boricuapab
boricuapab
After closing both a1111 and oobabooga and relaunching only a1111, I can generate a high res fixed version of the image. https://user-images.githubusercontent.com/61924816/232977442-a0413fcc-eea3-4cb6-831a-71768bd1bc41.mp4
I also feel adding options for restore face and high res fixing in oobabooga would be great, right now my workflow is to take the generated image back to a1111...
Works great, thank you all. https://user-images.githubusercontent.com/61924816/233772129-7398eda9-2de8-412c-b0db-d30a29174ad9.mp4
Seeing this as well 
Thank you very much, it's working as expected in the latest version. https://www.youtube.com/watch?v=vzleOzohKNA
I've been getting this error as well with either a yaml or json character file, my workaround has been to select the cai-chat or chat radio buttons before selecting a...
Thanks this workaround is great of copying the yaml/json files into both locations, I can start chatting immediately via instruct mode.
@korodarn no, they're different models
I'm also getting error loading on Win10 2060 rtx 8gb gpu when using the --pre_layer 30 flag Starting the web UI... Gradio HTTP request redirected to localhost :) Loading TheBloke_stable-vicuna-13B-GPTQ......