Comments (13)
The minimum requirements that @lllyasviel posted above says 16GB GPU memory required for AMD on Windows with DirectML
from fooocus.
ComfyUI already has support for AMD cards on Windows via Microsoft's DirectML, but it has to be activated through a CLI argument (--directml). Since Fooocus imports Comfy directly I don't see any way of setting the args.directml
value to anything from Fooocus' code.
I tried to hack around this in the Comfy repository. First by changing if args.directml is not None:
to if not torch.cuda.is_available() and platform.system() == "Windows":
, but Fooocus for some reason pulls down the latest Comfy version from git at every start, thereby overwriting any changes.
So I commented out that code, and after a while I got the web UI running, but i was unable to generate any images since I apparently have too little RAM in my old computer (12 GB):
RuntimeError: [enforce fail at ..\c10\core\impl\alloc_cpu.cpp:72] data. DefaultCPUAllocator: not enough memory: you tried to allocate 84934656 bytes.
The GPU and VRAM was barely used during this, so there was some bug still preventing DirectML to be used I think.
On top of that xFormers complains that it was built for PyTorch with Cuda, and I could find any way of either installing a CPU only version, or disable it.
I got slightly better results trying to use the same SDXL models in ComfyUI, but ultimately I got out of memory error there as well and gave up.
[W D:\a\_work\1\s\pytorch-directml-plugin\torch_directml\csrc\engine\dml_heap_allocator.cc:120] DML allocator out of memory!
At least this time i could see that both the GPU and VRAM was being used, but I'm guessing the limiting factor is still RAM since I got 8 GB VRAM and there were still some free.
I should mention that in both Fooocus' and ComfyUI's Python environments i had installed torch-directml (version 0.2.0.dev230426), which obviously is needed to import it.
from fooocus.
Same issue with RX 6700 XT.
from fooocus.
Same on AMD 6750XT
from fooocus.
Related: comfyanonymous/ComfyUI#160
from fooocus.
Same on Amd RX588
from fooocus.
same on Amd 580
from fooocus.
RX 5700XT not work
from fooocus.
AMD Radeon RX 7900 XTX not working here as well
from fooocus.
AMD Radeon RX 6750 XT also does not work here
from fooocus.
See also https://github.com/lllyasviel/Fooocus?tab=readme-ov-file#minimal-requirement
from fooocus.
I've been using Fooocus on a 7900 XTX and it seems to work. Just need to make the changes mentioned in #624 (comment)
I would like to see some optimizations done to make it faster on AMD cards though
from fooocus.
thanks it works now ^^
edited: RuntimeError: Could not allocate tensor with 167772160 bytes. There is not enough GPU video memory available!
from fooocus.
Related Issues (20)
- [Feature Request]: Is it possible to "teach" Fooocus new words? HOT 1
- [Bug]: Constantly removes my custom checkpoints folder HOT 3
- [Feature Request]: mask generation mode HOT 1
- [Feature Request]: Automatic upscale after every generation. HOT 1
- [Feature Request]: Simple checkbox to exclude main prompt for inpaint HOT 2
- Add NPU support HOT 1
- [Bug]: Cannot install Fooocus due to error when executing run.bat related to NVIDIA driver HOT 1
- [Feature Request]: Slow Fooocus Colab Installation Process Fix HOT 1
- [Bug]: Install Issue HOT 3
- [Bug]: Black images on debian 12 VM HOT 2
- [Feature Request]: SD3 support HOT 6
- [Bug]: Generation output is messy when using a prompt with lots of "weight" or keywords HOT 4
- Add hires fix[Feature Request]: HOT 3
- [Feature Request]: Specifying a VAE in presets HOT 1
- [Bug]: PyYaml 6.0 is broken on Python 3.12.3 (Ubuntu 24.04 LTS) HOT 4
- [Feature Request]: Always Random Wildcards #2761 HOT 1
- [Feature Request]: 如何将从huggingface下载模型改为镜像? HOT 2
- [Bug]: Load preset [J:\FOOOCUS\Fooocus_win64\Fooocus\presets\realistic.json] failed HOT 2
- [Feature Request]: Is it possible to find here explained doc for presets variables? HOT 2
- [Feature Request]: hash generation HOT 4
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fooocus.