Disen-Forcing

Paper | Project page | Code

Disen-Forcing is an autoregressive text-to-video model distilled from Wan2.1-T2V-1.3B. It generates 832Γ—480 videos at 16 fps from 5 s to 1 min in 4 sampling steps per chunk, keeping long-range consistency without the low-dynamic motion that a frame sink tends to cause.

Model

  • disen_forcing.safetensors: model weights (bf16).
  • Student: Wan2.1-T2V-1.3B, initialized from the Causal Forcing chunk-wise ODE checkpoint; teacher: Wan2.1-T2V-14B.
  • Training: DMD distillation with the improved recipe described in the code repository.

Usage

git clone https://github.com/Dijkstra14/Disen-Forcing && cd Disen-Forcing
# environment: see the repository README
huggingface-cli download Wan-AI/Wan2.1-T2V-1.3B --local-dir wan_models/Wan2.1-T2V-1.3B
huggingface-cli download ZY-Dijkstra/Disen-Forcing disen_forcing.safetensors --local-dir checkpoints

python inference.py --config configs/inference.yaml --checkpoint checkpoints/disen_forcing.safetensors \
    --prompts prompts/MovieGenVideoBench.txt --extended_prompts prompts/MovieGenVideoBench_extended.txt \
    --output_dir videos --num_output_frames 126 --seed 0

--num_output_frames counts latent frames: 21 β‰ˆ 5 s, 126 β‰ˆ 30 s, 252 β‰ˆ 1 min.

Citation

@inproceedings{yu2026disenforcing,
  title     = {Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion},
  author    = {Yu, Zhengyang and Hayakawa, Akio and Ishii, Masato and Yu, Qingtao and Li, Xuesong and Shibuya, Takashi and Mitsufuji, Yuki and Zhang, Jing},
  booktitle = {Advances in Neural Information Processing Systems (NeurIPS)},
  year      = {2026}
}

Acknowledgements

This model is distilled from Wan2.1 and initialized from Causal Forcing. The code builds on CausVid, Self-Forcing, Infinite-Forcing, Causal Forcing and Self Gradient Forcing.

License

Apache-2.0, following Wan2.1.

Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for ZY-Dijkstra/Disen-Forcing

Finetuned
(131)
this model

Paper for ZY-Dijkstra/Disen-Forcing