Downloads · 30 days
28
1% of all-time downloads
waifu-diffusion/wd-1-5-beta2
wd-1-5-beta2 is a text-to-image model from waifu-diffusion. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as other.
For this release, we release two versions of the model:
Downloads · 30 days
28
1% of all-time downloads
All-time downloads
2.6K
Public
Parameters
866M
21.9 GB on disk
Likes
130
Public
Click a slice to open those files.
.safetensors21.9 GB · 100%
From the Hugging Face model README
For this release, we release two versions of the model:
For the aesthetic version, we finetune the attention layer on popular aesthetic images. For training, it is recomended to use the base version.
WD 1.5 uses the same VAE as WD 1.4, which can be found here https://huggingface.co/hakurei/waifu-diffusion-v1-4/blob/main/vae/kl-f8-anime2.ckpt
https://cafeai.notion.site/WD-1-5-Beta-2-Release-Notes-2852db5a9cdd456ba52fc5730b91acfd
https://cafeai.notion.site/WD-1-5-Beta-2-Aesthetic-Ver-c44a410fec06478fbf1a08a9890310ff
WD 1.5 is released under the Fair AI Public License 1.0-SD (https://freedevproject.org/faipl-1.0-sd/). If any derivative of this model is made, please share your changes accordingly. Special thanks to ronsor/undeleted (https://undeleted.ronsor.com/) for help with the license.