wangbo/ComfyUI
1
0
Fork 0
mirror of https://github.com/comfyanonymous/ComfyUI.git synced 2026-07-21 23:41:28 +08:00
Code Issues Actions 10 Packages Projects Releases Wiki Activity
3,846 Commits 305 Branches 166 Tags
810c3032104d31a6e3fa0311c6837c4b5cace2b7
Commit Graph
1827 Commits
Author SHA1 Message Date
doctorpangloss 810c303210 Remove web directory from package 2025-03-05 14:05:18 -08:00
doctorpangloss 8d2d613f95 Move language extensions in order to support packagized frontend 2025-03-05 10:39:31 -08:00
doctorpangloss d82261485f Prompt upsampling, better torch.compile support for language models 2025-03-03 18:36:47 -08:00
doctorpangloss c6111fae7d Fix Pixtral 12b compatibility 2025-03-03 13:07:36 -08:00
doctorpangloss 048746f58b Update to 0.3.15 and improve models 
- Cosmos now fully tested
 - Preliminary support for essential Cosmos prompt "upsampler"
 - Lumina tests
 - Tweaks to language and image resizing nodes
 - Fix for #31 all the samplers are now present again
 2025-02-24 21:27:15 -08:00
doctorpangloss 693038738a Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2025-02-24 09:39:26 -08:00
comfyanonymous 96d891cb94 Speedup on some models by not upcasting bfloat16 to float32 on mac. 2025-02-24 05:41:32 -05:00
comfyanonymous ace899e71a Prioritize fp16 compute when using allow_fp16_accumulation 2025-02-23 04:45:54 -05:00
comfyanonymous aff16532d4 Remove some useless code. 2025-02-22 04:45:14 -05:00
comfyanonymous 072db3bea6 Assume the mac black image bug won't be fixed before v16. 2025-02-21 20:24:07 -05:00
comfyanonymous a6deca6d9a Latest mac still has the black image bug. 2025-02-21 20:14:30 -05:00
comfyanonymous 41c30e92e7 Let all model memory be offloaded on nvidia. 2025-02-21 06:32:21 -05:00
comfyanonymous 12da6ef581 Apparently directml supports fp16. 2025-02-20 09:30:24 -05:00
SilverandGitHub c5be423d6b Fix link pointing to non-exisiting docs (#6891) 
* Fix link pointing to non-exisiting docs

The current link is pointing to a path that does not exist any longer.
I changed it to point to the currect correct path for custom nodes datatypes.

* Update node_typing.py
 2025-02-20 07:07:07 -05:00
maedtbandGitHub 5715be2ca9 Fix Hunyuan unet config detection for some models. (#6877) 
The change to support 32 channel hunyuan models is missing the `key_prefix` on the key.

This addresses a complain in the comments of acc152b674.
 2025-02-19 07:14:45 -05:00
Benjamin Berman 83ae94b96c Fix absolute import 2025-02-18 20:09:56 -08:00
Benjamin Berman 1e74a4cf08 Fix absolute imports, fix linting issue with dataclass 2025-02-18 19:59:09 -08:00
Benjamin Berman ffc6a7fd38 Use spawn multiprocessing context to fix Linux ProcessPool issues 2025-02-18 19:46:57 -08:00
doctorpangloss e65faca817 Distributed setup now defaults to panicking when out of memory now, to facilitate graceful recovery 2025-02-18 15:07:02 -08:00
bymyselfandGitHub afc85cdeb6 Add Load Image Output node (#6790) 
* add LoadImageOutput node

* add route for input/output/temp files

* update node_typing.py

* use literal type for image_folder field

* mark node as beta
 2025-02-18 17:53:01 -05:00
doctorpangloss 3ddec8ae90 Better support for process pool executors 
- --panics-when=torch.cuda.OutOfMemory will now correctly panic and
   exit the worker, giving it time to reply that the execution failed
   and better dealing with irrecoverable out-of-memory errors
 - --executor-factory=ProcessPoolExecutor will use a process instead of
   a thread to execute comfyui workflows when using the worker. When
   this process panics and exits, it will be correctly replaced, making
   a more robust worker
 2025-02-18 14:37:20 -08:00
Jukka SeppänenandGitHub acc152b674 Support loading and using SkyReels-V1-Hunyuan-I2V (#6862) 
* Support SkyReels-V1-Hunyuan-I2V

