Commit Graph

4379 Commits

Author SHA1 Message Date
comfyanonymous
7eaff81be1
fp16 accumulation can now be enabled on the stable package. (#7750) 2025-04-23 05:28:24 -04:00
comfyanonymous
21a11ef817
Pytorch stable 2.7 is out and support cu128 (#7749) 2025-04-23 05:12:59 -04:00
comfyanonymous
552615235d
Fix for dino lowvram. (#7748) 2025-04-23 04:12:52 -04:00
Robin Huang
0738e4ea5d
[API nodes] Add backbone for supporting api nodes in ComfyUI (#7745)
* Add Ideogram generate node.

* Add staging api.

* COMFY_API_NODE_NAME node property

* switch to boolean flag and use original node name for id

* add optional to type

* Add API_NODE and common error for missing auth token (#5)

* Add Minimax Video Generation + Async Task queue polling example (#6)

* [Minimax] Show video preview and embed workflow in ouput (#7)

* [API Nodes] Send empty request body instead of empty dictionary. (#8)

* Fixed: removed function from rebase.

* Add pydantic.

* Remove uv.lock

* Remove polling operations.

* Update stubs workflow.

* Remove polling comments.

* Update stubs.

* Use pydantic v2.

* Use pydantic v2.

* Add basic OpenAITextToImage node

* Add.

* convert image to tensor.

* Improve types.

* Ruff.

* Push tests.

* Handle multi-form data.

- Don't set content-type for multi-part/form
- Use data field instead of JSON

* Change to api.comfy.org

* Handle error code 409.

* Remove nodes.

---------

Co-authored-by: bymyself <cbyrne@comfy.org>
Co-authored-by: Yoland Y <4950057+yoland68@users.noreply.github.com>
2025-04-23 02:18:08 -04:00
Alex Butler
92cdc692f4
Replace aom-av1 with svt-av1 for saving webm videos, use preset 6 + yuv420p10le pixel format (#7736)
* Add support for saving svt-av1 webm videos & yuv420p10le pixel format

* Replace aom-av1 with svt-av1

Use yuv420p10le for av1
2025-04-22 17:57:17 -04:00
comfyanonymous
2d6805ce57
Add option for using fp8_e8m0fnu for model weights. (#7733)
Seems to break every model I have tried but worth testing?
2025-04-22 06:17:38 -04:00
Kohaku-Blueleaf
a8f63c0d5b
Support dora_scale on both axis (#7727) 2025-04-22 05:01:27 -04:00
Terry Jia
454a635c1b
upstream MaskPreview from ComfyUI_essentials (#7719) 2025-04-22 05:00:28 -04:00
Kohaku-Blueleaf
966c43ce26
Add OFT/BOFT algorithm in weight adapter (#7725) 2025-04-22 04:59:47 -04:00
comfyanonymous
3ab231f01f
Fix issue with WAN VACE implementation. (#7724) 2025-04-21 23:36:12 -04:00
Kohaku-Blueleaf
1f3fba2af5
Unified Weight Adapter system for better maintainability and future feature of Lora system (#7540) 2025-04-21 20:15:32 -04:00
comfyanonymous
5d0d4ee98a
Add strength control for vace. (#7717) 2025-04-21 19:36:20 -04:00
Alexander G. Morano
9d57b8afd8
Update nodes_primitive.py (#7716)
Allow FLOAT and INT types to support negative numbers. 
Caps the numbers at the user's own system min and max.
2025-04-21 18:51:31 -04:00
filtered
5d51794607
Add node type hint for socketless option (#7714)
* Add node type hint for socketless option

* nit - Doc
2025-04-21 16:13:00 -04:00
comfyanonymous
ce22f687cc
Support for WAN VACE preview model. (#7711)
* Support for WAN VACE preview model.

* Remove print.
2025-04-21 14:40:29 -04:00
Chenlei Hu
b6fd3ffd10
Populate AUTH_TOKEN_COMFY_ORG hidden input (#7709) 2025-04-21 14:39:45 -04:00
comfyanonymous
11b72c9c55
CLIPTextEncodeHiDream. (#7703) 2025-04-21 02:41:51 -04:00
comfyanonymous
2c735c13b4
Slightly better fix for #7687 2025-04-20 11:33:27 -04:00
comfyanonymous
fd27494441 Use empty t5 of size 128 for hidream, seems to give closer results. 2025-04-19 19:49:40 -04:00
power88
f43e1d7f41
Hidream: Allow loading hidream text encoders in CLIPLoader and DualCLIPLoader (#7676)
* Hidream: Allow partial loading text encoders

