How to use freQuensy23/diffusion-cloody with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("freQuensy23/diffusion-cloody", dtype=torch.bfloat16, device_map="cuda") prompt = "A [V] cat swimming" image = pipe(prompt).images[0]
Model trained using dream booth on clooody-cat dataset
