xinyun/ComfyUI
1
0
Fork 0
mirror of https://git.datalinker.icu/comfyanonymous/ComfyUI synced 2026-08-16 03:23:32 +08:00
Code Issues Packages Projects Releases Wiki Activity
3,527 Commits 55 Branches 103 Tags
Commit Graph

3527 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
comfyanonymous
cd52c6352b Fix updater issue with newer portable. (#7917) 2025-05-03 00:28:10 -04:00
Terry Jia
4e982c1d01 upstream Preview Any from rgthree-comfy (#7815) 
* upstream Preview Any from rgthree-comfy

* use IO.ANY
 2025-05-02 13:15:54 -04:00
Chenlei Hu
48ca3a5b6d [BugFix] Update frontend 1.18.6 (#7910) 2025-05-02 13:14:52 -04:00
Kohaku-Blueleaf
204e96f2d3 Fix the bugs in OFT/BOFT moule (#7909) 
* Correct calculate_weight and load for OFT

* Correct calculate_weight and loading for BOFT
 2025-05-02 13:12:37 -04:00
catboxanon
a571b1b9c0 Fix outdated comment about Internet connectivity (#7827) 2025-05-02 05:28:27 -04:00
catboxanon
36faaff30d Add node to extend sigmas (#7901) 
* Add ExpandSigmas node

* Rename, add interpolation functions

Co-authored-by: liesen <liesen.dev@gmail.com>

* Move computed interpolation outside loop

* Add type hints

---------

Co-authored-by: liesen <liesen.dev@gmail.com>
 2025-05-02 05:28:05 -04:00
comfyanonymous
1b641f0e7f Make clipsave work with more TE models. (#7908) 2025-05-02 05:15:32 -04:00
catboxanon
eb38bf9103 Lint instance methods (#7903) 2025-05-01 19:32:04 -04:00
Chenlei Hu
efa88f4c6a Update frontend to v1.18 (#7898) 2025-05-01 10:57:54 -04:00
comfyanonymous
58c07d0def Switch ltxv to use the pytorch RMSNorm. (#7897) 2025-05-01 06:33:42 -04:00
Christian Byrne
319335b42a fix bug (#7894) 2025-05-01 03:24:32 -04:00
comfyanonymous
bedb911371 Cleanup chroma PR. 2025-04-30 20:57:30 -04:00
Silver
0a476dd474 Support for Chroma - Flux1 Schnell distilled with CFG (#7355) 
* Upload files for Chroma Implementation

* Remove trailing whitespace

* trim more trailing whitespace..oops

* remove unused imports

* Add supported_inference_dtypes

* Set min_length to 0 and remove attention_mask=True

* Set min_length to 1

* get_mdulations added from blepping and minor changes

* Add lora conversion if statement in lora.py

* Update supported_models.py

* update model_base.py

* add uptream commits

* set modelType.FLOW, will cause beta scheduler to work properly

* Adjust memory usage factor and remove unnecessary code

* fix mistake

* reduce code duplication

* remove unused imports

* refactor for upstream sync

* sync chroma-support with upstream via syncbranch patch

* Update sd.py

* Add Chroma as option for the OptimalStepsScheduler node
 2025-04-30 20:57:00 -04:00
comfyanonymous
e734ae0d28 Add updater test to stable release workflow. (#7887) 2025-04-30 14:42:18 -04:00
comfyanonymous
a31c296ccc Test updater in the windows release workflow. (#7886) 2025-04-30 14:18:20 -04:00
comfyanonymous
554a681864 Better vace memory estimation. (#7875) 2025-04-29 20:42:00 -04:00
comfyanonymous
42219515c6 Bump minimum pyav version to 14.2.0 (#7874) 2025-04-29 20:38:45 -04:00
comfyanonymous
0280886398 Per device stream counters for async offload. (#7873) 2025-04-29 20:28:52 -04:00
Terry Jia
d4abb04316 support more example folders (#7836) 
* support more example folders

* add warning message
 2025-04-29 11:28:04 -04:00
Chenlei Hu
308dc52796 Add release process section to README (#7855) 
* Add release process section to README

* move

* Update README.md
 2025-04-29 06:32:34 -04:00
comfyanonymous
8663298f2e Latest desktop and portable should work on blackwell. (#7861) 
Removed the mention about the cards from the readme.
 2025-04-29 06:29:38 -04:00
guill
a7fafcd751 Add support for VIDEO as a built-in type (#7844) 
* Add basic support for videos as types

This PR adds support for VIDEO as first-class types. In order to avoid
unnecessary costs, VIDEO outputs must implement the `VideoInput` ABC,
but their implementation details can vary. Included are two
implementations of this type which can be returned by other nodes:

* `VideoFromFile` - Created with either a path on disk (as a string) or
  a `io.BytesIO` containing the contents of a file in a supported format
  (like .mp4). This implementation won't actually load the video unless
  necessary. It will also avoid re-encoding when saving if possible.
* `VideoFromComponents` - Created from an image tensor and an optional
  audio tensor.

Currently, only h264 encoded videos in .mp4 containers are supported for
saving, but the plan is to add additional encodings/containers in the
near future (particularly .webm).

* Add optimization to avoid parsing entire video

* Improve type declarations to reduce warnings

* Make sure bytesIO objects can be read many times

* Fix a potential issue when saving long videos

* Fix incorrect type annotation

* Add a `LoadVideo` node to make testing easier

* Refactor new types out of the base comfy folder

I've created a new `comfy_api` top-level module. The intention is that
anything within this folder would be covered by semver-style versioning
that would allow custom nodes to rely on them not introducing breaking
changes.

