4362 Commits

This Branch

This Branch

All Branches

Author	SHA1	Message	Date
Alexander Piskun	93948e3fc5	feat(api-nodes): enable Kling Omni O1 node (#11229)	2025-12-10 22:11:12 -08:00
Farshore	e711aaf1a7	Lower VAE loading requirements：Create a new branch for GPU memory calculations in qwen-image vae (#11199)	2025-12-10 22:02:26 -05:00
Johnpaul Chiwetelu	57ddb7fd13	Fix: filter hidden files from /internal/files endpoint (#11191)	2025-12-10 21:49:49 -05:00
comfyanonymous	17c92a9f28	Tweak Z Image memory estimation. (#11254)	2025-12-10 19:59:48 -05:00
Alexander Piskun	36357bbcc3	process the NodeV1 dict results correctly (#11237)	2025-12-10 11:55:09 -08:00
Benjamin Lu	f668c2e3c9	bump comfyui-frontend-package to 1.34.8 (#11220)	2025-12-09 22:27:07 -05:00
comfyanonymous	fc657f471a	ComfyUI version v0.4.0 ... From now on ComfyUI will do version numbers a bit differently, every stable off the master branch will increment the minor version. Anytime a fix needs to be backported onto a stable version the patch version will be incremented. Example: We release v0.6.0 off the master branch then a day later a bug is discovered and we decide to backport the fix onto the v0.6.0 stable, this will be done in a separate branch in the main repository and this new stable will be tagged v0.6.1	2025-12-09 18:26:49 -05:00
comfyanonymous	791e30ff50	Fix nan issue when quantizing fp16 tensor. (#11213)	2025-12-09 17:03:21 -05:00
Jukka Seppänen	e2a800e7ef	Fix for HunyuanVideo1.5 meanflow distil (#11212)	2025-12-09 16:59:16 -05:00
rattus	9d252f3b70	ops: delete dead code (#11204) ... This became dead code in https://github.com/comfyanonymous/ComfyUI/pull/11069	2025-12-09 00:55:13 -05:00
Lodestone	b9fb542703	add chroma-radiance-x0 mode (#11197)	2025-12-08 23:33:29 -05:00
Christian Byrne	cabc4d351f	bump comfyui-frontend-package to 1.33.13 (patch) (#11200)	2025-12-08 23:22:02 -05:00
rattus	e136b6dbb0	dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171) ... * make setattr safe for non existent attributes Handle the case where the attribute doesnt exist by returning a static sentinel (distinct from None). If the sentinel is passed in as the set value, del the attr. * Account for dequantization and type-casts in offload costs When measuring the cost of offload, identify weights that need a type change or dequantization and add the size of the conversion result to the offload cost. This is mutually exclusive with lowvram patches which already has a large conservative estimate and wont overlap the dequant cost so\ dont double count. * Set the compute type on CLIP MPs So that the loader can know the size of weights for dequant accounting.	2025-12-08 23:21:31 -05:00
comfyanonymous	d50f342c90	Fix potential issue. (#11201)	2025-12-08 23:20:04 -05:00
comfyanonymous	3b0368aa34	Fix regression. (#11194)	2025-12-08 17:38:36 -05:00
ComfyUI Wiki	935493f6c1	chore: update workflow templates to v0.7.54 (#11192)	2025-12-08 15:18:53 -05:00
rattus	60ee574748	retune lowVramPatch VRAM accounting (#11173) ... In the lowvram case, this now does its math in the model dtype in the post de-quantization domain. Account for that. The patching was also put back on the compute stream getting it off-peak so relax the MATH_FACTOR to only x2 so get out of the worst-case assumption of everything peaking at once.	2025-12-08 15:18:06 -05:00
dxqb	8e889c535d	Support "transformer." LoRA prefix for Z-Image (#11135)	2025-12-08 15:17:26 -05:00
Alexander Piskun	fd271dedfd	[API Nodes] add support for seedance-1-0-pro-fast model (#10947) ... * feat(api-nodes): add support for seedance-1-0-pro-fast model * feat(api-nodes): add support for seedream-4.5 model	2025-12-08 01:33:46 -08:00
Alexander Piskun	c3c6313fc7	Added "system_prompt" input to Gemini nodes (#11177)	2025-12-08 01:28:17 -08:00
