cog-sdxl icon indicating copy to clipboard operation
cog-sdxl copied to clipboard

Published 20 hours ago • verified publisher icon replicate

Fixed VAE is very low quality

Open levi opened this issue 1 year ago • 1 comments

Using the built-in upcast fixed vae, fine details like hair come out fuzzy and pixelated. This is particularly present if cog-sdxl is used to generate a full fine tune and then loras are created from the full fine tune from images generated from the model.

Changing to use madebyollin/sdxl-vae-fp16-fix for fp16/bf16 training fixes the issue.

Generation from full fine tune: image

Generation from LoRA trained on full fine tune as base model: image

levi avatar Jan 21 '24 17:01 levi