Downloads · 30 days
10
8% of all-time downloads
vae-kl-f8-d16
otinpo/vae-kl-f8-d16
vae-kl-f8-d16 is a machine learning model from otinpo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for diffusers. The card lists the license as mit.
A 16 channel VAE with 8x downsample. Trained from scratch on a balance of photos, artistic, text, cartoons, vector images.
All-time downloads
126
Public
Parameters
57.3M
115 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors115 MB · 100%
At a glance
- Library
- diffusers
- License
- mit
- Access
- Public
- Created
- Jul 6, 2024
- Updated
- Jul 6, 2024
- SHA
- fc0d8ea9
Model card
From the Hugging Face model README
Ostris VAE - KL-f8-d16
A 16 channel VAE with 8x downsample. Trained from scratch on a balance of photos, artistic, text, cartoons, vector images.
It is lighter weight that most VAEs with only 57,266,643 parameters (vs SD3 VAE: 83,819,683) which means it is faster and uses less VRAM yet scores quite similarly on real images. Plus it is MIT licensed so you can do whatever you want with it.
| VAE | PSNR (higher better) | LPIPS (lower better) | # params |
|---|---|---|---|
| sd-vae-ft-mse | 26.939 | 0.0581 | 83,653,863 |
| SDXL | 27.370 | 0.0540 | 83,653,863 |
| SD3 | 31.681 | 0.0187 | 83,819,683 |
| Ostris KL-f8-d16 | 31.166 | 0.0198 | 57,266,643 |
Compare
Check out the comparison at imgsli.
What do I do with this?
If you don't know, you probably don't need this. This is made as an open source lighter version of a 16ch vae. You would need to train it into a network before it is useful. I plan to do this myself for SD 1.5, SDXL, and possibly pixart. Follow me on Twitter to keep up with my work on that.
Note: Not SD3 compatable
This VAE is not SD3 compatable as it is trained from scratch and has an entirely different latent space.
- Library
- diffusers
- License
- mit
- Created
- Jul 6, 2024
- Updated
- Jul 6, 2024