import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("enryu43/anifusion_sd_unet", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
This model is converted with https://github.com/huggingface/diffusers/blob/main/scripts/convert_original_stable_diffusion_to_diffusers.py.
However, the tokenizer in the diffuser model is wrong, for proper usage, see description at https://medium.com/@enryu9000/anifusion-sd-91a59431a6dd, and instructions/examples at https://github.com/enryu43/anifusion2-stable-diffusion.
Also, the original checkpoint in the Latent Diffusion format is available.
Installation instructions for webui: https://gist.github.com/enryu43/fccaa7f165ffcb214780d203c565761f
- Downloads last month
- 5
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support