2510 Commits

Author	SHA1	Message	Date
doctorpangloss	abb68c3de6	Merge branch 'master' of github.com:comfyanonymous/ComfyUI into merge/0.4.0-snapshot	2025-12-12 12:13:42 -08:00
doctorpangloss	b309e0424e	Fix transformers 5 compatibility	2025-12-12 12:11:25 -08:00
comfyanonymous	c5a47a1692	Fix bias dtype issue in mixed ops. (#11293)	2025-12-12 11:49:35 -05:00
comfyanonymous	5495589db3	Respect the dtype the op was initialized in for non quant mixed op. (#11282)	2025-12-11 23:32:27 -05:00
doctorpangloss	b81a5b15ae	improve tests	2025-12-11 17:03:39 -08:00
comfyanonymous	eeb020b9b7	Better chroma radiance and other models vram estimation. (#11278)	2025-12-11 17:33:09 -05:00
doctorpangloss	a2e898f091	Merge branch 'master' of github.com:comfyanonymous/ComfyUI into merge/0.4.0-snapshot	2025-12-11 14:28:38 -08:00
doctorpangloss	e7d0cc457d	fix tests, replace broken llava and fix transformers videos issue	2025-12-11 14:23:05 -08:00
comfyanonymous	ae65433a60	This only works on radiance. (#11277)	2025-12-11 17:15:00 -05:00
comfyanonymous	fdebe18296	Fix regular chroma radiance (#11276)	2025-12-11 17:09:35 -05:00
comfyanonymous	f8321eb57b	Adjust memory usage factor. (#11257)	2025-12-11 01:30:31 -05:00
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
comfyanonymous	17c92a9f28	Tweak Z Image memory estimation. (#11254)	2025-12-10 19:59:48 -05:00
doctorpangloss	f294c5d401	Merge branch 'master' of github.com:comfyanonymous/ComfyUI into merge/0.3.76-snapshot	2025-12-09 17:58:53 -08:00
doctorpangloss	7338873262	full test suite wip	2025-12-09 16:29:05 -08:00
doctorpangloss	9c892a9b34	pass unit tests	2025-12-09 16:13:43 -08:00
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
doctorpangloss	79cf2c2867	move and tweak tests	2025-12-09 13:29:41 -08:00
doctorpangloss	b20a1edf8e	investigate this issue further	2025-12-09 13:25:04 -08:00
doctorpangloss	194ac1f596	Merge branch 'master' of github.com:comfyanonymous/ComfyUI into merge/0.3.76-snapshot	2025-12-09 13:24:52 -08:00
doctorpangloss	7fb748fcef	wip merge	2025-12-09 13:22:27 -08:00
doctorpangloss	a7ef3e04ea	update extra nodes	2025-12-09 09:05:18 -08:00
doctorpangloss	a00c902067	Merge branch 'master' of github.com:comfyanonymous/ComfyUI into merge/0.3.76-snapshot	2025-12-09 08:58:52 -08:00
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
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
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
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
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
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
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
doctorpangloss	8e282aea6d	improve images and videos support	2025-12-03 15:28:56 -08:00
doctorpangloss	4349fac71a	fix torch compile for language models	2025-12-03 14:40:52 -08:00
doctorpangloss	b149031748	add video support for language models, improve torch compile for transformers models, make it easier to load videos, fix progess messages from language nodes	2025-12-03 14:40:27 -08:00
rattus	519c941165	Prs/lora reservations (reduce massive Lora reservations especially on Flux2) (#11069) ... * mp: only count the offload cost of math once This was previously bundling the combined weight storage and computation cost * ops: put all post async transfer compute on the main stream Some models have massive weights that need either complex dequantization or lora patching. Don't do these patchings on the offload stream, instead do them on the main stream to syncrhonize the potentially large vram spikes for these compute processes. This avoids having to assume a worst case scenario of multiple offload streams all spiking VRAM is parallel with whatever the main stream is doing.	2025-12-03 02:28:45 -05:00