kadattack comments

Results 3 comments of


                                            kadattack

How is multi-scale fusion performed?

> You can see this in the forward pass of the HighResolutionNet module. After interpolation upsizing the resulting arrays are concatenated, and then passed through the last_layer submodule that consists...

Error loading gpt4-x-alpaca-13b-native-4bit-128g on Alienware M15 Ryzen Edition R5 laptop

Have the same issue with RTX 2070 Super 8GB on Ubuntu linux and trying to run the [vicuna-13b-GPTQ-4bit-128g](https://huggingface.co/anon8231489123/vicuna-13b-GPTQ-4bit-128g/tree/main) and [gpt4-x-alpaca-13b-native-4bit-128g](https://huggingface.co/anon8231489123/gpt4-x-alpaca-13b-native-4bit-128g) models with `--auto-devices --chat --wbits 4 --groupsize 128` commands. Get...

[Bug]: --gradio-img2img-tool color-sketch breaks "send to img2img" button + weird bug on inpaint tab + Image Browser extension "Send to.." bug

Thanks for writing this report. Came here to report the same issue and it saved me time. I also noticed that with mask inpainting img2img, when you press generate it...