* Fix linting issue
 2025-04-29 05:58:00 -04:00
comfyanonymous
87ca14eb5e Support HiDream E1 model. (#7857) 2025-04-28 15:01:15 -04:00
Yoland Yan
2544cec74a Add moderation level option to OpenAIGPTImage1 node and update api_call method signature (#7804) 2025-04-28 13:59:22 -04:00
chaObserv
4cc5ea895e CFG++ for gradient estimation sampler (#7809) 2025-04-28 13:51:35 -04:00
Andrew Kvochko
47fc21bf37 ltxv: overwrite existing mask on conditioned frame. (#7845) 
This commit overwrites the noise mask on the latent frame that is being
conditioned with keyframe conditioning, setting it to one.
 2025-04-28 13:42:04 -04:00
comfyanonymous
44ddce3a45 Fix stream priority to support older pytorch. (#7856) 2025-04-28 13:07:21 -04:00
Pam
31b1662657 Save v pred zsnr metadata (#7840) 2025-04-28 13:03:21 -04:00
Andrew Kvochko
69bd55bc4d ltxv: add strength parameter to conditioning. (#7849) 
This commit adds strength parameter to the LTXVImgToVideo node.
 2025-04-28 12:59:17 -04:00
Benjamin Lu
04473a89e5 Add /api/v2/userdata endpoint (#7817) 
* Add list_userdata_v2

* nit

* nit

* nit

* nit

* please set me free

* \\\\

* \\\\
 2025-04-27 20:06:55 -04:00
comfyanonymous
520b3c22e3 Use stream for casting if enabled. (#7833) 2025-04-27 05:38:11 -04:00
comfyanonymous
6d1455de3f Prevent custom nodes from hooking certain functions. (#7825) 2025-04-26 20:52:56 -04:00
comfyanonymous
06146cf019 Make loras work with --async-offload (#7824) 2025-04-26 19:56:22 -04:00
comfyanonymous
0782adba34 Add experimental --async-offload lowvram weight offloading. (#7820) 
This should speed up the lowvram mode a bit. It currently is only enabled when --async-offload is used but it will be enabled by default in the future if there are no problems.
 2025-04-26 16:11:21 -04:00
comfyanonymous
4876e56483 Update portable package workflow to cu128 (#7812) 2025-04-26 04:43:12 -04:00
comfyanonymous
11606962cf Add a T5TokenizerOptions node to set options for the T5 tokenizer. (#7803) 2025-04-25 19:36:00 -04:00
AustinMroz
364eb4c3f7 [NodeDef] Add documentation on widgetType (#7768) 
* [NodeDef] Add documentation on widgetType

* Document required version for widgetType
 2025-04-25 13:35:07 -04:00
comfyanonymous
53e7a5517f Support SimpleTuner lycoris lora format for HiDream. 2025-04-25 03:11:14 -04:00
comfyanonymous
20a7f2bf6a ComfyUI version 0.3.30 2025-04-24 16:03:01 -04:00
comfyanonymous
73546137a2 Switch LTXVPreprocess to libx264 (#7776) 2025-04-24 13:58:31 -04:00
thot experiment
b39ebf016c fix multiple image return from api nodes (#7772) 2025-04-24 03:29:05 -04:00
thot experiment
78d56f3232 throw away alpha channel in clip vision preprocessor (#7769) 
saves users having to explicitly discard the channel
 2025-04-23 21:28:36 -04:00
filtered
efb90e1bad [BugFix] Update frontend to 1.17.11 (#7766) 2025-04-23 18:16:12 -04:00
thot experiment
c48c759ec7 change timeout to 7 days (#7765) 2025-04-23 17:53:34 -04:00
thot experiment
93af0818ec implement multi image prompting for gpt-image-1 and fix transparency in outputs (#7763) 
* implement multi image prompting for GPTI Image 1

* fix transparency not working

* fix ruff
 2025-04-23 16:10:10 -04:00
filtered
35ce5255ca [BugFix] Update frontend to 1.17.10 (#7762) 2025-04-23 16:02:41 -04:00
Robin Huang
62b57302c1 Add support for API Nodes in ComfyUI. (#7726) 
* 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.

* separate out nodes per openai model

* Update error message.

* fix wrong output type

* re-categorize nodes, remove ideogram (for now)

* oops, fix mappings

* fix ruff

* Update frontend  to 1.17.9

* embargo lift rename nodes

* remove unused autogenerated model code

* fix API type error and add b64 support for 4o

* fix ruff

* oops forgot mask scaling code

* Remove unused types.

---------

Co-authored-by: bymyself <cbyrne@comfy.org>
Co-authored-by: Yoland Y <4950057+yoland68@users.noreply.github.com>
Co-authored-by: thot-experiment <thot@thiic.cc>
 2025-04-23 15:38:34 -04:00
comfyanonymous
c094c3c848 Lower size of release package more. (#7754) 2025-04-23 06:33:09 -04:00
comfyanonymous
7d83da5af8 Lower size of release package. (#7751) 2025-04-23 05:47:09 -04:00
comfyanonymous
8607868bde fp16 accumulation can now be enabled on the stable package. (#7750) 2025-04-23 05:28:24 -04:00