The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.
Go to file
2024-09-09 12:08:46 +03:00
.ci swap legacy sdv15 link (#4682) 2024-08-29 19:48:48 -04:00
.github Add back CI action for tests-ui (#4859) 2024-09-09 04:32:55 -04:00
api_server Get logs endpoint & system_stats additions (#4690) 2024-08-30 12:46:37 -04:00
app fix: url decode filename from API (#4801) 2024-09-08 21:02:32 -04:00
comfy Merge branch 'comfyanonymous:master' into master 2024-09-08 22:20:50 +03:00
comfy_execution Nodes using UNIQUE_ID as input are NOT_IDEMPOTENT (#4793) 2024-09-05 19:33:02 -04:00
comfy_extras SaveLora node can now save "full diff" lora format. 2024-09-07 03:21:02 -04:00
custom_nodes Add optional deprecated/experimental flag to node class (#4506) 2024-08-21 00:01:34 -04:00
input LoadLatent and SaveLatent should behave like the LoadImage and SaveImage. 2023-05-18 00:09:12 -04:00
model_filemanager Add model downloading endpoint. (#4248) 2024-08-13 15:48:52 -04:00
models unet -> diffusion_models. 2024-08-17 21:31:04 -04:00
notebooks swap legacy sdv15 link (#4682) 2024-08-29 19:48:48 -04:00
output Initial commit. 2023-01-16 22:37:14 -05:00
script_examples swap legacy sdv15 link (#4682) 2024-08-29 19:48:48 -04:00
tests Fix error with ExecutionBlocker and OUTPUT_IS_LIST (#4836) 2024-09-08 09:48:47 -04:00
tests-unit Cleanup empty dir if frontend zip download failed (#4574) 2024-08-27 02:07:25 -04:00
web Update frontend to v1.2.47 (#4798) 2024-09-05 18:56:01 -04:00
.gitattributes Tell github not to count the web directory in language stats. 2024-08-15 13:48:56 -04:00
.gitignore Add .venv to gitignore (#4756) 2024-09-09 04:31:18 -04:00
.pylintrc Disallow use of eval with pylint (#4033) 2024-07-16 21:15:08 -04:00
CODEOWNERS Add codeowners file. 2023-08-14 16:54:30 -04:00
comfyui_screenshot.png Update screenshot. 2023-04-10 03:37:46 -04:00
CONTRIBUTING.md Add CONTRIBUTING.md (#3910) 2024-07-01 13:51:00 -04:00
cuda_malloc.py Update cuda_malloc.py 2024-08-30 12:19:50 +03:00
deepcache-sample.json Add files via upload 2024-08-16 00:51:30 +03:00
execution.py Fix error with ExecutionBlocker and OUTPUT_IS_LIST (#4836) 2024-09-08 09:48:47 -04:00
extra_model_paths.yaml.example Move and comment out. 2023-10-12 20:54:43 -04:00
fix_torch.py Avoid loading the dll when it's not necessary. 2024-07-24 13:50:34 -04:00
fixforrx580.bat Add files via upload 2024-08-16 00:51:30 +03:00
folder_paths.py allow current timestamp in save image prefix (#4030) 2024-09-09 02:55:51 -04:00
install.bat Add files via upload 2024-08-16 00:51:30 +03:00
latent_preview.py Make live preview size a configurable launch argument (#4649) 2024-09-03 19:16:38 -04:00
LICENSE Initial commit. 2023-01-16 22:37:14 -05:00
main.py Add an experimental LoraSave node to extract model loras. 2024-09-04 16:38:38 -04:00
new_updater.py Update the old updater if present when running on the windows standalone. 2024-02-26 13:32:14 -05:00
node_helpers.py Less confusing exception if pillow() function fails. 2024-07-29 11:15:37 -04:00
nodes.py Add an experimental LoraSave node to extract model loras. 2024-09-04 16:38:38 -04:00
patchzluda.bat Add files via upload 2024-08-16 00:51:30 +03:00
pytest.ini Execution Model Inversion (#2666) 2024-08-15 11:21:11 -04:00
README.md Update README.md 2024-09-06 09:53:12 +03:00
requirements.txt Add sentencepiece dependency. 2024-07-11 22:58:03 -04:00
server.py Fix issue where sometimes origin doesn't contain the port. 2024-09-09 03:18:17 -04:00
start-tunableop-novram.bat Update start-tunableop-novram.bat 2024-08-30 16:07:10 +03:00
start.bat Update start.bat 2024-09-03 15:23:59 +03:00

# ComfyUI-ZLUDA

  • Windows only version of comfyui which uses ZLUDA to get better performance with AMD GPUs.

