2278 Commits

Include renames

Author	SHA1	Message	Date
comfyanonymousandGitHub	28eaab608b	Diffusion model part of Qwen Image Layered. (#11408) ... Only thing missing after this is some nodes to make using it easier.	2025-12-18 20:21:14 -05:00
comfyanonymousandGitHub	6a2678ac65	Trim/pad channels in VAE code. (#11406)	2025-12-18 18:22:38 -05:00
comfyanonymousandGitHub	e4fb3a3572	Support loading Wan/Qwen VAEs with different in/out channels. (#11405)	2025-12-18 17:45:33 -05:00
comfyanonymousandGitHub	bf7dc63bd6	skip_load_model -> force_full_load (#11390) ... This should be a bit more clear and less prone to potential breakage if the logic of the load models changes a bit.	2025-12-17 23:29:32 -05:00
Kohaku-BlueleafandGitHub	86dbb89fc9	Resolution bucketing and Trainer implementation refactoring (#11117)	2025-12-17 22:15:27 -05:00
chaObservandGitHub	5d9ad0c6bf	Fix the last step with non-zero sigma in sa_solver (#11380)	2025-12-17 13:57:40 -05:00
chaObservandGitHub	827bb1512b	Add exp_heun_2_x0 sampler series (#11360)	2025-12-16 23:35:43 -05:00
comfyanonymousandGitHub	ffdd53b327	Check state dict key to auto enable the index_timestep_zero ref method. (#11362)	2025-12-16 17:03:17 -05:00
comfyanonymousandGitHub	bc606d7d64	Add a way to set the default ref method in the qwen image code. (#11349)	2025-12-16 01:26:55 -05:00
comfyanonymousandGitHub	683569de55	Only enable fp16 on ZImage on newer pytorch. (#11344)	2025-12-15 22:33:27 -05:00
HaomingandGitHub	ea2c117bc3	[BlockInfo] Wan (#10845) ... * block info * animate * tensor * device * revert	2025-12-15 17:59:16 -08:00
3 people	fc4af86068	[BlockInfo] Lumina (#11227) ... * block info * device * Make tensor int again --------- Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>	2025-12-15 17:57:28 -08:00
comfyanonymousandGitHub	70541d4e77	Support the new qwen edit 2511 reference method. (#11340) ... index_timestep_zero can be selected in the FluxKontextMultiReferenceLatentMethod now with the display name set to the more generic "Edit Model Reference Method" node.	2025-12-15 19:20:34 -05:00
3 people	77b2f7c228	Add context windows callback for custom cond handling (#11208) ... Co-authored-by: ozbayb <17261091+ozbayb@users.noreply.github.com>	2025-12-15 16:06:32 -08:00
Dr.Lt.DataandGitHub	dbd330454a	feat(preview): add per-queue live preview method override (#11261) ... - Add set_preview_method() to override live preview method per queue item - Read extra_data.preview_method from /prompt request - Support values: taesd, latent2rgb, none, auto, default - "default" or unset uses server's CLI --preview-method setting - Add 44 tests (37 unit + 7 E2E)	2025-12-15 15:57:39 -08:00
comfyanonymousandGitHub	5ac3b26a7d	Update warning for old pytorch version. (#11319) ... Versions below 2.4 are no longer supported. We will not break support on purpose but will not fix it if we do.	2025-12-14 04:02:50 -05:00
chaObservandGitHub	6592bffc60	seeds_2: add phi_2 variant and sampler node (#11309) ... * Add phi_2 solver type to seeds_2 * Add sampler node of seeds_2	2025-12-14 00:03:29 -05:00
comfyanonymousandGitHub	971cefe7d4	Fix pytorch warnings. (#11314)	2025-12-13 18:45:23 -05:00
comfyanonymousandGitHub	da2bfb5b0a	Basic implementation of z image fun control union 2.0 (#11304) ... The inpaint part is currently missing and will be implemented later. I think they messed up this model pretty bad. They added some control_noise_refiner blocks but don't actually use them. There is a typo in their code so instead of doing control_noise_refiner -> control_layers it runs the whole control_layers twice. Unfortunately they trained with this typo so the model works but is kind of slow and would probably perform a lot better if they corrected their code and trained it again.	2025-12-13 01:39:11 -05:00
comfyanonymousandGitHub	c5a47a1692	Fix bias dtype issue in mixed ops. (#11293)	2025-12-12 11:49:35 -05:00
comfyanonymousandGitHub	5495589db3	Respect the dtype the op was initialized in for non quant mixed op. (#11282)	2025-12-11 23:32:27 -05:00
comfyanonymousandGitHub	eeb020b9b7	Better chroma radiance and other models vram estimation. (#11278)	2025-12-11 17:33:09 -05:00
comfyanonymousandGitHub	ae65433a60	This only works on radiance. (#11277)	2025-12-11 17:15:00 -05:00
comfyanonymousandGitHub	fdebe18296	Fix regular chroma radiance (#11276)	2025-12-11 17:09:35 -05:00
comfyanonymousandGitHub	f8321eb57b	Adjust memory usage factor. (#11257)	2025-12-11 01:30:31 -05:00
FarshoreandGitHub	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
comfyanonymousandGitHub	17c92a9f28	Tweak Z Image memory estimation. (#11254)	2025-12-10 19:59:48 -05:00
comfyanonymousandGitHub	791e30ff50	Fix nan issue when quantizing fp16 tensor. (#11213)	2025-12-09 17:03:21 -05:00
Jukka SeppänenandGitHub	e2a800e7ef	Fix for HunyuanVideo1.5 meanflow distil (#11212)	2025-12-09 16:59:16 -05:00
rattusandGitHub	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
LodestoneandGitHub	b9fb542703	add chroma-radiance-x0 mode (#11197)	2025-12-08 23:33:29 -05:00
rattusandGitHub	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
comfyanonymousandGitHub	d50f342c90	Fix potential issue. (#11201)	2025-12-08 23:20:04 -05:00
comfyanonymousandGitHub	3b0368aa34	Fix regression. (#11194)	2025-12-08 17:38:36 -05:00
rattusandGitHub	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
dxqbandGitHub	8e889c535d	Support "transformer." LoRA prefix for Z-Image (#11135)	2025-12-08 15:17:26 -05:00
comfyanonymousandGitHub	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
comfyanonymousandGitHub	329480da5a	Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162)	2025-12-06 17:50:10 -08:00
rattusandGitHub	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
comfyanonymousandGitHub	50ca97e776	Speed up lora compute and lower memory usage by doing it in fp16. (#11161)	2025-12-06 18:36:20 -05:00
comfyanonymousandGitHub	ae676ed105	Fix regression. (#11137)	2025-12-05 23:01:19 -05:00
Jukka SeppänenandGitHub	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
comfyanonymousandGitHub	092ee8a500	Fix some custom nodes. (#11134)	2025-12-05 18:25:31 -05:00
4 people	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
comfyanonymousandGitHub	6fd463aec9	Fix regression when text encoder loaded directly on GPU. (#11129)	2025-12-05 15:33:16 -05:00
comfyanonymousandGitHub	43071e3de3	Make old scaled fp8 format use the new mixed quant ops system. (#11000)	2025-12-05 14:35:42 -05:00
Jedrzej KosinskiandGitHub	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
rattusandGitHub	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
rattusandGitHub	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
rattusandGitHub	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