Hunyuanvideo I2V

🚀 HunyuanVideo-I2V

Following the successful open-sourcing of HunyuanVideo, HunyuanVideo-I2V is a new image-to-video generation framework that accelerates exploration in the open-source community.

🚀 Quick Start

After the great success of open-sourcing HunyuanVideo, we are proud to present HunyuanVideo-I2V, a novel image-to-video generation framework designed to expedite exploration within the open-source community.

This repository includes official PyTorch model definitions, pre-trained weights, and inference/sampling code. You can view more visualizations on our project page. Additionally, we have released the LoRA training code for customizable special effects, enabling the creation of more engaging video effects.

HunyuanVideo: A Systematic Framework For Large Video Generation Model

🔥🔥🔥 News!!

• Mar 13, 2025: 🚀 We released the parallel inference code for HunyuanVideo-I2V powered by xDiT.
• Mar 07, 2025: 🔥 We fixed the bug in the open-source version that caused ID changes. Please try the new model weights of HunyuanVideo-I2V to ensure full visual consistency in the first frame and generate higher-quality videos.
• Mar 06, 2025: 👋 We released the inference code and model weights of HunyuanVideo-I2V. Download.

📑 Open-source Plan

• HunyuanVideo-I2V (Image-to-Video Model)
  • [x] Inference
  • [x] Checkpoints
  • [x] ComfyUI
  • [x] Lora training scripts
  • [x] Multi-gpus Sequence Parallel inference (Faster inference speed on more gpus)
  • [ ] Diffusers

✨ Features

Leveraging the advanced video generation capabilities of HunyuanVideo, we extended its application to image-to-video generation tasks. To achieve this, we employed a token replace technique to effectively reconstruct and incorporate reference image information into the video generation process.

Since we use a pre-trained Multimodal Large Language Model (MLLM) with a Decoder-Only architecture as the text encoder, we can significantly enhance the model's ability to comprehend the semantic content of the input image and seamlessly integrate information from both the image and its associated caption. Specifically, the input image is processed by the MLLM to generate semantic image tokens. These tokens are then concatenated with the video latent tokens, enabling comprehensive full-attention computation across the combined data.

The overall architecture of our system is designed to maximize the synergy between image and text modalities, ensuring a robust and coherent generation of video content from static images. This integration not only improves the fidelity of the generated videos but also enhances the model's ability to interpret and utilize complex multimodal inputs. The overall architecture is as follows.

📦 Installation

📜 Requirements

The following table shows the requirements for running the HunyuanVideo-I2V model (batch size = 1) to generate videos:

• An NVIDIA GPU with CUDA support is required.
  • The model was tested on a single 80G GPU.
  • Minimum: The minimum GPU memory required is 60GB for 720p.
  • Recommended: We recommend using a GPU with 80GB of memory for better generation quality.
• Tested operating system: Linux

🛠️ Dependencies and Installation

Begin by cloning the repository:

git clone https://github.com/tencent/HunyuanVideo-I2V
cd HunyuanVideo-I2V

Installation Guide for Linux

We recommend CUDA versions 12.4 or 11.8 for manual installation.

Conda's installation instructions are available here.

# 1. Create a conda environment
conda create -n HunyuanVideo-I2V python==3.11.9

# 2. Activate the environment
conda activate HunyuanVideo-I2V

# 3. Install PyTorch and other dependencies using conda
# For CUDA 12.4
conda install pytorch==2.4.0 torchvision==0.19.0 torchaudio==2.4.0 pytorch-cuda=12.4 -c pytorch -c nvidia

# 4. Install pip dependencies
python -m pip install -r requirements.txt

# 5. Install flash attention v2 for acceleration (requires CUDA 11.8 or above)
python -m pip install ninja
python -m pip install git+https://github.com/Dao-AILab/flash-attention.git@v2.6.3

# 6. Install xDiT for parallel inference (It is recommended to use torch 2.4.0 and flash-attn 2.6.3)
python -m pip install xfuser==0.4.0

In case you encounter a float point exception (core dump) on a specific GPU type, you can try the following solutions:

# Make sure you have installed CUDA 12.4, CUBLAS>=12.4.5.8, and CUDNN>=9.00 (or simply use our CUDA 12 docker image).
pip install nvidia-cublas-cu12==12.4.5.8
export LD_LIBRARY_PATH=/opt/conda/lib/python3.8/site-packages/nvidia/cublas/lib/

Additionally, HunyuanVideo-I2V also provides a pre-built Docker image. Use the following command to pull and run the Docker image.

