Commit Graph

3867 Commits

Author SHA1 Message Date
Jacob Segal
e9db9554bd ACTUALLY skip timing checks in CI 2025-09-03 12:30:44 -07:00
Jacob Segal
98be8e1969 Whoops, reverted a change in the last commit 2025-09-03 12:21:13 -07:00
Jacob Segal
766ff74207 Just disable timing-related assertions in CI
That way there's no risk of periodic non-deterministic test failures.
2025-09-03 12:18:48 -07:00
Jacob Segal
b1b5f87534 Add more leeway on async tests for Windows CI 2025-09-02 23:43:15 -07:00
Jacob Segal
cf45fd1742 Add missing test modules 2025-09-02 23:21:43 -07:00
Jacob Segal
e7314f49e6 Fix showing progress from other sessions
Because `client_id` was missing from ths `progress_state` message, it
was being sent to all connected sessions. This technically meant that if
someone had a graph with the same nodes, they would see the progress
updates for others.

Also added a test to prevent reoccurance and moved the tests around to
make CI easier to hook up.
2025-09-02 23:17:26 -07:00
contentis
e2d1e5dad9 Enable Convolution AutoTuning (#9301) 2025-09-01 20:33:50 -04:00
comfyanonymous
27e067ce50 Implement the USO subject identity lora. (#9674)
Use the lora with FluxContextMultiReferenceLatentMethod node set to "uso"
and a ReferenceLatent node with the reference image.
2025-09-01 18:54:02 -04:00
comfyanonymous
9b15155972 Probably not necessary anymore. (#9646) 2025-08-31 01:32:10 -04:00
chaObserv
32a627bf1f SEEDS: update noise decomposition and refactor (#9633)
- Update the decomposition to reflect interval dependency
- Extract phi computations into functions
- Use torch.lerp for interpolation
2025-08-31 00:01:45 -04:00
Alexander Piskun
fe442fac2e convert Primitive nodes to V3 schema (#9372) 2025-08-30 23:21:58 -04:00
Alexander Piskun
d2c502e629 convert nodes_stability.py to V3 schema (#9497) 2025-08-30 23:20:17 -04:00
Alexander Piskun
fea9ea8268 convert Video nodes to V3 schema (#9489) 2025-08-30 23:19:54 -04:00
Alexander Piskun
f949094b3c convert Stable Cascade nodes to V3 schema (#9373) 2025-08-30 23:19:21 -04:00
comfyanonymous
4449e14769 ComfyUI version 0.3.56 v0.3.56 2025-08-30 06:31:19 -04:00
comfyanonymous
885015eecf Lower ram usage on windows. (#9628) 2025-08-29 23:06:04 -04:00
comfyanonymous
a86aaa4301 ComfyUI v0.3.55 v0.3.55 2025-08-29 06:03:41 -04:00
ComfyUI Wiki
2efb2cbc38 Update template to 0.1.70 (#9620) 2025-08-29 06:03:25 -04:00
comfyanonymous
15aa9222c4 Trim audio to video when saving video. (#9617) 2025-08-29 04:12:00 -04:00
comfyanonymous
c7bb3e2bce Support the 5B fun inpaint model. (#9614)
Use the WanFunInpaintToVideo node without the clip_vision_output.
2025-08-28 22:46:57 -04:00
comfyanonymous
e80a14ad50 Support wan2.2 5B fun control model. (#9611)
Use the Wan22FunControlToVideo node.
2025-08-28 22:13:07 -04:00
comfyanonymous
d28b39d93d Add a LatentCut node to cut latents. (#9609) 2025-08-28 19:38:28 -04:00
comfyanonymous
1c184c29eb Fix issue with s2v node when extending past audio length. (#9608) 2025-08-28 18:34:01 -04:00
comfyanonymous
edde0b5043 WanSoundImageToVideoExtend node to manually extend s2v video. (#9606) 2025-08-28 17:59:48 -04:00
comfyanonymous
0063610177 ComfyUI version 0.3.54 v0.3.54 2025-08-28 10:44:57 -04:00
comfyanonymous
ce0052c087 Fix diffsynth controlnet regression. (#9597) 2025-08-28 10:37:42 -04:00
comfyanonymous
0eb821a7b6 ComfyUI 0.3.53 v0.3.53 2025-08-27 23:09:06 -04:00
comfyanonymous
4aa79dbf2c Adjust flux mem usage factor a bit. (#9588) 2025-08-27 23:08:17 -04:00
comfyanonymous
38f697d953 Add a LatentConcat node. (#9587) 2025-08-27 22:28:10 -04:00
Gangin Park
3aad339b63 Add DPM++ 2M SDE Heun (RES) sampler (#9542) 2025-08-27 19:07:31 -04:00
comfyanonymous
491755325c Better s2v memory estimation. (#9584) 2025-08-27 19:02:42 -04:00
comfyanonymous
496888fd68 Improve s2v performance when generating videos longer than 120 frames. (#9582) 2025-08-27 16:06:40 -04:00
comfyanonymous
b5ac6ed7ce Fixes to make controlnet type models work on qwen edit and kontext. (#9581) 2025-08-27 15:26:28 -04:00
Kohaku-Blueleaf
b20ba1f27c Fix #9537 (#9576) 2025-08-27 12:45:02 -04:00
comfyanonymous
31a37686d0 Negative audio in s2v should be zeros. (#9578) 2025-08-27 12:44:29 -04:00
comfyanonymous
88aee596a3 WIP Wan 2.2 S2V model. (#9568) 2025-08-27 01:10:34 -04:00
ComfyUI Wiki
6a193ac557 Update template to 0.1.68 (#9569)
* Update template to 0.1.67