Alexander Piskun	85c4b4ae26	chore: replace imports of deprecated V1 classes (#11127)	2025-12-08 01:27:02 -08:00
ComfyUI Wiki	058f084371	Update workflow templates to v0.7.51 (#11150) ... * chore: update workflow templates to v0.7.50 * Update template to 0.7.51	2025-12-08 01:22:51 -08:00
Alexander Piskun	ec7f65187d	chore(comfy_api): replace absolute imports with relative (#11145)	2025-12-08 01:21:41 -08:00
comfyanonymous	56fa7dbe38	Properly load the newbie diffusion model. (#11172) ... There is still one of the text encoders missing and I didn't actually test it.	2025-12-07 07:44:55 -05:00
comfyanonymous	329480da5a	Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162)	2025-12-06 17:50:10 -08:00
rattus	4086acf3c2	Fix on-load VRAM OOM (#11144) ... slow down the CPU on model load to not run ahead. This fixes a VRAM on flux 2 load. I went to try and debug this with the memory trace pickles, which needs --disable-cuda-malloc which made the bug go away. So I tried this synchronize and it worked. The has some very complex interactions with the cuda malloc async and I dont have solid theory on this one yet. Still debugging but this gets us over the OOM for the moment.	2025-12-06 18:42:09 -05:00
comfyanonymous	50ca97e776	Speed up lora compute and lower memory usage by doing it in fp16. (#11161)	2025-12-06 18:36:20 -05:00
Jukka Seppänen	7ac7d69d94	Fix EmptyAudio node input types (#11149)	2025-12-06 10:09:44 -08:00
Alexander Piskun	76f18e955d	marked all Pika API nodes a deprecated (#11146)	2025-12-06 03:28:08 -08:00
comfyanonymous	d7a0aef650	Set OCL_SET_SVM_SIZE on AMD. (#11139)	2025-12-06 00:15:21 -05:00
Alexander Piskun	913f86b727	[V3] convert nodes_mask.py to V3 schema (#10669) ... * convert nodes_mask.py to V3 schema * set "Preview Mask" as display name for MaskPreview	2025-12-05 20:24:10 -08:00
Alexander Piskun	117bf3f2bd	convert nodes_freelunch.py to the V3 schema (#10904)	2025-12-05 20:22:02 -08:00
comfyanonymous	ae676ed105	Fix regression. (#11137)	2025-12-05 23:01:19 -05:00
Jukka Seppänen	fd109325db	Kandinsky5 model support (#10988) ... * Add Kandinsky5 model support lite and pro T2V tested to work * Update kandinsky5.py * Fix fp8 * Fix fp8_scaled text encoder * Add transformer_options for attention * Code cleanup, optimizations, use fp32 for all layers originally at fp32 * ImageToVideo -node * Fix I2V, add necessary latent post process nodes * Support text to image model * Support block replace patches (SLG mostly) * Support official LoRAs * Don't scale RoPE for lite model as that just doesn't work... * Update supported_models.py * Rever RoPE scaling to simpler one * Fix typo * Handle latent dim difference for image model in the VAE instead * Add node to use different prompts for clip_l and qwen25_7b * Reduce peak VRAM usage a bit * Further reduce peak VRAM consumption by chunking ffn * Update chunking * Update memory_usage_factor * Code cleanup, don't force the fp32 layers as it has minimal effect * Allow for stronger changes with first frames normalization Default values are too weak for any meaningful changes, these should probably be exposed as advanced node options when that's available. * Add image model's own chat template, remove unused image2video template * Remove hard error in ReplaceVideoLatentFrames -node * Update kandinsky5.py * Update supported_models.py * Fix typos in prompt template They were now fixed in the original repository as well * Update ReplaceVideoLatentFrames Add tooltips Make source optional Better handle negative index * Rename NormalizeVideoLatentFrames -node For bit better clarity what it does * Fix NormalizeVideoLatentStart node out on non-op	2025-12-05 22:20:22 -05:00
