Instructions to use waifu-diffusion/wd-1-5-beta2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use waifu-diffusion/wd-1-5-beta2 with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("waifu-diffusion/wd-1-5-beta2", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
- DiffusionBee
WD 1.5 Beta 2
For this release, we release two versions of the model:
- WD 1.5 Beta 2
- WD 1.5 Beta 2 Aesthetic
For the aesthetic version, we finetune the attention layer on popular aesthetic images. For training, it is recomended to use the base version.
VAE
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
Release Notes
https://cafeai.notion.site/WD-1-5-Beta-2-Release-Notes-2852db5a9cdd456ba52fc5730b91acfd
Example Images
https://cafeai.notion.site/WD-1-5-Beta-2-Aesthetic-Ver-c44a410fec06478fbf1a08a9890310ff
License
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.
- Downloads last month
- 10