stable-diffusion-webui
stable-diffusion-webui copied to clipboard
[Feature Request] SD upscale in txt2img mode
would be nice to have it in there as well.
And even better - would be cool if we could automate the whole process. As in: first have the image go through the SD upscale, and then through the ESRGAN upscale automatically.
txt2img and img2img need different generation params. SD upscale needs to know what denoising you want. You must see the pic before you know what denoising you want. I don't think this feature will be useful or feasible.