Commit Graph

3768 Commits

Author SHA1 Message Date
Jedrzej Kosinski
e4f7ea105f Added context window support to core sampling code (#9238)
* Added initial support for basic context windows - in progress

* Add prepare_sampling wrapper for context window to more accurately estimate latent memory requirements, fixed merging wrappers/callbacks dicts in prepare_model_patcher

* Made context windows compatible with different dimensions; works for WAN, but results are bad

* Fix comfy.patcher_extension.merge_nested_dicts calls in prepare_model_patcher in sampler_helpers.py

* Considering adding some callbacks to context window code to allow extensions of behavior without the need to rewrite code

* Made dim slicing cleaner

* Add Wan Context WIndows node for testing

* Made context schedule and fuse method functions be stored on the handler instead of needing to be registered in core code to be found

* Moved some code around between node_context_windows.py and context_windows.py

* Change manual context window nodes names/ids

* Added callbacks to IndexListContexHandler

* Adjusted default values for context_length and context_overlap, made schema.inputs definition for WAN Context Windows less annoying

* Make get_resized_cond more robust for various dim sizes

* Fix typo

* Another small fix
2025-08-13 21:33:05 -04:00
Simon Lui
c991a5da65 Fix XPU iGPU regressions (#9322)
* Change bf16 check and switch non-blocking to off default with option to force to regain speed on certain classes of iGPUs and refactor xpu check.

* Turn non_blocking off by default for xpu.

* Update README.md for Intel GPUs.
2025-08-13 19:13:35 -04:00
comfyanonymous
9df8792d4b Make last PR not crash comfy on old pytorch. (#9324) 2025-08-13 15:12:41 -04:00
contentis
3da5a07510 SDPA backend priority (#9299) 2025-08-13 14:53:27 -04:00
comfyanonymous
afa0a45206 Reduce portable size again. (#9323)
* compress more

* test

* not needed
2025-08-13 14:42:08 -04:00
comfyanonymous
615eb52049 Put back frontend version. (#9317) 2025-08-13 03:48:06 -04:00
comfyanonymous
d5c1954d5c ComfyUI version 0.3.50 v0.3.50 2025-08-13 03:46:38 -04:00
comfyanonymous
e400f26c8f Downgrade frontend for release. (#9316) 2025-08-13 03:44:54 -04:00
comfyanonymous
5ca8e2fac3 Update release workflow to python3.13 pytorch cu129 (#9315)
* Try to reduce size of portable even more.

* Update stable release workflow to python 3.13 cu129

* Update dependencies workflow to python3.13 cu129
2025-08-13 03:01:12 -04:00
ComfyUI Wiki
3294782d19 Update template to 0.1.59 (#9313) 2025-08-13 02:50:50 -04:00
Jedrzej Kosinski
898d88e10e Make torchaudio exception catching less specific (#9309) 2025-08-12 23:34:58 -04:00
comfyanonymous
560d38f34c Wan2.2 fun control support. (#9292) 2025-08-12 23:26:33 -04:00
comfyanonymous
e1d4f36d8d Update test release package workflow with python 3.13 cu129. (#9306) 2025-08-12 20:13:04 -04:00
ComfyUI Wiki
1e3ae1eed8 Update template to 0.1.58 (#9302) 2025-08-12 17:14:27 -04:00
Alexander Piskun
f4231a80b1 fix(Kling Image API Node): do not pass "image_type" when no image (#9271)
* fix(Kling Image API Node): do not pass "image_type" when no image

* fix(Kling Image API Node): raise client-side error when kling_v1 is used with reference image
2025-08-11 17:15:14 -04:00
PsychoLogicAu
2208aa616d Support SimpleTuner lycoris lora for Qwen-Image (#9280) 2025-08-11 16:56:16 -04:00
ComfyUI Wiki
629b173837 Update template & embedded docs (#9283)
* Update template & embedded docs

* Update embedded docs to 0.2.6
2025-08-11 16:52:12 -04:00
Alexander Piskun
fa340add55 remove creation of non-used asyncio_loop (#9284) 2025-08-11 16:48:17 -04:00
comfyanonymous
966f3a5206 Only show feature flags log when verbose. (#9281) 2025-08-11 05:53:01 -04:00
comfyanonymous
0552de7c7d Bump pytorch cuda and rocm versions in readme instructions. (#9273) 2025-08-10 05:03:47 -04:00
comfyanonymous
5828607ccf Not sure if AMD actually support fp16 acc but it doesn't crash. (#9258) 2025-08-09 12:49:25 -04:00
comfyanonymous
735bb4bdb1 Users report gfx1201 is buggy on flux with pytorch attention. (#9244) 2025-08-08 04:21:00 -04:00
Alexander Piskun
bf2a1b5b1e async API nodes (#9129)
* converted API nodes to async

