import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("MeissonFlow/Mei", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]DDMD-V: Distilling Uniform Discrete Diffusion Models into a One-Step Video Generator
The 3rd Generation MeissonFlow Foundation Model.
DDMD-V (Discrete Distribution Matching Distillation for Video) distills the uniform discrete video diffusion model URSA into a comparable one-step generator Mei.
More details can be found at https://github.com/viiika/DDMD-V
- Downloads last month
- 33