thomaseding
/

vae-teding-aliased-2024-03

thomaseding commited on Mar 24, 2024

Commit

856d141

1 Parent(s): fbfd162

Add comparison image

Files changed (3) hide show

.gitattributes CHANGED Viewed

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text

 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.png filter=lfs diff=lfs merge=lfs -text

README.md CHANGED Viewed

@@ -4,4 +4,6 @@ license: creativeml-openrail-m
 Stable Diffusion 1.5 fine tuned VAE decoder for better pixel art generation by aliasing the output of the decoder.
 Fine tuning was done by training 50 thousand images for 1 epoch effective batch size 12. I preprocessed the images to quantize each 8x8 tile to its average color. On a RTX3090, this took about 4 hours to fine-tune. Used only MSE loss at 1e-5 learning rate. The training data set was just generated from other stable diffusion models, mostly cartoon-like images.

 Stable Diffusion 1.5 fine tuned VAE decoder for better pixel art generation by aliasing the output of the decoder.
+![comparison](https://huggingface.co/thomaseding/vae-teding-aliased-2024-03/resolve/main/comparison.png)
 Fine tuning was done by training 50 thousand images for 1 epoch effective batch size 12. I preprocessed the images to quantize each 8x8 tile to its average color. On a RTX3090, this took about 4 hours to fine-tune. Used only MSE loss at 1e-5 learning rate. The training data set was just generated from other stable diffusion models, mostly cartoon-like images.

comparison.png ADDED Viewed