* VAE scaling

* Fix T2V

oops

* Proper latent scaling
 2025-02-18 17:06:54 -05:00
doctorpangloss 684d180446 Users can now configure their workers to panic if they have out of memory exceptions, which occur due to complex failures in custom nodes 2025-02-18 10:57:23 -08:00
comfyanonymous b07258cef2 Fix typo. 
Let me know if this slows things down on 2000 series and below.
 2025-02-18 07:28:33 -05:00
comfyanonymous 31e54b7052 Improve AMD arch detection. 2025-02-17 04:53:40 -05:00
comfyanonymous 8c0bae50c3 bf16 manual cast works on old AMD. 2025-02-17 04:42:40 -05:00
comfyanonymous 530412cb9d Refactor torch version checks to be more future proof. 2025-02-17 04:36:45 -05:00
doctorpangloss d04288ce8d ImagePadForOutpaint now correctly returns a MaskBatch 2025-02-16 15:39:36 -08:00
comfyanonymous e2919d38b4 Disable bf16 on AMD GPUs that don't support it. 2025-02-16 05:46:10 -05:00
doctorpangloss 0ca30c3c87 export_custom_nodes now handles abstract base classes better 2025-02-14 15:36:51 -08:00
doctorpangloss f4e65590b8 Fix subfolder being None when images are viewed 2025-02-14 07:20:58 -08:00
comfyanonymous 1cd6cd6080 Disable pytorch attention in VAE for AMD. 2025-02-14 05:42:14 -05:00
comfyanonymous d7b4bf21a2 Auto enable mem efficient attention on gfx1100 on pytorch nightly 2.7 
I'm not not sure which arches are supported yet. If you see improvements in
memory usage while using --use-pytorch-cross-attention on your AMD GPU let
me know and I will add it to the list.
 2025-02-14 04:18:14 -05:00
comfyanonymous 019c7029ea Add a way to set a different compute dtype for the model at runtime. 
Currently only works for diffusion models.
 2025-02-13 20:34:03 -05:00
comfyanonymous 8773ccf74d Better memory estimation for ROCm that support mem efficient attention. 
There is no way to check if the card actually supports it so it assumes
that it does if you use --use-pytorch-cross-attention with yours.
 2025-02-13 08:32:36 -05:00
doctorpangloss 31b6b53236 Quality of life improvements 
- export_custom_nodes() finds all the classes that inherit from
   CustomNode and exports them correctly for custom node discovery to
   find
 - regular expressions
 - additional string formatting and parsing nodes
 2025-02-12 14:12:10 -08:00
comfyanonymous 1d5d6586f3 Fix ruff. 2025-02-12 06:49:16 -05:00
zhoufan2956andGitHub 35740259de mix_ascend_bf16_infer_err (#6794) 2025-02-12 06:48:11 -05:00
comfyanonymous ab888e1e0b Add add_weight_wrapper function to model patcher. 
Functions can now easily be added to wrap/modify model weights.
 2025-02-12 05:55:35 -05:00
comfyanonymous d9f0fcdb0c Cleanup. 2025-02-11 17:17:03 -05:00
HishamCandGitHub b124256817 Fix for running via DirectML (#6542) 
* Fix for running via DirectML

Fix DirectML empty image generation issue with Flux1. add CPU fallback for unsupported path. Verified the model works on AMD GPUs

* fix formating

* update casual mask calculation
 2025-02-11 17:11:32 -05:00
comfyanonymous af4b7c91be Make --force-fp16 actually force the diffusion model to be fp16. 2025-02-11 08:33:09 -05:00
comfyanonymous 4027466c80 Make lumina model work with any latent resolution. 2025-02-10 00:24:20 -05:00
comfyanonymous 095d867147 Remove useless function. 2025-02-09 07:02:57 -05:00
PamandGitHub caeb27c3a5 res_multistep: Fix cfgpp and add ancestral samplers (#6731) 2025-02-08 19:39:58 -05:00
comfyanonymous 3d06e1c555 Make error more clear to user. 2025-02-08 18:57:24 -05:00
catboxanonandGitHub 43a74c0de1 Allow FP16 accumulation with --fast (#6453) 
Currently only applies to PyTorch nightly releases. (>=20250208)
 2025-02-08 17:00:56 -05:00
comfyanonymous 079eccc92a Don't compress http response by default. 
Remove argument to disable it.

Add new --enable-compress-response-body argument to enable it.
 2025-02-07 03:29:21 -05:00
doctorpangloss ef74b9fdda More graceful health check handling of this connection not being ready 2025-02-06 11:08:09 -08:00
doctorpangloss 5b3eb2e51c Fix torch.zeroes error 2025-02-06 09:00:10 -08:00