Update README.md
Browse files
README.md
CHANGED
|
@@ -8,7 +8,7 @@ pipeline_tag: text-to-image
|
|
| 8 |
library_name: diffusers
|
| 9 |
---
|
| 10 |
|
| 11 |
-
This VAE was finetuned on PNG only anime illustrations for 512 steps.
|
| 12 |
Used fp32 weights + fp16 mixed precision with learning rate 4e-6 and effective batch size of 16.
|
| 13 |
|
| 14 |
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.
|
|
|
|
| 8 |
library_name: diffusers
|
| 9 |
---
|
| 10 |
|
| 11 |
+
This VAE was finetuned on PNG only anime illustrations for 512 steps with MAE Loss.
|
| 12 |
Used fp32 weights + fp16 mixed precision with learning rate 4e-6 and effective batch size of 16.
|
| 13 |
|
| 14 |
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.
|