import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("thinkermode/sdxl-db-powerstar", dtype=torch.bfloat16, device_map="cuda")
prompt = "powerstar"
image = pipe(prompt).images[0]- Downloads last month
- 4
Model tree for thinkermode/sdxl-db-powerstar
Base model
stabilityai/stable-diffusion-xl-base-1.0