502 Commits

Author	SHA1	Message	Date
krigeta	dc9822b7df	Add working Qwen 2512 ControlNet (Fun ControlNet) support (#12359)	2026-02-13 22:23:52 -05:00
comfyanonymous	726af73867	Fix some custom nodes. (#12455)	2026-02-13 20:21:10 -05:00
comfyanonymous	e1add563f9	Use torch RMSNorm for flux models and refactor hunyuan video code. (#12432)	2026-02-13 15:35:13 -05:00
comfyanonymous	76a7fa96db	Make built in lora training work on anima. (#12402)	2026-02-10 22:04:32 -05:00
Kohaku-Blueleaf	cdcf4119b3	[Trainer] training with proper offloading (#12189) ... * Fix bypass dtype/device moving * Force offloading mode for training * training context var * offloading implementation in training node * fix wrong input type * Support bypass load lora model, correct adapter/offloading handling	2026-02-10 21:45:19 -05:00
comfyanonymous	039955c527	Some fixes to previous pr. (#12339)	2026-02-06 20:14:52 -05:00
tdrussell	6a26328842	Support fp16 for Cosmos-Predict2 and Anima (#12249)	2026-02-06 20:12:15 -05:00
comfyanonymous	eba6c940fd	Make ace step 1.5 base model work properly with default workflow. (#12337)	2026-02-06 19:14:56 -05:00
comfyanonymous	458292fef0	Fix some lowvram stuff with ace step 1.5 (#12312)	2026-02-05 19:15:04 -05:00
comfyanonymous	6555dc65b8	Make ace step 1.5 work without the llm. (#12311)	2026-02-05 16:43:45 -05:00
comfyanonymous	a50c32d63f	Disable sage attention on ace step 1.5 (#12297)	2026-02-04 22:15:30 -05:00
comfyanonymous	6125b80979	Add llm sampling options and make reference audio work on ace step 1.5 (#12295)	2026-02-04 21:29:22 -05:00
comfyanonymous	3c1a1a2df8	Basic support for the ace step 1.5 model. (#12237)	2026-02-03 00:06:18 -05:00
rattus	f8acd9c402	Reduce RAM usage, fix VRAM OOMs, and fix Windows shared memory spilling with adaptive model loading (#11845)	2026-02-01 01:01:11 -05:00
comfyanonymous	b8f848bfe3	Fix model not working with any res. (#12186)	2026-01-31 00:12:48 -05:00
rattus	6516ab335d	wan-vae: Switch off feature cache for single frame (#12090) ... The code throughout is None safe to just skip the feature cache saving step if none. Set it none in single frame use so qwen doesn't burn VRAM on the unused cache.	2026-01-26 19:40:19 -05:00
comfyanonymous	635406e283	Only enable fp16 on z image models that actually support it. (#12065)	2026-01-24 22:32:28 -05:00
rattus	4e6a1b66a9	speed up and reduce VRAM of QWEN VAE and WAN (less so) (#12036) ... * ops: introduce autopad for conv3d This works around pytorch missing ability to causal pad as part of the kernel and avoids massive weight duplications for padding. * wan-vae: rework causal padding This currently uses F.pad which takes a full deep copy and is liable to be the VRAM peak. Instead, kick spatial padding back to the op and consolidate the temporal padding with the cat for the cache. * wan-vae: implement zero pad fast path The WAN VAE is also QWEN where it is used single-image. These convolutions are however zero padded 3d convolutions, which means the VAE is actually just 2D down the last element of the conv weight in the temporal dimension. Fast path this, to avoid adding zeros that then just evaporate in convoluton math but cost computation.	2026-01-23 19:56:14 -05:00
Jukka Seppänen	55bd606e92	LTX2: Refactor forward function for better VRAM efficiency and fix spatial inpainting (#12046) ... * Disable timestep embed compression when inpainting Spatial inpainting not compatible with the compression * Reduce crossattn peak VRAM * LTX2: Refactor forward function for better VRAM efficiency	2026-01-23 15:26:38 -05:00
Omri Marom	d7f3241bf6	qwen_image: propagate attention mask. (#11966)	2026-01-22 20:02:31 -05:00
rattus	0fd1b78736	Reduce LTX2 VAE VRAM consumption (#12028) ... * causal_video_ae: Remove attention ResNet This attention_head_dim argument does not exist on this constructor so this is dead code. Remove as generic attention mid VAE conflicts with temporal roll. * ltx-vae: consoldate causal/non-causal code paths * ltx-vae: add cache rolling adder * ltx-vae: use cached adder for resnet * ltx-vae: Implement rolling VAE Implement a temporal rolling VAE for the LTX2 VAE. Usually when doing temporal rolling VAEs you can just chunk on time relying on causality and cache behind you as you go. The LTX VAE is however non-causal. So go whole hog and implement per layer run ahead and backpressure between the decoder layers using recursive state beween the layers. Operations are ammended with temporal_cache_state{} which they can use to hold any state then need for partial execution. Convolutions cache their inputs behind the up to N-1 frames, and skip connections need to cache the mismatch between convolution input and output that happens due to missing future (non-causal) input. Each call to run_up() processes a layer accross a range on input that may or may not be complete. It goes depth first to process as much as possible to try and digest frames to the final output ASAP. If layers run out of input due to convolution losses, they simply return without action effectively applying back-pressure to the earlier layers. As the earlier layers do more work and caller deeper, the partial states are reconciled and output continues to digest depth first as much as possible. Chunking is done using a size quota rather than a fixed frame length and any layer can initiate chunking, and multiple layers can chunk at different granulatiries. This remove the old limitation of always having to process 1 latent frame to entirety and having to hold 8 full decoded frames as the VRAM peak.	2026-01-22 16:54:18 -05:00
