Consistency Models
Paper • 2303.01469 • Published • 8
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("dg845/diffusers-cm_edm_imagenet64_ema", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]This is a version of the edm_imagenet64_ema EDM model checkpoint developed by OpenAI and released as part of the consistency models code repo intended to be compatible with the experimental KarrasEDMPipeline.
- Downloads last month
- 43
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support