This VAE was finetuned on PNG only anime illustrations for 512 steps with MAE Loss.
Used fp32 weights + fp16 mixed precision with learning rate 4e-6 and effective batch size of 16.

This training was to test my VAE decoder training code and 512 step model turned out to be better than i expected and fixes the color shifting issues of the original SD3 VAE pretty well.
I stopped messing with SD3 after a while but i decided to release this VAE finetune instead of deleting it.

Original Image:

orig.png

Original SD3 VAE:

vae_orig.png

Anime VAE Finetune:

vae_ft.png

Downloads last month
22
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Disty0/sd3_vae_anime_ft

Finetuned
(77)
this model

Dataset used to train Disty0/sd3_vae_anime_ft