Jukka Seppänen	16b9aabd52	Support Multi/InfiniteTalk (#10179) ... * re-init * Update model_multitalk.py * whitespace... * Update model_multitalk.py * remove print * this is redundant * remove import * Restore preview functionality * Move block_idx to transformer_options * Remove LoopingSamplerCustomAdvanced * Remove looping functionality, keep extension functionality * Update model_multitalk.py * Handle ref_attn_mask with separate patch to avoid having to always return q and k from self_attn * Chunk attention map calculation for multiple speakers to reduce peak VRAM usage * Update model_multitalk.py * Add ModelPatch type back * Fix for latest upstream * Use DynamicCombo for cleaner node Basically just so that single_speaker mode hides mask inputs and 2nd audio input * Update nodes_wan.py	2026-01-21 23:09:48 -05:00
comfyanonymous	abe2ec26a6	Support the Anima model. (#12012)	2026-01-21 19:44:28 -05:00
Ivan Zorin	965d0ed509	fix: remove normalization of audio in LTX Mel spectrogram creation (#11990) ... For LTX Audio VAE, remove normalization of audio during MEL spectrogram creation. This aligs inference with training and prevents loud audio from being attenuated.	2026-01-20 18:44:28 -05:00
comfyanonymous	8ccc0c94fa	Make omni stuff work on regular z image for easier testing. (#11985)	2026-01-20 00:32:00 -05:00
comfyanonymous	2108167f9f	Support zimage omni base model. (#11979)	2026-01-19 23:17:38 -05:00
rkfg	0da5a0fe58	Convert mono audio to fake stereo for LTXV VAE encoding (#11965)	2026-01-19 22:12:02 -05:00
Jukka Seppänen	fd5c0755af	Reduce LTX2 VRAM use by more efficient timestep embed handling (#11829)	2026-01-12 17:28:59 -05:00
comfyanonymous	1a20656448	Fix import issue. (#11746)	2026-01-08 17:23:59 -05:00
comfyanonymous	023cf13721	Fix lowvram issue with ltxv2 text encoder. (#11675)	2026-01-06 17:33:03 -05:00
comfyanonymous	c3c3e93c5b	Use rope functions from comfy kitchen. (#11674)	2026-01-06 16:57:50 -05:00
comfyanonymous	1618002411	Revert "Use rope functions from comfy kitchen. (#11647)" (#11648) ... This reverts commit 6ef85c4915.	2026-01-05 23:07:39 -05:00
comfyanonymous	6ef85c4915	Use rope functions from comfy kitchen. (#11647)	2026-01-05 22:50:35 -05:00
comfyanonymous	f2b002372b	Support the LTXV 2 model. (#11632)	2026-01-05 01:58:59 -05:00
comfyanonymous	65cfcf5b1b	New Year ruff cleanup. (#11595)	2026-01-01 22:06:14 -05:00
mengqin	0357ed7ec4	Add support for sage attention 3 in comfyui, enable via new cli arg (#11026) ... * Add support for sage attention 3 in comfyui, enable via new cli arg --use-sage-attiention3 * Fix some bugs found in PR review. The N dimension at which Sage Attention 3 takes effect is reduced to 1024 (although the improvement is not significant at this scale). * Remove the Sage Attention3 switch, but retain the attention function registration. * Fix a ruff check issue in attention.py	2025-12-30 22:53:52 -05:00
comfyanonymous	8fd07170f1	Comment out unused norm_final in lumina/z image model. (#11545)	2025-12-28 22:07:25 -05:00
comfyanonymous	31e961736a	Fix issue with batches and newbie. (#11435)	2025-12-20 00:23:51 -05:00
comfyanonymous	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
comfyanonymous	e4fb3a3572	Support loading Wan/Qwen VAEs with different in/out channels. (#11405)	2025-12-18 17:45:33 -05:00
comfyanonymous	ffdd53b327	Check state dict key to auto enable the index_timestep_zero ref method. (#11362)	2025-12-16 17:03:17 -05:00
comfyanonymous	bc606d7d64	Add a way to set the default ref method in the qwen image code. (#11349)	2025-12-16 01:26:55 -05:00
Haoming	ea2c117bc3	[BlockInfo] Wan (#10845) ... * block info * animate * tensor * device * revert	2025-12-15 17:59:16 -08:00
Haoming	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
comfyanonymous	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
comfyanonymous	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
Jukka Seppänen	e2a800e7ef	Fix for HunyuanVideo1.5 meanflow distil (#11212)	2025-12-09 16:59:16 -05:00
Lodestone	b9fb542703	add chroma-radiance-x0 mode (#11197)	2025-12-08 23:33:29 -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