19 Commits

Author SHA1 Message Date
comfyanonymous
c4a6b389de
Lower ltxv mem usage to what it was before previous pr. (#10643)
Bring back qwen behavior to what it was before previous pr.
2025-11-04 22:47:35 -05:00
contentis
4cd881866b
Use single apply_rope function across models (#10547) 2025-11-04 20:10:11 -05:00
Jedrzej Kosinski
d7f40442f9
Enable Runtime Selection of Attention Functions (#9639)
* Looking into a @wrap_attn decorator to look for 'optimized_attention_override' entry in transformer_options

* Created logging code for this branch so that it can be used to track down all the code paths where transformer_options would need to be added

* Fix memory usage issue with inspect

* Made WAN attention receive transformer_options, test node added to wan to test out attention override later

* Added **kwargs to all attention functions so transformer_options could potentially be passed through

* Make sure wrap_attn doesn't make itself recurse infinitely, attempt to load SageAttention and FlashAttention if not enabled so that they can be marked as available or not, create registry for available attention

* Turn off attention logging for now, make AttentionOverrideTestNode have a dropdown with available attention (this is a test node only)

* Make flux work with optimized_attention_override

* Add logs to verify optimized_attention_override is passed all the way into attention function

* Make Qwen work with optimized_attention_override

* Made hidream work with optimized_attention_override

* Made wan patches_replace work with optimized_attention_override

* Made SD3 work with optimized_attention_override

* Made HunyuanVideo work with optimized_attention_override

* Made Mochi work with optimized_attention_override

* Made LTX work with optimized_attention_override

* Made StableAudio work with optimized_attention_override

* Made optimized_attention_override work with ACE Step

* Made Hunyuan3D work with optimized_attention_override

* Make CosmosPredict2 work with optimized_attention_override

* Made CosmosVideo work with optimized_attention_override

* Made Omnigen 2 work with optimized_attention_override

* Made StableCascade work with optimized_attention_override

* Made AuraFlow work with optimized_attention_override

* Made Lumina work with optimized_attention_override

* Made Chroma work with optimized_attention_override

* Made SVD work with optimized_attention_override

* Fix WanI2VCrossAttention so that it expects to receive transformer_options

* Fixed Wan2.1 Fun Camera transformer_options passthrough

* Fixed WAN 2.1 VACE transformer_options passthrough

* Add optimized to get_attention_function

* Disable attention logs for now

* Remove attention logging code

* Remove _register_core_attention_functions, as we wouldn't want someone to call that, just in case

* Satisfy ruff

* Remove AttentionOverrideTest node, that's something to cook up for later
2025-09-12 18:07:38 -04:00
Jedrzej Kosinski
fc247150fe
Implement EasyCache and Invent LazyCache (#9496)
* Attempting a universal implementation of EasyCache, starting with flux as test; I screwed up the math a bit, but when I set it just right it works.

* Fixed math to make threshold work as expected, refactored code to use EasyCacheHolder instead of a dict wrapped by object

* Use sigmas from transformer_options instead of timesteps to be compatible with a greater amount of models, make end_percent work

* Make log statement when not skipping useful, preparing for per-cond caching

* Added DIFFUSION_MODEL wrapper around forward function for wan model

* Add subsampling for heuristic inputs

* Add subsampling to output_prev (output_prev_subsampled now)

* Properly consider conds in EasyCache logic

* Created SuperEasyCache to test what happens if caching and reuse is moved outside the scope of conds, added PREDICT_NOISE wrapper to facilitate this test

* Change max reuse_threshold to 3.0

* Mark EasyCache/SuperEasyCache as experimental (beta)

* Make Lumina2 compatible with EasyCache

* Add EasyCache support for Qwen Image

* Fix missing comma, curse you Cursor

* Add EasyCache support to AceStep

* Add EasyCache support to Chroma

* Added EasyCache support to Cosmos Predict t2i

* Make EasyCache not crash with Cosmos Predict ImagToVideo latents, but does not work well at all

* Add EasyCache support to hidream

* Added EasyCache support to hunyuan video

* Added EasyCache support to hunyuan3d

* Added EasyCache support to LTXV (not very good, but does not crash)

* Implemented EasyCache for aura_flow

* Renamed SuperEasyCache to LazyCache, hardcoded subsample_factor to 8 on nodes

* Eatra logging when verbose is true for EasyCache
2025-08-22 22:41:08 -04:00
Harel Cain
9bc2798f72
LTXV VAE decoder: switch default padding mode (#8930) 2025-07-16 13:54:38 -04:00
comfyanonymous
7ea79ebb9d
Add correct eps to ltxv rmsnorm. (#8542) 2025-06-15 12:21:25 -04:00
comfyanonymous
aa9d759df3
Switch ltxv to use the pytorch RMSNorm. (#7897) 2025-05-01 06:33:42 -04:00
comfyanonymous
369b079ff6 Fix lowvram issue with ltxv vae. 2025-03-05 05:26:08 -05:00
comfyanonymous
93fedd92fe Support LTXV 0.9.5.
Credits: Lightricks team.
2025-03-05 00:13:49 -05:00
comfyanonymous
ff838657fa Cleaner handling of attention mask in ltxv model code. 2025-01-09 07:12:03 -05:00
comfyanonymous
80f07952d2 Fix lowvram issue with ltxv vae. 2024-12-22 23:20:17 -05:00
comfyanonymous
da13b6b827 Get rid of meshgrid warning. 2024-12-20 18:02:12 -05:00
comfyanonymous
418eb7062d Support new LTXV VAE. 2024-12-20 04:38:29 -05:00
Chenlei Hu
0fd4e6c778
Lint unused import (#5973)
* Lint unused import

* nit

* Remove unused imports

* revert fix_torch import

* nit
2024-12-09 15:24:39 -05:00
comfyanonymous
8af9a91e0c A few improvements to #5937. 2024-12-06 05:49:15 -05:00
Michael Kupchick
005d2d3a13
ltxv: add noise to guidance image to ensure generated motion. (#5937) 2024-12-06 05:46:08 -05:00
comfyanonymous
ab885b33ba Skip layer guidance node now works on LTX-Video. 2024-11-23 10:33:05 -05:00
comfyanonymous
e5c3f4b87f LTXV lowvram fixes. 2024-11-22 17:17:11 -05:00
comfyanonymous
5e16f1d24b Support Lightricks LTX-Video model. 2024-11-22 08:46:39 -05:00