* Update template to 0.1.68
2025-08-27 00:10:20 -04:00
Jedrzej Kosinski
47f4db3e84 Adding Google Gemini Image API node (#9566)
* bigcat88's progress on adding Google Gemini Image node

* Made Google Gemini Image node functional

* Bump frontend version to get static pricing badge on Gemini Image node
2025-08-26 22:20:44 -04:00
ComfyUI Wiki
5352abc6d3 Update template to 0.1.66 (#9557) 2025-08-26 13:33:54 -04:00
comfyanonymous
39aa06bd5d Make AudioEncoderOutput usable in v3 node schema. (#9554) 2025-08-26 12:50:46 -04:00
comfyanonymous
914c2a2973 Implement wav2vec2 as an audio encoder model. (#9549)
This is useless on its own but there are multiple models that use it.
2025-08-25 23:26:47 -04:00
comfyanonymous
e633a47ad1 Add models/audio_encoders directory. (#9548) 2025-08-25 20:13:54 -04:00
comfyanonymous
f6b93d41a0 Remove models from readme that are not fully implemented. (#9535)
Cosmos model implementations are currently missing the safety part so it is technically not fully implemented and should not be advertised as such.
2025-08-24 15:40:32 -04:00
blepping
95ac7794b7 Fix EasyCache/LazyCache crash when tensor shape/dtype/device changes during sampling (#9528)
* Fix EasyCache/LazyCache crash when tensor shape/dtype/device changes during sampling

* Fix missing LazyCache check_metadata method
Ensure LazyCache reset method resets all the tensor state values
2025-08-24 15:29:49 -04:00
comfyanonymous
71ed4a399e ComfyUI version 0.3.52 v0.3.52 2025-08-23 18:57:09 -04:00
Christian Byrne
3e316c6338 Update frontend to v1.25.10 and revert navigation mode override (#9522)
- Update comfyui-frontend-package from 1.25.9 to 1.25.10
- Revert forced legacy navigation mode from PR #9518
- Frontend v1.25.10 includes proper navigation mode fixes and improved display text
2025-08-23 17:54:01 -04:00
comfyanonymous
8be0d22ab7 Don't use the annoying new navigation mode by default. (#9518) 2025-08-23 13:56:17 -04:00
comfyanonymous
59eddda900 Python 3.13 is well supported. (#9511) 2025-08-23 01:36:44 -04:00
comfyanonymous
41048c69b4 Fix Conditioning masks on 3d latents. (#9506) 2025-08-22 23:15:44 -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