# For CUDA 12.4 (updated to avoid float point exception)
docker pull hunyuanvideo/hunyuanvideo-i2v:cuda12
docker run -itd --gpus all --init --net=host --uts=host --ipc=host --name hunyuanvideo-i2v --security-opt=seccomp=unconfined --ulimit=stack=67108864 --ulimit=memlock=-1 --privileged hunyuanvideo/hunyuanvideo-i2v:cuda12

🧱 Download Pretrained Models

The details of downloading pretrained models are shown here.

💻 Usage Examples

🔑 Single-gpu Inference

Similar to HunyuanVideo, HunyuanVideo-I2V supports high-resolution video generation, with a resolution of up to 720P and a video length of up to 129 frames (5 seconds).

Tips for Using Image-to-Video Models

• Use Concise Prompts: To effectively guide the model's generation, keep your prompts short and to the point.
• Include Key Elements: A well-structured prompt should cover:
  • Main Subject: Specify the primary focus of the video.
  • Action: Describe the main movement or activity taking place.
  • Background (Optional): Set the scene for the video.
  • Camera Angle (Optional): Indicate the perspective or viewpoint.
• Avoid Overly Detailed Prompts: Lengthy or highly detailed prompts can lead to unnecessary transitions in the video output.

Using Command Line

If you want to generate a more stable video, you can set --i2v-stability and --flow-shift 7.0. Execute the command as follows:

cd HunyuanVideo-I2V

python3 sample_image2video.py \
    --model HYVideo-T/2 \
    --prompt "An Asian man with short hair in black tactical uniform and white clothes waves a firework stick." \
    --i2v-mode \
    --i2v-image-path ./assets/demo/i2v/imgs/0.jpg \
    --i2v-resolution 720p \
    --i2v-stability \
    --infer-steps 50 \
    --video-length 129 \
    --flow-reverse \
    --flow-shift 7.0 \
    --seed 0 \
    --embedded-cfg-scale 6.0 \
    --use-cpu-offload \
    --save-path ./results

If you want to generate a more high-dynamic video, you can unset --i2v-stability and set --flow-shift 17.0. Execute the command as follows:

cd HunyuanVideo-I2V

python3 sample_image2video.py \
    --model HYVideo-T/2 \
    --prompt "An Asian man with short hair in black tactical uniform and white clothes waves a firework stick." \
    --i2v-mode \
    --i2v-image-path ./assets/demo/i2v/imgs/0.jpg \
    --i2v-resolution 720p \
    --infer-steps 50 \
    --video-length 129 \
    --flow-reverse \
    --flow-shift 17.0 \
    --seed 0 \
    --embedded-cfg-scale 6.0 \
    --use-cpu-offload \
    --save-path ./results

More Configurations

We list some more useful configurations for easy usage:

🎉 Customizable I2V LoRA effects training

Requirements

The following table shows the requirements for training the HunyuanVideo-I2V LoRA model (batch size = 1) to generate videos:

• An NVIDIA GPU with CUDA support is required.
  • The model was tested on a single 80G GPU.
  • Minimum: The minimum GPU memory required is 79GB for 360p.
  • Recommended: We recommend using a GPU with 80GB of memory for better generation quality.
• Tested operating system: Linux
• Note: You can train with 360p data and directly infer 720p videos.

Environment

pip install -r requirements.txt

Training data construction

Prompt description: The trigger word is written directly in the video caption. It is recommended to use a phrase or short sentence.

For example, AI hair growth effect (trigger): rapid_hair_growth, The hair of the characters in the video is growing rapidly. + original prompt

After having the training video and prompt pair, refer to here for training data construction.

Training

cd HunyuanVideo-I2V

sh scripts/run_train_image2video_lora.sh

We list some training-specific configurations for easy usage:

After training, you can find pytorch_lora_kohaya_weights.safetensors in {SAVE_BASE}/log_EXP/*_{EXP_NAME}/checkpoints/global_step{*}/pytorch_lora_kohaya_weights.safetensors and set it in --lora-path to perform inference.

