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
2,480 Commits 305 Branches 166 Tags
8a1557f75055b7c74bc7d832612c535d88e47d77
Commit Graph
2480 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
doctorpangloss a79ccd625f bf16 selection for AMD 2024-05-22 22:45:15 -07:00
comfyanonymous 6507a9c716 Remove the CTRL-Delete keybind. 
On some keyboards it's apparently too easy to accidentally do CTRL-Delete
when pressing CTRL-Enter repeatedly.

CTRL-Backspace can still be used to clear the workflow.
 2024-05-23 01:29:22 -04:00
doctorpangloss 35cf996b68 ROCm 6.0 seems to require get_device_name to be called before memory methods in order to return valid data 2024-05-22 22:09:07 -07:00
doctorpangloss bb159a219e Fix pip 22 bug, prefer vendor index URLs over PyPi 2024-05-22 21:26:44 -07:00
doctorpangloss c0fc1d1458 Add pytorch-triton-rocm to dependencies when targeting AMD because accelerate needs to find it in the rocm repo 2024-05-22 21:21:23 -07:00
doctorpangloss 0fcd07962f Add Intel, AMD Linux Dockerfiles, improve error messages on AMD 2024-05-22 21:16:34 -07:00
comfyanonymous 6c23854f54 Fix OSX latent2rgb previews. 2024-05-22 13:56:28 -04:00
Chenlei HuandGitHub 7718ada4ed Add type annotation UnetWrapperFunction (#3531) 
* Add type annotation UnetWrapperFunction

* nit

* Add types.py
 2024-05-22 02:07:27 -04:00
comfyanonymous 8508df2569 Work around black image bug on Mac 14.5 by forcing attention upcasting. 2024-05-21 16:56:33 -04:00
doctorpangloss b241ecc56d Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2024-05-21 11:38:24 -07:00
doctorpangloss 5b9eadc165 WIP documentation work 2024-05-21 11:38:20 -07:00
comfyanonymous 83d969e397 Disable xformers when tracing model. 2024-05-21 13:55:49 -04:00
doctorpangloss f69b6225c0 Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2024-05-20 12:06:35 -07:00
comfyanonymous 1900e5119f Fix potential issue. 2024-05-20 08:19:54 -04:00
comfyanonymous 276f8fce9f Print error when node is missing. 2024-05-20 07:04:08 -04:00
Dr.Lt.DataandGitHub 4bc1884478 Provide a better error message when attempting to execute the workflow with a missing node. (#3517) 2024-05-20 06:58:46 -04:00
comfyanonymous 09e069ae6c Log the pytorch version. 2024-05-20 06:22:29 -04:00
comfyanonymous 11a2ad5110 Fix controlnet not upcasting on models that have it enabled. 2024-05-19 17:58:03 -04:00
comfyanonymous 4ae1515f14 Slightly faster latent2rgb previews. 2024-05-19 17:42:35 -04:00
comfyanonymous f37a47110b Make --preview-method auto default to the fast latent2rgb previews. 2024-05-19 11:45:36 -04:00
comfyanonymous 0bdc2b15c7 Cleanup. 2024-05-18 10:11:44 -04:00
comfyanonymous 98f828fad9 Remove unnecessary code. 2024-05-18 09:36:44 -04:00
doctorpangloss 519cddcefc Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2024-05-17 14:04:44 -07:00
doctorpangloss 3f69a6cf1e Skip test related to freezing time 2024-05-17 14:01:55 -07:00
comfyanonymous 1c4af5918a Better error message if the webcam node doesn't work. 2024-05-17 14:02:09 -04:00
pythongosssssandGitHub 91590adf04 Add webcam node (#3497) 
* Add webcam node

* unused import
 2024-05-17 13:16:08 -04:00
doctorpangloss acd98ceef3 Further fixes to unit tests when running in GitHub 2024-05-17 10:12:23 -07:00
doctorpangloss cb45b86b63 Patch torch device code here 2024-05-17 07:19:15 -07:00
doctorpangloss 4eb66f8a0a Fix clip clone bug 2024-05-17 07:17:33 -07:00
comfyanonymous 19300655dd Don't automatically switch to lowvram mode on GPUs with low memory. 2024-05-17 00:31:32 -04:00
doctorpangloss b318b4cc28 Update tests to support CPU in GitHub 2024-05-16 15:31:55 -07:00
doctorpangloss 87d1f30902 Some base nodes now have unit tests 2024-05-16 15:01:51 -07:00
doctorpangloss 3d98440fb7 Merge branch 'master' of github.com:comfyanonymous/ComfyUI 2024-05-16 14:28:49 -07:00
doctorpangloss 5a9055fe05 Tokenizers are now shallow cloned when CLIP is cloned. This allows nodes to add vocab to the tokenizer, as some checkpoints and LoRAs may require. 2024-05-16 12:39:19 -07:00
comfyanonymous 46daf0a9a7 Add debug options to force on and off attention upcasting. 2024-05-16 04:09:41 -04:00
comfyanonymous 58f8388020 More proper fix for #3484. 2024-05-16 00:11:01 -04:00
comfyanonymous 2d41642716 Fix lowvram dora issue. 2024-05-15 02:47:40 -04:00
doctorpangloss 8741cb3ce8 LLM support in ComfyUI 
- Currently uses `transformers`
 - Supports model management and correctly loading and unloading models
   based on what your machine can support
 - Includes a Text Diffusers 2 workflow to demonstrate text rendering in
   SD1.5
 2024-05-14 17:30:23 -07:00
comfyanonymous ec6f16adb6 Fix SAG. 2024-05-14 18:02:27 -04:00
comfyanonymous bb4940d837 Only enable attention upcasting on models that actually need it. 2024-05-14 17:00:50 -04:00
comfyanonymous b0ab31d06c Refactor attention upcasting code part 1. 2024-05-14 12:47:31 -04:00
doctorpangloss 0ee2f3bf15 Move advanced samplers into a place where it will be found 2024-05-13 19:36:27 -07:00
comfyanonymous 2de3b69b30 Support saving some more modelspec types. 2024-05-13 21:54:11 -04:00
doctorpangloss 355f2aef3a Fix parameters and user agent for ImageRequestParameter. 2024-05-13 17:59:02 -07:00
doctorpangloss 78e340e2d8 Traces now include the arguments for executing a node, wherever it makes sense to do so. 2024-05-13 15:48:16 -07:00
doctorpangloss d11aed87ba OpenAPI ImageRequestParameter node uses a Chrome user-agent to facilitate external URLs better 2024-05-13 15:03:34 -07:00
freakabcdandGitHub cf6e1efb69 Show message on error when loading wf from file (works on drag and drop) (#3466) 2024-05-13 15:22:22 -04:00
comfyanonymous ece5acb8e8 Fix nightly package workflow. 2024-05-12 16:05:10 -04:00
comfyanonymous 794a357f7a Update the nightly workflow. 2024-05-12 07:24:12 -04:00
shawningtonandGitHub 22edd3add5 Fix to LoadImage Node for #3416 HDR images loading additional smaller… (#3454) 
* Fix to LoadImage Node for #3416 HDR images loading additional smaller images. 

Added a blocking if statement  in the ImageSequence.Iterator that checks if subsequent images after the first match dimensionally, and prevent them from being appended to output_images if they do not match. 

This does not fix or change current behavior for PIL 10.2.0 where the images are loaded at the same size, but it does for 10.3.0 where they are loaded at their correct smaller sizes.

* added list of excluded formats that should return 1 image

added an explicit check for the image format so that additional formats can be added to the list that have problematic behavior.
 2024-05-12 07:07:38 -04:00