Dr.Lt.Data	bed12674a1	docs: add ComfyUI-Manager documentation and update to v4.0.3b4 (#11133) ... - Add manager setup instructions and command line options to README - Document --enable-manager, --enable-manager-legacy-ui, and --disable-manager-ui flags - Bump comfyui_manager version from 4.0.3b3 to 4.0.3b4	2025-12-05 15:45:38 -08:00
comfyanonymous	092ee8a500	Fix some custom nodes. (#11134)	2025-12-05 18:25:31 -05:00
Jukka Seppänen	79d17ba233	Context windows fixes and features (#10975) ... * Apply cond slice fix * Add FreeNoise * Update context_windows.py * Add option to retain condition by indexes for each window This allows for example Wan/HunyuanVideo image to video to "work" by using the initial start frame for each window, otherwise windows beyond first will be pure T2V generations. * Update context_windows.py * Allow splitting multiple conds into different windows * Add handling for audio_embed * whitespace * Allow freenoise to work on other dims, handle 4D batch timestep Refactor Freenoise function. And fix batch handling as timesteps seem to be expanded to batch size now. * Disable experimental options for now So that the Freenoise and bugfixes can be merged first --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com> Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>	2025-12-05 12:42:46 -08:00
comfyanonymous	6fd463aec9	Fix regression when text encoder loaded directly on GPU. (#11129)	2025-12-05 15:33:16 -05:00
comfyanonymous	43071e3de3	Make old scaled fp8 format use the new mixed quant ops system. (#11000)	2025-12-05 14:35:42 -05:00
Jedrzej Kosinski	0ec05b1481	Remove line made unnecessary (and wrong) after transformer_options was added to NextDiT's _forward definition (#11118)	2025-12-05 14:05:38 -05:00
comfyanonymous	35fa091340	Forgot to put this in README. (#11112)	2025-12-04 22:52:09 -05:00
Alexander Piskun	3c8456223c	[API Nodes]: fixes and refactor (#11104) ... * chore(api-nodes): applied ruff's pyupgrade(python3.10) to api-nodes client's to folder * chore(api-nodes): add validate_video_frame_count function from LTX PR * chore(api-nodes): replace deprecated V1 imports * fix(api-nodes): the types returned by the "poll_op" function are now correct.	2025-12-04 14:05:28 -08:00
rattus	9bc893c5bb	sd: bump HY1.5 VAE estimate (#11107) ... Im able to push vram above estimate on partial unload. Bump the estimate. This is experimentally determined with a 720P and 480P datapoint calibrating for 24GB VRAM total.	2025-12-04 09:50:36 -08:00
rattus	f4bdf5f830	sd: revise hy VAE VRAM (#11105) ... This was recently collapsed down to rolling VAE through temporal. Clamp The time dimension.	2025-12-04 09:50:04 -08:00
rattus	6be85c7920	mp: use look-ahead actuals for stream offload VRAM calculation (#11096) ... TIL that the WAN TE has a 2GB weight followed by 16MB as the next size down. This means that team 8GB VRAM would fully offload the TE in async offload mode as it just multiplied this giant size my the num streams. Do the more complex logic of summing up the upcoming to-load weight sizes to avoid triple counting this massive weight. partial unload does the converse of recording the NS most recent unloads as they go.	2025-12-03 23:28:44 -05:00
comfyanonymous	ea17add3c6	Fix case where text encoders where running on the CPU instead of GPU. (#11095)	2025-12-03 23:15:15 -05:00
comfyanonymous	ecdc8697d5	Qwen Image Lora training fix from #11090 (#11094)	2025-12-03 22:49:28 -05:00
Alexander Piskun	dce518c2b4	convert nodes_audio.py to V3 schema (#10798)	2025-12-03 17:35:04 -08:00
Alexander Piskun	440268d394	convert nodes_load_3d.py to V3 schema (#10990)	2025-12-03 13:52:31 -08:00
Alexander Piskun	87c104bfc1	add support for "@image" reference format in Kling Omni API nodes (#11082)	2025-12-03 08:55:44 -08:00