ByteDance / ContentV-8B

ContentV: Efficient Training of Video Generation Models with Limited Compute

This project presents ContentV , an efficient framework for accelerating the training of DiT-based video generation models through three key innovations:

• A minimalist architecture that maximizes reuse of pre-trained image generation models for video synthesis
• A systematic multi-stage training strategy leveraging flow matching for enhanced efficiency
• A cost-effective reinforcement learning with human feedback framework that improves generation quality without requiring additional human annotations

Our open-source 8B model (based on Stable Diffusion 3.5 Large and Wan-VAE) achieves state-of-the-art result (85.14 on VBench) in only 4 weeks of training with 256×64GB NPUs.

⚡ Quickstart

Recommended PyTorch Version

• GPU: torch >= 2.3.1 (CUDA >= 12.2)

Installation

git clone https://github.com/bytedance/ContentV.git
cd ContentV
pip3 install -r requirements.txt

T2V Generation

## For GPU
python3 demo.py

📊 VBench

✅ Todo List

• Inference code and checkpoints
• Training code of RLHF

🧾 License

This code repository and part of the model weights are licensed under the Apache 2.0 License . Please note that:

• MMDiT are derived from Stable Diffusion 3.5 Large and trained with video samples. This Stability AI Model is licensed under the Stability AI Community License , Copyright © Stability AI Ltd. All Rights Reserved
• Video VAE from Wan2.1 is licensed under Apache 2.0 License

❤️ Acknowledgement

• Stable Diffusion 3.5 Large
• Wan2.1
• Diffusers
• HuggingFace

🔗 Citation

@article{contentv2025,
  title     = {ContentV: Efficient Training of Video Generation Models with Limited Compute},
  author    = {Bytedance Douyin Content Team},
  journal   = {arXiv preprint arXiv:2506.05343},
  year      = {2025}
  }