Claude cce20f136a Shot Camera: spaCy model failed to load with preshed 3.0.14 (OverflowError); pin preshed<3.0.14, repair on start, name the real cause in the log
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01T81dXrsAyE9Uu8UvYzKvGt
2026-10-25 16:20:14 +00:00
Claude b903648950 Wheel: Clear references and Disable all guidance enhancements; Guidance switch in Engine settings; branch notes in the branch switcher
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01QNQWU3ukHBLpBb9driYFi8
2026-10-25 16:16:46 +00:00
Claude 527d368c82 SLA: optional rising sparsity (sla_sparsity_start), GSRS idea; CPU test env script
Skip fewer attention blocks on early steps and more on late ones, in a straight
line up to sla_sparsity. Off at 0, untested on H3. Credit GSRS (arXiv 2610.21129).
tools/test_env.sh and tools/cpuforce.py set up the suite on a GPU-less machine.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_0176SHndmQj7T1VtWAWZiNcq
2026-10-25 16:05:33 +00:00
Claude dc4e51563c 5.0.3: stale Decisiveness test, migration tests, changelog folded into the release
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016acRss69eH1235eRdFTZHY
2026-10-25 13:44:56 +00:00
Claude 2e445244df Test: self-removal refusal names the folder, whatever it is called
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016acRss69eH1235eRdFTZHY
2026-10-25 13:28:36 +00:00
Claude 3adebb731f Rename FunPack to FunUI (5.0.3 Classy Chopper): /fun endpoint, wink logo, load-time migration of old names
Old project/workflow names and browser settings migrate on load; /funpack redirects to /fun.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016acRss69eH1235eRdFTZHY
2026-10-25 13:11:03 +00:00
Claude a3031cf630 feat: one switch in Settings > Conditioning turns off automatic camera prompt enhancement
Shot camera's moves, cuts, views, reframes and their chances sit out;
liked details and every other enhancement are untouched.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_014xY2qM34KgJ8yHLsTQEou1
2026-10-22 15:38:39 +00:00
Claude b1def9bab2 feat: Log colours only the lines that need attention (warnings amber, errors red); healthy output stays plain
The Log window and the terminal share one rule. Levels come from FunPack's own
[Log] severities; ComfyUI and other packs are matched on strict error/warning
markers and tracebacks, not on words in prose.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FACCerXXJ2TbeLuRi6k5AG
2026-10-22 06:50:08 +00:00
Claude 156f86e618 fix: checkpoint loader reports a missing VAE; a start picture no pipeline slot takes is named as unused
Tests: VAE, LoRA (7 key dialects), CLIP and checkpoint loaders; every preset x every kind of picked file is used or named.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WP6HMLLhRYcghAEXK4KLwK
2026-10-21 04:36:20 +00:00
Claude c089fe3a9a test: every diffusion loader option loads a tiny H3 file; every reference kind reaches its H3 socket and passes ComfyUI validation
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WP6HMLLhRYcghAEXK4KLwK
2026-10-21 04:29:20 +00:00
Claude 98a1504a29 fix: workflow import reads the official ComfyUI templates: lost widget values, dynamic inputs, autogrow names, prompt through guiders
Audit against all 634 workflows ComfyUI ships (comfyui-workflow-templates). Found and fixed: a crash on list-valued widgets; widgets of nodes inside subgraphs losing seed/denoise; dynamic combos (resize, save format, sparse attention) shifting every later value; instance values mapped by the wrong inputs; Math expression / Batch images / Reference multi latent inputs refused; INT wires into FLOAT-or-INT widgets refused; the prompt not found when conditioning goes through BasicGuider (official H3 workflows); widgets an older export never had now take the node default; nodes no save or preview uses are left out as ComfyUI does. Autogrow sockets are now numbered as ComfyUI numbers them (R2V has 9/3/3/3, FunPack offered one extra of each).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01WP6HMLLhRYcghAEXK4KLwK
2026-10-21 04:10:12 +00:00
Claude 24f946f43c release: 5.0.1 changelog, version and training credit
Load Media refuses unreadable files in plain words; gallery delete refuses odd names; stale tests updated.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01V9uCRvqd1GDx6PZDZLyovu
2026-10-21 03:40:31 +00:00
Claude f6b49d318a feat: a video with a soundtrack also feeds R2V's paired video audio input
The media list says which videos have sound.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:46:44 +00:00
Claude bf62683f5a feat: Load Media takes a picture, video or sound and the app wires the output that fits
A video or audio reference now uses an ordinary reference slot, so old projects need no new slots; saved media slots take the preset's current roles.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CHWxqHtxwWrq4kEyFTaHds
2026-10-21 02:22:23 +00:00
Claude 2921ff517b Gallery: saved videos and pictures next to Temp files, with preview and confirmed delete
Settings > Saved & Temp Files now has two tabs. Saved lists what ComfyUI wrote to its output folder; Temp is the old list. Click a file to look at it, open it in a tab, or delete it after a question. Delete only removes media files inside the chosen folder.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_015xHQk4XeXzJpBR3HSwnoBZ
2026-10-17 21:17:31 +00:00
Claude 65a731584c LoRA training: save a copy of the LoRA every N steps as name_stepN
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 20:14:16 +00:00
Claude 6603f42ecb LoRA training: pause, resume and a preview LoRA at chosen steps (backend)
A run can wait at a step boundary (Pause, or every N steps for a preview): its state is saved,
the LoRA so far is written as <name>_preview.safetensors, and the card is let go. Resume carries on
from the saved state under the same run. UNTESTED on real weights.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 20:08:01 +00:00
Claude 919097c732 LoRA training: our own loop for H3, and a Log that survives a crash
The H3 run trains with a loop of our own (LoRA on the attention and feed-forward projections of the
50 blocks, per-block checkpoint, uniform noise levels, musubi-tuner's approach) while ComfyUI carries
the batches. Every Log record is flushed to disk as it is said and reloaded on start; the run
writes each stage and step to it. ComfyUI's own offloading toggle is ignored by the new loop.
UNTESTED on the real weights.

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MpnF7GwNGMbngU11wjym7P
2026-10-17 19:57:06 +00:00