Downloads · 30 days
0
vae-teding-aliased-2024-03
thomaseding/vae-teding-aliased-2024-03
vae-teding-aliased-2024-03 is a machine learning model from thomaseding. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as creativeml-openrail-m.
Stable Diffusion 1.5 fine tuned VAE decoder for better pixel art generation by aliasing the output of the decoder.
Access
Public
Updated Mar 24, 2024
Repo size
339 MB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.safetensors335 MB · 99%
At a glance
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Mar 24, 2024
- Updated
- Mar 24, 2024
- SHA
- 856d1415
Model card
From the Hugging Face model README
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.
- License
- creativeml-openrail-m
- Created
- Mar 24, 2024
- Updated
- Mar 24, 2024