Inference

cd HunyuanVideo-I2V

python3 sample_image2video.py \
   --model HYVideo-T/2 \
   --prompt "Two people hugged tightly, In the video, two people are standing apart from each other. They then move closer to each other and begin to hug tightly. The hug is very affectionate, with the two people holding each other tightly and looking into each other's eyes. The interaction is very emotional and heartwarming, with the two people expressing their love and affection for each other." \
   --i2v-mode \
   --i2v-image-path ./assets/demo/i2v_lora/imgs/embrace.png \
   --i2v-resolution 720p \
   --i2v-stability \
   --infer-steps 50 \
   --video-length 129 \
   --flow-reverse \
   --flow-shift 5.0 \
   --embedded-cfg-scale 6.0 \
   --seed 0 \
   --use-cpu-offload \
   --save-path ./results \
   --use-lora \
   --lora-scale 1.0 \
   --lora-path ./ckpts/hunyuan-video-i2v-720p/lora/embrace_kohaya_weights.safetensors

We list some LoRA-specific configurations for easy usage:

🚀 Parallel Inference on Multiple GPUs by xDiT

xDiT is a Scalable Inference Engine for Diffusion Transformers (DiTs) on multi-GPU clusters. It has successfully provided low-latency parallel inference solutions for a variety of DiTs models, including mochi-1, CogVideoX, Flux.1, SD3, etc. This repository adopted the Unified Sequence Parallelism (USP) APIs for parallel inference of the HunyuanVideo-I2V model.

Using Command Line

For example, to generate a video with 8 GPUs, you can use the following command:

cd HunyuanVideo-I2V

torchrun --nproc_per_node=8 sample_image2video.py \
    --model HYVideo-T/2 \
    --prompt "An Asian man with short hair in black tactical uniform and white clothes waves a firework stick." \
    --i2v-mode \
    --i2v-image-path ./assets/demo/i2v/imgs/0.jpg \
    --i2v-resolution 720p \
    --i2v-stability \
    --infer-steps 50 \
    --video-length 129 \
    --flow-reverse \
    --flow-shift 7.0 \
    --seed 0 \
    --embedded-cfg-scale 6.0 \
    --save-path ./results \
    --ulysses-degree 8 \
    --ring-degree 1 \
    --video-size 1280 720 \
    --xdit-adaptive-size

You can change the --ulysses-degree and --ring-degree to control the parallel configurations for the best performance. Note that you need to set --video-size since xDiT's acceleration mechanism has requirements for the size of the video to be generated. To prevent black padding after converting the original image height/width to the target height/width, you can use --xdit-adaptive-size. The valid parallel configurations are shown in the following table.

🔧 Technical Details

🔗 BibTeX

If you find HunyuanVideo useful for your research and applications, please cite using this BibTeX:

@misc{kong2024hunyuanvideo,
      title={HunyuanVideo: A Systematic Framework For Large Video Generative Models}, 
      author={Weijie Kong, Qi Tian, Zijian Zhang, Rox Min, Zuozhuo Dai, Jin Zhou, Jiangfeng Xiong, Xin Li, Bo Wu, Jianwei Zhang, Kathrina Wu, Qin Lin, Aladdin Wang, Andong Wang, Changlin Li, Duojun Huang, Fang Yang, Hao Tan, Hongmei Wang, Jacob Song, Jiawang Bai, Jianbing Wu, Jinbao Xue, Joey Wang, Junkun Yuan, Kai Wang, Mengyang Liu, Pengyu Li, Shuai Li, Weiyan Wang, Wenqing Yu, Xinchi Deng, Yang Li, Yanxin Long, Yi Chen, Yutao Cui, Yuanbo Peng, Zhentao Yu, Zhiyu He, Zhiyong Xu, Zixiang Zhou, Zunnan Xu, Yangyu Tao, Qinglin Lu, Songtao Liu, Dax Zhou, Hongfa Wang, Yong Yang, Di Wang, Yuhong Liu, and Jie Jiang, along with Caesar Zhong},
      year={2024},
      archivePrefix={arXiv preprint arXiv:2412.03603},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2412.03603}, 
}

Acknowledgements

We would like to thank the contributors to the SD3, FLUX, Llama, LLaVA, Xtuner, diffusers and HuggingFace repositories for their open research and exploration. Additionally, we also thank the Tencent Hunyuan Multimodal team for their help with the text encoder.