Downloads · 30 days
80
3% of all-time downloads
sd-1-5-mse-vae
nousr/sd-1-5-mse-vae
sd-1-5-mse-vae is a text-to-image model from nousr. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
This repo swaps out the original vae in stable diffusion v1.5 for the new MSE vae found at https://huggingface.co/stabilityai/sd-vae-ft-mse-original.
All-time downloads
2.5K
Public
Repo size
15.2 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin5.5 GB · 56%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Oct 21, 2022
- Updated
- May 16, 2023
- SHA
- c8b72441
Model card
From the Hugging Face model README
This repo swaps out the original vae in stable diffusion v1.5 for the new MSE vae found at https://huggingface.co/stabilityai/sd-vae-ft-mse-original.
The results seem very minimal, perhaps i'm improperly swapping the decoder weights...
This is mostly for those curious, so break stuff, try it out, see what works, etc...
NOTE: usage of this model implies accpetance of stable diffusion's CreativeML Open RAIL-M license
- Task
- Text-to-Image
- Library
- diffusers
- License
- creativeml-openrail-m
- Created
- Oct 21, 2022
- Updated
- May 16, 2023