search

fiatrete / OpenDAN-Personal-AI-OS

OpenDAN is an open source Personal AI OS , which consolidates various AI modules in one place for your personal use.
https://opendan.ai
MIT License
1.68k stars 137 forks source link

The 1660 graphics card does not work well with local sd #2

Closed lowkeywx closed 11 months ago

lowkeywx commented 1 year ago

My laptop configuration： Intel(R) Core(TM) i7-9750H CPU @ 2.60GHz 2.60 GHz 16.0 GB (15.9 GB 可用) nVidia 1660

System Info： Windows 11 home 22H2

I've deployed stable-diffusion-webui locally. Use the following command to start: python launch.py --share --api . Set the value DEMO_STABLE_DIFFUSION_ADDRESS=<sd share url> in docker/jarvis/.env . When I was running autotest in webset, the cpu, memory and hard disk usage was 100%.

fiatrete commented 1 year ago

How much is your GPU memory ? Depending on the specific model you are using, Stable Diffusion can consume between 4GB and 10GB of video memory. So, you may need a more powerful graphics card.

Certainly, you can also optimize it by following these methods:

  1. use --xformers when startup Stable Diffusion webui
  2. set "enable_hr": Fasle, in stable_diffusion.module.py to disable upscale