lllyasviel / lllyasviel/stable-diffusion-webui-forge

RTX 5070 (Blackwell) Your device does not support the current version of Torch/CUDA!

Open
#2,886 3 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13k
Forks
1.7k
PR merge metrics
No merged PRs in 30d

Description

RuntimeError: Your device does not support the current version of Torch/CUDA! Consider download another version:
https://github.com/lllyasviel/stable-diffusion-webui-forge/releases/tag/latest

I got Forge with CUDA 12.4 + Pytorch 2.4 <- Fastest, but MSVC may be broken, xformers may not work

I have read online that i think i need Cuda Version 12.8

On https://github.com/AUTOMATIC1111/stable-diffusion-webui this worked:

Download the sd.webui.zip from here, this package is from v1.0.0-pre we will update it to the latest webui version in step 3.
Extract the zip file at your desired location.
Double click the update.bat to update web UI to the latest version, wait till finish then close the window.
Optional (Required for 50 Series GPUs) use the switch-branch-toole.bat to switch to dev branch.
Double click the run.bat to launch web UI, during the first launch it will download large amounts of files. After everything has been downloaded and installed correctly, you should see a message "Running on local URL: http://127.0.0.1:7860", opening the link will present you with the web UI interface.

But there is a option for "(Required for 50 Series GPUs) use the switch-branch-toole.bat to switch to dev branch" this. But here on Forge not. I am more of a beginner of this all so i dont know what to do to make it work.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the reported Forge CUDA 12.4/PyTorch 2.4 package and reproduce the RTX 5070 error. Compare this with the AUTOMATIC1111 sd.webui.zip workflow, including update.bat, run.bat, and the 50 Series switch-branch-toole.bat reference. Done means documenting or confirming a supported Forge setup for RTX 5070 hardware.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.