Disty0
/

sd3_vae_anime_ft

Model card Files Files and versions

Disty0 commited on May 30

Commit

b224f24

·

verified ·

1 Parent(s): b0d816c

Update README.md

Files changed (1) hide show

README.md +4 -4

README.md CHANGED Viewed

@@ -7,11 +7,11 @@ pipeline_tag: text-to-image
 library_name: diffusers
 ---
-This VAE was finetuned on PNG only anime illustrations for 512 steps.
-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.

 library_name: diffusers
 ---
+This VAE was finetuned on PNG only anime illustrations for 512 steps.
+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.