metadata
license: apache-2.0
library_name: diffusers
pipeline_tag: text-to-video
base_model:
- BAAI/URSA-1.7B-FSQ320
base_model_relation: finetune
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