Elucidating the Design Space of Diffusion-Based Generative Models
Paper • 2206.00364 • Published • 18
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("dg845/cm_edm_test_uncond", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]A small random test non-class-conditional EDM model checkpoint based on the consistency models EDM implementation.
- Downloads last month
- 3
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support