How to use choicow/sample with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("choicow/sample", dtype=torch.bfloat16, device_map="cuda") prompt = "Generate an image of sks person matching this pose: There is sks person in the image who is performing conditioning exercise, resistance training." image = pipe(prompt).images[0]
The community tab is the place to discuss and collaborate with the HF community!
