How to use tzvc/hilleli with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("tzvc/hilleli", dtype=torch.bfloat16, device_map="cuda") prompt = "sdcid" image = pipe(prompt).images[0]
Sample pictures of:
sdcid (use that on your prompt)
