You can deploy this model and start earning money today!

JaydenLu666/
Reward-Forcing-T2V-1.3B

Name: Reward-Forcing-T2V-1.3B
Availability: InStock

2512.04678

Views

No views yet

Reward Forcing:
Efficient Streaming Video Generation with
Rewarded Distribution Matching Distillation

Yunhong Lu^1,2, Yanhong Zeng², Haobo Li^2,4, Hao Ouyang², Qiuyu Wang², Ka Leong Cheng²,
Jiapeng Zhu², Hengyuan Cao¹, Zhipeng Zhang⁵, Xing Zhu², Yujun Shen², Min Zhang^1,3

¹ZJU, ²Ant Group, ³SIAS-ZJU, ⁴HUST, ⁵SJTU

🚀 Progress

📝 Technical Report / Paper
🌐 Project Homepage
💻 Training & Inference Code
🤗 Pretrained Model: T2V-1.3B
🔜 Pretrained Model: T2V-14B (In progress)

🎯 Overview

TL;DR: We propose Reward Forcing to distill a bidirectional video diffusion model into a 4-step autoregressive student model that enables real-time (23.1 FPS) streaming video generation. Instead of using vanilla distribution matching distillation (DMD), Reward Forcing adopts a novel rewarded distribution matching distillation (Re-DMD) that prioritizes matching towards high-reward regions, leading to enhanced object motion dynamics and immersive scene navigation dynamics in generated videos.

🔧 Requirements

GPU: NVIDIA GPU with at least 24GB memory for inference, 80GB memory for training.
RAM: 64GB or more recommended.
Linux operating system.

🛠️ Installation

Step 1: Clone the repository

bash

git clone https://github.com/JaydenLyh/Reward-Forcing.git
cd Reward-Forcing

Step 2: Create conda environment

bash

conda create -n reward_forcing python=3.10
conda activate reward_forcing

Step 3: Install dependencies

bash

pip install -r requirements.txt
pip install flash-attn --no-build-isolation

Step 4: Install the package

pip install -e .

📦 Pretrained Checkpoints

Download Links

Model	Download
VideoReward	Hugging Face
Wan2.1-T2V-1.3B	Hugging Face
Wan2.1-T2V-14B	Hugging Face
ODE Initialization	Hugging Face
Reward Forcing	Hugging Face

File Structure

After downloading, organize the checkpoints as follows:

checkpoints/
├── Videoreward/
│   ├── checkpoint-11352/
│   └── model_config.json
├── Wan2.1-T2V-1.3B/
├── Wan2.1-T2V-14B/
├── Reward-Forcing-T2V-1.3B/
└── ode_init.pt

Quick Download Script

bash

pip install "huggingface_hub[cli]"

# Download all checkpoints
bash download_checkpoints.sh

🚀 Inference

Quick Start

bash

# 5-seconds video inference
python inference.py \
    --num_output_frames 21 \
    --config_path configs/reward_forcing.yaml \
    --checkpoint_path checkpoints/Reward-Forcing-T2V-1.3B/rewardforcing.pt \
    --output_folder videos/rewardforcing-5s \
    --data_path prompts/MovieGenVideoBench_extended.txt \
    --use_ema

# 30-seconds video inference
python inference.py \
    --num_output_frames 120 \
    --config_path configs/reward_forcing.yaml \
    --checkpoint_path checkpoints/Reward-Forcing-T2V-1.3B/rewardforcing.pt \
    --output_folder videos/rewardforcing-30s \
    --data_path prompts/MovieGenVideoBench_extended.txt \
    --use_ema

🏋️ Training

Multi-GPU Training

bash

# bash train.sh
torchrun --nnodes=1 --nproc_per_node=8 --rdzv_id=5235 --rdzv_backend=c10d  \
    --rdzv_endpoint=$MASTER_PORT train.py  --config_path configs/reward_forcing.yaml \
    --logdir logs/reward_forcing \
    --disable-wandb

Multi-Node Training

bash

torchrun --nnodes=$NODE_SIZE --nproc_per_node=8 --node-rank=$NODE_RANK --rdzv_id=5235 --rdzv_backend=c10d  \
    --rdzv_endpoint=$MASTER_IP:$MASTER_PORT train.py  --config_path configs/reward_forcing.yaml \
    --logdir logs/reward_forcing \
    --disable-wandb

Configuration Files

Training configurations are in configs/:

default_config.yaml: Default configuration
reward_forcing.yaml: Reward Forcing configuration

📊 Results

Quantitative Results

Performance on VBench

Method	Total Score	Quality Score	Semantic Score	Params	FPS
SkyReels-V2	82.67	84.70	74.53	1.3B	0.49
MAGI-1	79.18	82.04	67.74	4.5B	0.19
NOVA	80.12	80.39	79.05	0.6B	0.88
Pyramid Flow	81.72	84.74	69.62	2B	6.7
CausVid	82.88	83.93	78.69	1.3B	17.0
Self Forcing	83.80	84.59	80.64	1.3B	17.0
LongLive	83.22	83.68	81.37	1.3B	20.7
Ours	84.13	84.84	81.32	1.3B	23.1

Qualitative Results

Visualizations can be found in our Project Page.

📄 Citation

If you find this work useful, please consider citing:

bibtex

@misc{lu2025rewardforcingefficientstreaming,
      title={Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation}, 
      author={Yunhong Lu and Yanhong Zeng and Haobo Li and Hao Ouyang and Qiuyu Wang and Ka Leong Cheng and Jiapeng Zhu and Hengyuan Cao and Zhipeng Zhang and Xing Zhu and Yujun Shen and Min Zhang},
      year={2025},
      eprint={2512.04678},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2512.04678}, 
}

🙏 Acknowledgements

This project is built upon several excellent works: CausVid, Self Forcing, Infinite Forcing, Wan2.1, VideoAlign

We thank the authors for their great work and open-source contribution.

📧 Contact

For questions and discussions, please:

Open an issue on GitHub Issues
Contact us at: yunhonglu@zju.edu.cn

JaydenLu666/Reward-Forcing-T2V-1.3B

Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation

🚀 Progress

🎯 Overview

📋 Table of Contents

🔧 Requirements

🛠️ Installation

Step 1: Clone the repository

Step 2: Create conda environment

Step 3: Install dependencies

Step 4: Install the package

📦 Pretrained Checkpoints

Download Links

File Structure

Quick Download Script

🚀 Inference

Quick Start

🏋️ Training

Multi-GPU Training

Multi-Node Training

Configuration Files

📊 Results

Quantitative Results

Performance on VBench

Qualitative Results

📄 Citation

🙏 Acknowledgements

📧 Contact

JaydenLu666/
Reward-Forcing-T2V-1.3B

Reward Forcing:
Efficient Streaming Video Generation with
Rewarded Distribution Matching Distillation