## What's New ?

*** BIG UPDATE. Things got broken, had to reset the fork, to get back and update successfully , on the comfyui-zluda directory run these one after another : git fetch --all (enter) git reset --hard origin/master (enter) now you can run start.bat , it will update to the latest version. And also after this a reboot of windows might be needed if the generation time seems to be low. After reboot speed returns to normal.

  • Regarding keeping the app up to date, don't use the update function from the manager, instead use git pull which we are doing on every start if start.bat is used. (APP ALREADY DOES IT EVERYTIME YOU OPEN IT , IF YOU ARE USING START.BAT, SO THIS WAY IT IS ALWAYS UP-TO-DATE WITH WHATEVER IS ON MY GITHUB PAGE) Only use comfy manager to update the extensions ( MANAGER - CUSTOM NODES MANAGER - SET FILTER TO INSTALLED - CLICK CHECK UPDATE ON THE BOTTOM OF THE WINDOW) otherwise it breaks the basic installation, and in that case run install.bat once again.

## CREDITS

## DEPENDENCIES

If coming from the very start, you need :

  1. Git : download from https://git-scm.com/download/win . During installation don't forget to check the box for "Use Git from the Windows Command line and also from 3rd-party-software" to add Git to your system's PATH .

  2. Python (3.10.11 or 3.11 from the official website) : Install latest release from python.org . DON'T USE WINDOWS STORE VERSION. If you have that installed, uninstall and please install from python.org .   During installation don't forget to check the box for "Add Python to PATH when you are at the the "Customize Python" screen.

  3. Visual C++ Runtime : download from https://aka.ms/vs/17/release/vc_redist.x64.exe , install it.

  4. Install HIP SDK 5.7.1 from https://www.amd.com/en/developer/resources/rocm-hub/hip-sdk.html ((UPDATE: HIP 6.1.2 released now, but there are problems so no need to use that one please be careful about selecting the correct version, "Windows 10 & 11 5.7.1 HIP SDK"))

  5. Add the system variable HIP_PATH , value : C:\Program Files\AMD\ROCm\5.7\ (this is the default folder, if you installed it on another drive, change if necessary)

    1. Check the variables on the lower part (System Variables) , there should be a variable called : HIP_PATH .
    1. Also check the variables on the lower part (System Variables) , there should be a variable called : "Path". Double click it and click "New" add this : C:\Program Files\AMD\ROCm\5.7\bin
  1. If you have an AMD GPU below 6800 (6700,6600 etc.) , download the recommended library files for you gpu from : https://github.com/brknsoul/ROCmLibs/
    1. Go to folder C:\Program Files\AMD\ROCm\5.7\bin\rocblas , there would be a "library" folder, backup the files inside to somewhere else.
    1. Open your downloaded optimized library archive and put them inside the library folder (overwriting if necessary) : "C:\Program Files\AMD\ROCm\5.7\bin\rocblas\library"
  1. Reboot your system.

## SETUP (FOR WINDOWS ONLY)

Open a cmd prompt.

git clone https://github.com/patientx/ComfyUI-Zluda
cd ComfyUI-Zluda
install.bat

to start for later use (or create a shortcut to) :

start.bat

also for later when you need to repatch zluda (maybe a torch update etc.) you can use :

patchzluda.bat
  • The first generation would take around 10-15 minutes, there won't any progress or indicator on the webui or cmd window, just wait. Zluda creates a database for use with generation with your gpu.

 ** !!! This might happen with torch changes , zluda version changes and / or gpu driver changes. !!! **

## TROUBLESHOOTING

  • wipe your pip cache ( C:\Users[your windows username]\AppData\Local\pip\cache ) You can also do this when venv is active with : pip cache purge

  • xformers isn't usable with zluda so any nodes / packages that require it doesn't work. Flash attention doesn't work. And lastly using codeformer for face restoration gives "Failed inference: CUDA driver error: unknown error" You should use gfpgan / gpen / restoreformer or other face restoration models.

  • have the latest drivers installed for your amd gpu. ALSO REMOVE ANY NVIDIA DRIVERS you might have from previous nvidia gpu's.

  • if you see zluda errors make sure these three files are inside "ComfyUI-Zluda\venv\Lib\site-packages\torch\lib" cublas64_11.dll (196kb) cusparse64_11.dll (193kb) nvrtc64_112_0.dll (125kb) If they are there but bigger files run : patchzluda.bat

  • if for some reason you can't solve with these and want to start from zero, delete "venv" folder and re-run install.bat

  • If you can't git pull to the latest version , run these commands, git fetch --all and then git reset --hard origin/master now you can git pull

  • Problems with "caffe2_nvrtc.dll" : if you are sure you properly installed hip and can see it on path, please DON'T use python from windows store, use the link provided or 3.11 from the official website. After uninstalling python from windows store and installing the one from the website, be sure the delete venv folder, and run install.bat once again.