* converted BFL API nodes to async

* fixed client bug; converted gemini, ideogram, minimax

* fixed client bug; converted openai nodes

* fixed client bug; converted moonvalley, pika nodes

* fixed client bug; converted kling, luma nodes

* converted pixverse, rodin nodes

* converted tripo, veo2

* converted recraft nodes

* add lost log_request_response call
2025-08-07 23:37:50 -04:00
Jedrzej Kosinski
42974a448c _ui.py import torchaudio safety check (#9234)
* Added safety around torchaudio import in _ui.py

* Trusted cursor too much, fixed torchaudio bool
2025-08-07 17:54:09 -04:00
comfyanonymous
05df2df489 Fix RepeatLatentBatch not working on multi dim latents. (#9227) 2025-08-07 11:20:40 -04:00
Christian Byrne
37d620a6b8 Update frontend to v1.24.3 (#9175) 2025-08-06 19:52:39 -04:00
ComfyUI Wiki
32691b16f4 Update template to 0.1.52 (#9206) 2025-08-06 13:26:29 -04:00
flybirdxx
4c3e57b0ae Fixed an issue where qwenLora could not be loaded properly. (#9208) 2025-08-06 13:23:11 -04:00
comfyanonymous
9126c0cfe4 Qwen Image model merging node. (#9202) 2025-08-06 04:07:04 -04:00
comfyanonymous
d8c51ba15a Add Qwen Image model to readme. (#9191) 2025-08-05 07:41:18 -04:00
comfyanonymous
32a95bba8a ComfyUI version 0.3.49 v0.3.49 2025-08-05 07:33:02 -04:00
ComfyUI Wiki
da1ad9b516 Update template to 0.1.51 (#9187) 2025-08-05 07:24:12 -04:00
comfyanonymous
d044a24398 Fix default shift and any latent size for qwen image model. (#9186) 2025-08-05 06:12:27 -04:00
ComfyUI Wiki
5be6fd09ff Update template to 0.1.48 (#9182) 2025-08-05 03:48:56 -04:00
Christian Byrne
f69609bbd6 Add Veo3 video generation node with audio support (#9110)
- Create new Veo3VideoGenerationNode that extends VeoVideoGenerationNode
- Add support for generateAudio parameter (only for Veo3 models)
- Support new Veo3 models: veo-3.0-generate-001, veo-3.0-fast-generate-001
- Fix Veo3 duration constraint to 8 seconds only
- Update original node to be clearly Veo 2 only
- Update API paths to use model parameter: /proxy/veo/{model}/generate
- Regenerate API types from staging to include generateAudio parameter
- Fix TripoModelVersion enum reference after regeneration
- Mark generated API types file in .gitattributes
2025-08-05 01:52:25 -04:00
comfyanonymous
c012400240 Initial support for qwen image model. (#9179) 2025-08-04 22:53:25 -04:00
comfyanonymous
03895dea7c Fix another issue with the PR. (#9170) 2025-08-04 04:33:04 -04:00
comfyanonymous
84f9759424 Add some warnings and prevent crash when cond devices don't match. (#9169) 2025-08-04 04:20:12 -04:00
comfyanonymous
7991341e89 Various fixes for broken things from earlier PR. (#9168) 2025-08-04 04:02:40 -04:00
comfyanonymous
140ffc7fdc Fix broken controlnet from last PR. (#9167) 2025-08-04 03:28:12 -04:00
comfyanonymous
182f90b5ec Lower cond vram use by casting at the same time as device transfer. (#9159) 2025-08-04 03:11:53 -04:00
comfyanonymous
aebac22193 Cleanup. (#9160) 2025-08-03 07:08:11 -04:00
comfyanonymous
13aaa66ec2 Make sure context is on the right device. (#9154) 2025-08-02 15:09:23 -04:00
comfyanonymous
5f582a9757 Make sure all the conds are on the right device. (#9151) 2025-08-02 15:00:13 -04:00
ComfyUI Wiki
fbcc23945d Update template to 0.1.47 (#9153) 2025-08-02 14:15:29 -04:00
Johnpaul Chiwetelu
3dfefc88d0 API for Recently Used Items (#8792)
* feat: add file creation time to model file metadata and user file info

* fix linting
2025-08-01 22:02:06 -04:00
comfyanonymous
bff60b5cfc ComfyUI version 0.3.48 v0.3.48 2025-08-01 20:03:22 -04:00
comfyanonymous
1e638a140b Tiny wan vae optimizations. (#9136) 2025-08-01 05:25:38 -04:00
ComfyUI Wiki
4696d74305 update template to 0.1.45 (#9135) 2025-08-01 03:06:18 -04:00
comfyanonymous
5ee381c058 Fix WanFirstLastFrameToVideo node when no clip vision. (#9134) 2025-07-31 23:33:27 -04:00