Diffusers 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]