3498 Commits

Author SHA1 Message Date
Terry Jia
0769c8aef0 remove mtl from 3d model file list (#8192) 2025-05-22 08:08:36 -04:00
Chenlei Hu
23fa4f5026 Update frontend to 1.20 (#8232) 2025-05-22 02:24:36 -04:00
ComfyUI Wiki
a46b9e2344 Update templates to 0.1.18 (#8224) 2025-05-21 11:40:08 -07:00
Michael Abrahams
85064ded58 Improve performance with large number of queued prompts (#8176)
* get_current_queue_volatile

* restore get_current_queue method

* remove extra import
2025-05-21 05:14:17 -04:00
编程界的小学生
123a3488be Code Optimization and Issues Fixes in ComfyUI server (#8196)
* Update server.py

* Update server.py
2025-05-21 04:59:42 -04:00
Jedrzej Kosinski
34f46bad71 Make torch.compile LoRA/key-compatible (#8213)
* Make torch compile node use wrapper instead of object_patch for the entire diffusion_models object, allowing key assotiations on diffusion_models to not break (loras, getting attributes, etc.)

* Moved torch compile code into comfy_api so it can be used by custom nodes with a degree of confidence

* Refactor set_torch_compile_wrapper to support a list of keys instead of just diffusion_model, as well as additional torch.compile args

* remove unused import

* Moved torch compile kwargs to be stored in model_options instead of attachments; attachments are more intended for things to be 'persisted', AKA not deepcopied

* Add some comments

* Remove random line of code, not sure how it got there
2025-05-21 04:56:56 -04:00
comfyanonymous
4cea54c4fd ComfyUI version v0.3.35 2025-05-21 04:50:37 -04:00
comfyanonymous
5168070fe6 Revert "This doesn't seem to be needed on chroma. (#8209)" (#8210)
This reverts commit 121fceb8eebcfcaa0d4d0ee5aab3211019ac2ebe.
2025-05-20 05:39:55 -04:00
comfyanonymous
121fceb8ee This doesn't seem to be needed on chroma. (#8209) 2025-05-20 05:29:23 -04:00
filtered
d36d7c5842 Update README ROCm text to match link (#8199)
- Follow-up on #8198
2025-05-19 16:40:55 -04:00
comfyanonymous
3ed0dfb84a Update AMD instructions in README. (#8198) 2025-05-19 04:58:41 -04:00
comfyanonymous
cf69093825 Remove default delimiter. (#8183) 2025-05-18 04:12:12 -04:00
LaVie024
3b4dc3da41 Update nodes_string.py (#8173) 2025-05-18 04:11:11 -04:00
comfyanonymous
e045a2d2af Node to add pixel space noise to an image. (#8182) 2025-05-18 04:09:56 -04:00
Christian Byrne
7e907ad94b Validate video inputs (#8133)
* validate kling lip sync input video

* add tooltips

* update duration estimates

* decrease epsilon

* fix rebase error
2025-05-18 04:08:47 -04:00
Silver
e5ff43f323 Add missing category for T5TokenizerOption (#8177)
Change it if you need to but it should at least have a category.
2025-05-18 02:59:06 -04:00
comfyanonymous
ae3ac7caa8 Remove useless log. (#8166) 2025-05-17 06:27:34 -04:00
comfyanonymous
5e6b01ad20 Make ImagePadForOutpaint return a 3 channel mask. (#8157) 2025-05-16 15:15:55 -04:00
filtered
983898e890 Remove Desktop versioning claim from README (#8155) 2025-05-16 10:45:36 -07:00
comfyanonymous
5f8984cc01 Fix typo in last PR. (#8144)
More robust model detection for future proofing.
2025-05-15 19:02:19 -04:00
George0726
ed547131dd Add Wan-FUN Camera Control models and Add WanCameraImageToVideo node (#8013)
* support wan camera models

* fix by ruff check

* change camera_condition type; make camera_condition optional

* support camera trajectory nodes

* fix camera direction

---------

Co-authored-by: Qirui Sun <sunqr0667@126.com>
2025-05-15 19:00:43 -04:00
comfyanonymous
9fd77f81f7 Remove old hack used to fix windows pytorch 2.4 on the portable. (#8139)
Not necessary anymore.
2025-05-15 08:21:47 -04:00
Christian Byrne
f2f9729346 Add get_duration method to Comfy VIDEO type (#8122)
* get duration from VIDEO type

* video get_duration unit test

* fix Windows unit test: can't delete opened temp file
2025-05-15 00:11:41 -04:00
comfyanonymous
d55def67fe Update comment on ROCm pytorch attention in README. (#8123) 2025-05-14 17:54:50 -04:00
Christian Byrne
ce56e16b6d don't retry if API returns task failure (#8111) 2025-05-14 01:28:30 -04:00
Christian Byrne
7180ce940b Display progress and result URL directly on API nodes (#8102)
* [Luma] Print download URL of successful task result directly on nodes (#177)

[Veo] Print download URL of successful task result directly on nodes (#184)

[Recraft] Print download URL of successful task result directly on nodes (#183)

[Pixverse] Print download URL of successful task result directly on nodes (#182)

[Kling] Print download URL of successful task result directly on nodes (#181)