* reformat code for ruff check.
2025-04-19 19:47:30 -04:00
Yoland Yan
4486b0d0ff
Update CODEOWNERS and add christian-byrne (#7663) 2025-04-19 17:23:31 -04:00
comfyanonymous
636d4bfb89 Fix hard crash when the spiece tokenizer path is bad. 2025-04-19 15:55:43 -04:00
Robin Huang
dc300a4569
Add wanfun template workflows. (#7678) 2025-04-19 15:21:46 -04:00
Chenlei Hu
f3b09b9f2d
[BugFix] Update frontend to 1.16.9 (#7655)
Backport https://github.com/Comfy-Org/ComfyUI_frontend/pull/3505
2025-04-18 15:12:42 -04:00
comfyanonymous
7ecd5e9614 Increase freq_cutoff in FreSca node. 2025-04-18 03:16:16 -04:00
City
2383a39e3b
Replace CLIPType if with getattr (#7589)
* Replace CLIPType if with getattr

* Forgot to remove breakpoint from testing
2025-04-18 02:53:36 -04:00
Terry Jia
34e06bf7ec
add support to output camera state (#7582) 2025-04-18 02:52:18 -04:00
Chenlei Hu
55822faa05
[Type] Annotate graph.get_input_info (#7386)
* [Type] Annotate graph.get_input_info

* nit

* nit
2025-04-17 21:02:24 -04:00
comfyanonymous
880c205df1 Add hidream to readme. 2025-04-17 16:58:27 -04:00
comfyanonymous
3dc240d089 Make fresca work on multi dim. 2025-04-17 15:46:41 -04:00
BVH
19373aee75
Add FreSca node (#7631) 2025-04-17 15:24:33 -04:00
comfyanonymous
93292bc450 ComfyUI version 0.3.29 2025-04-17 14:45:01 -04:00
Christian Byrne
05d5a75cdc
Update frontend to 1.16 (Install templates as pip package) (#7623)
* install templates as pip package

* Update requirements.txt

* bump templates version to include hidream

---------

Co-authored-by: Chenlei Hu <hcl@comfy.org>
2025-04-17 14:25:33 -04:00
comfyanonymous
eba7a25e7a Add WanFirstLastFrameToVideo node to use the new model. 2025-04-17 13:23:22 -04:00
comfyanonymous
dbcfd092a2 Set default context_img_len to 257 2025-04-17 12:42:34 -04:00
comfyanonymous
c14429940f Support loading WAN FLF model. 2025-04-17 12:04:48 -04:00
comfyanonymous
0d720e4367 Don't hardcode length of context_img in wan code. 2025-04-17 06:25:39 -04:00
comfyanonymous
1fc00ba4b6 Make hidream work with any latent resolution. 2025-04-16 18:34:14 -04:00
comfyanonymous
9899d187b1 Limit T5 to 128 tokens for HiDream: #7620 2025-04-16 18:07:55 -04:00
comfyanonymous
f00f340a56 Reuse code from flux model. 2025-04-16 17:43:55 -04:00
Chenlei Hu
cce1d9145e
[Type] Mark input options NotRequired (#7614) 2025-04-16 15:41:00 -04:00
codeflash-ai[bot]
72233ef320
️ Speed up function state_dict_prefix_replace by 127%
Here's an optimized version of your Python function. The primary changes are to minimize the creation of intermediate lists and to use dictionary comprehensions for more efficient data manipulation.



### Changes and Optimizations

1. **Avoid Unneeded List Creation:** 
   - Instead of mapping and filtering the keys in a separate step (`map` and `filter`), it is done directly in the list comprehension.
   
2. **Dictionary Comprehension**: 
   - By directly assigning `out` to `{}` or `state_dict`, it forgoes unnecessary intermediate steps in the conditional initialization.
   
3. **In-Loop Item Assignment**.
   - Keys to be replaced and corresponding operations are now handled directly within loops, reducing intermediate variable assignments.

This rewritten function should perform better, especially with large dictionaries, due to reduced overhead from list operations and more efficient key manipulation.
2025-04-16 10:21:07 +00:00
comfyanonymous
b4dc03ad76 Fix issue on old torch. 2025-04-16 04:53:56 -04:00
comfyanonymous
9ad792f927 Basic support for hidream i1 model. 2025-04-15 17:35:05 -04:00
comfyanonymous
6fc5dbd52a Cleanup. 2025-04-15 12:13:28 -04:00
comfyanonymous
3e8155f7a3 More flexible long clip support.
Add clip g long clip support.

Text encoder refactor.

Support llama models with different vocab sizes.
2025-04-15 10:32:21 -04:00
comfyanonymous
8a438115fb add RMSNorm to comfy.ops 2025-04-14 18:00:33 -04:00
comfyanonymous
a14c2fc356 ComfyUI version v0.3.28 2025-04-13 12:21:12 -07:00
JNP
9ee6ca99d8
add_optimalsteps (#7584)
Co-authored-by: bebebe666 <jianningpei@tencent.com>
2025-04-12 20:33:36 -04:00
comfyanonymous
bb495cc9b8 Print python version in log. 2025-04-12 18:58:34 -04:00