Article: https://civarchive.com/articles/4760

This collection of basic workflows will allow you to get started with Generating images locally using ComfyUI and the new SDXS-512-0.9 model.

Basic versions for txt2img, img2img and using my Zenkai system. More will follow in the next collection version.

It is compatible with SD2.1 Lora's, be sure to grab my Zenkai style Lora model :)

https://civarchive.com/models/10003?modelVersionId=79886

Installation:

UNETLoader node:

https://huggingface.co/IDKiro/sdxs-512-0.9/blob/main/unet/diffusion_pytorch_model.safetensors

rename to sdxs-512-0.9.safetensors and place inside /models/unet/SDXS/

Load Clip node:

https://huggingface.co/IDKiro/sdxs-512-0.9/blob/main/text_encoder/model.safetensors

rename to clip_h.safetensors and place inside /models/clip/SDXS/

Load VAE node:

https://huggingface.co/stabilityai/sd-vae-ft-mse-original/blob/main/vae-ft-mse-840000-ema-pruned.safetensors

place inside /models/VAE/