[MiniMax] Print progress text and download URL of successful task result directly on nodes (#179)

[Docs] Link to docs in `API_NODE` class property type annotation comment (#178)

[Ideogram] Print download URL of successful task result directly on nodes (#176)

[Kling] Print download URL of successful task result directly on nodes (#181)

[Veo] Print download URL of successful task result directly on nodes (#184)

[Recraft] Print download URL of successful task result directly on nodes (#183)

[Pixverse] Print download URL of successful task result directly on nodes (#182)

[MiniMax] Print progress text and download URL of successful task result directly on nodes (#179)

[Docs] Link to docs in `API_NODE` class property type annotation comment (#178)

[Luma] Print download URL of successful task result directly on nodes (#177)

[Ideogram] Print download URL of successful task result directly on nodes (#176)

Show output URL and progress text on Pika nodes (#168)

[BFL] Print download URL of successful task result directly on nodes (#175)

[OpenAI ] Print download URL of successful task result directly on nodes (#174)

* fix ruff errors

* fix 3.10 syntax error
2025-05-14 00:33:18 -04:00
thot experiment
f73c829fb3 rework client.py to be more robust, add logging of api requests (#7988)
* rework how errors are handled on the client side

* add logging to /temp

* fix ruff

* fix rebase, stupid vscode gui
2025-05-13 20:42:29 -04:00
comfyanonymous
7af90cc4c8 Hunyuan Custom initial untested implementation. (#8101) 2025-05-13 15:53:47 -04:00
thot experiment
527dc62ece fix negative momentum (#8100) 2025-05-13 10:50:32 -07:00
comfyanonymous
c593e84c4d Fix issue with old pytorch RMSNorm. (#8095) 2025-05-13 07:54:28 -04:00
comfyanonymous
6e86e1b648 Support official ACE Step loras. (#8094) 2025-05-13 07:32:16 -04:00
Christian Byrne
7019db90ab add comment about using api key in headless (#8082) 2025-05-12 23:06:44 -04:00
thot experiment
ee23f5733b implement APG guidance (#8081)
* first pass at impementing AGP

* rename, cleanup code

* fix ruff

* fix modified cond to match ref impl better, support different cond arity
2025-05-12 21:10:24 -04:00
Terry Jia
312edca570 add support to record video as output for 3d node (#7927)
* add support to record video as output for 3d node

* source format

* add support to record video for load3d animation node
2025-05-12 16:47:14 -04:00
Chenlei Hu
f3916dfcf2 Update frontend to v1.19 (#8076)
* Update frontend to v1.19

* Update requirements.txt
2025-05-12 16:47:02 -04:00
Terry Jia
49d371a4e4 string node (#7952) 2025-05-12 16:29:32 -04:00
thot experiment
9d774f5818 add opus and mp3 to audio output node (#8019)
* first pass at opus and mp3 as well as migrating flac to pyav

* minor mp3 encoding fix

* fix ruff

* delete dead code

* split out save audio to separate nodes per filetype

* fix ruff
2025-05-12 16:00:01 -04:00
comfyanonymous
a2f32f0122 ComfyUI version 0.3.34 2025-05-12 15:58:28 -04:00
comfyanonymous
b23a35bfe8 Fix torch warning about deprecated function. (#8075)
Drop support for torch versions below 2.2 on the audio VAEs.
2025-05-12 14:32:01 -04:00
Christian Byrne
b9cc0d4019 remove aspect ratio from kling request (#8062) 2025-05-12 13:32:24 -04:00
comfyanonymous
88e90694c3 ACE VAE works in fp16. (#8055) 2025-05-11 04:58:00 -04:00
Christian Byrne
01ee64ca26 Add support for Comfy API keys (#8041)
* Handle Comfy API key based authorizaton (#167)

Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>

* Bump frontend version to include API key features (#170)

* bump templates version

---------

Co-authored-by: Jedrzej Kosinski <kosinkadink1@gmail.com>
2025-05-10 22:10:58 -04:00
Christian Byrne
97f502c35a Add method to stream text to node UI (#8018)
* show text progress preview

* include node id in message
2025-05-10 20:40:02 -04:00
comfyanonymous
ecee5fe929 Fix issue with fp8 ops on some models. (#8045)
_scaled_mm errors when an input is non contiguous.
2025-05-10 07:52:56 -04:00
Pam
f459314eba Fix res_multistep_ancestral sampler (#8030) 2025-05-09 20:14:13 -04:00
Christian Byrne
99798972f0 update node tooltips and validation (#8036) 2025-05-09 20:02:45 -04:00
blepping
2d78e7c0af Use normal ComfyUI attention in ACE-Steps model (#8023)
* Use normal ComfyUI attention in ACE-Steps model

* Let optimized_attention handle output reshape for ACE
2025-05-09 13:51:02 -04:00
thot experiment
0a5ca1c2e5 move SVG to core (#7982)
* move SVG to core

* fix workflow embedding w/ unicode characters
2025-05-09 13:46:34 -04:00
comfyanonymous
79edf6d03e Add --mmap-torch-files to enable use of mmap when loading ckpt/pt (#8021) 2025-05-09 04:52:47 -04:00
comfyanonymous
8c8e9716e9 Add ACE Step to README. (#8005) 2025-05-08 08:40:57 -04:00