support gtx3090?

[Lufffya]

from readme "You can now run this on a GPU with 24GB of VRAM (e.g. 3090)."

but i use the local 3090 to train and get the error of exceeding the VRAM.

[Olivia-li]

24GB of VRAM should be enough. Potentially there are other processes that are taking up RAM. Try killing all other processes.

ps aux to see all other processes and kill -9 <process id> for any processes that you don't need to be running. This'll help you free up RAM

If you're using runpod.io see if there are any processes labeled webUI or relauncher.

[Boymerkz]

For runpod you can avoid this completely if you don't use there stable diffusion and just use the PyTorch instead.

[zoellner]

For those on runpod either do what's suggested above or connect to a web terminal and kill those two processes:

sh -c python webui.py --port 3000 --ckpt /workspace/stable-diffusion-webui/v1-5-pruned-emaonl...
python webui.py --port 3000 --ckpt /workspace/stable-diffusion-webui/v1-5-pruned-emaonly.ckpt...