SDXL is out: stable-diffusion-xl-base-1.0
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
here is the refiner: https://huggingface.co/stabilityai/stable-diffusion-xl-refiner-1.0
You're viewing a single thread.
Still kinda new to this, do we download the whole huggingface directory? Just the safetensors? Do we need the refiner too? I guess, what are the steps for "optimal installation"?
So from what I understand, all you need is the base for A1111. If you're using comfyUI, might want to download the refiner too.
Just learned that you can generate image using text to image using base model then send it to img2img and use refiner model with around 0.33 to 0.25 strength.
Okay that makes sense, and that's just the safetensors file right? I don't need the whole repo?
Right you don't need any of the other files