InstructAV2AV: Instruction-Guided Audio-Video Joint Editing

Haojie Zheng^{1, 2}, Yixin Yang² , Siqi Yang², Shuchen Weng ^1,2* , Boxin Shi ^2*
* Corresponding authors
¹ BAAI, ² Peking University

---

🎥 Video Demo

InstructAV2AV.mp4

For the best experience, please enable audio.

📅 Todo List

We are working hard to deliver the components as soon as possible. Here is our roadmap for the upcoming release:

• Inference Code (Including pre-trained weights and pipeline scripts)
• InsAVE Dataset (The complete dataset used for training and evaluation)
• Training Scripts (Codes for reproducing or fine-tuning our model)

⚙️ Installation

For CUDA 12.1, you can install the dependencies with the following commands.

git clone https://github.com/suimuc/InstructAV2AV.git
cd InstructAV2AV

conda create -n instructav2av python=3.10 -y
conda activate instructav2av

pip install torch==2.6.0 torchvision torchaudio
pip install -r requirements.txt
pip install flash_attn --no-build-isolation
pip install -e .

📥 Download Pretrained Models

Using huggingface-cli to download the models:

# InstructAV2AV Model
huggingface-cli download suimu/InstructAV2AV \
  --local-dir ckpts/InstructAV2AV
  
# Text Encoder & Video VAE
huggingface-cli download Wan-AI/Wan2.2-TI2V-5B \
  --include \
    "google/*" \
    "models_t5_umt5-xxl-enc-bf16.pth" \
    "Wan2.2_VAE.pth" \
  --local-dir ckpts/Wan2.2-TI2V-5B

# Audio VAE
huggingface-cli download hkchengrex/MMAudio \
  --include \
    "ext_weights/best_netG.pt" \
    "ext_weights/v1-16.pth" \
  --local-dir ckpts/MMAudio

🎮 Inference

Command-Line

The unified inference entry point is scripts/edit.py. The source video must contain an audio track unless a separate file is provided with --source-audio.

python scripts/edit.py \
  --source-video assets/input.mp4 \
  --instruction "Keep the person’s identity and change the spoken words to <S>This is more than just art, it’s a statement.<E>." \
  --finetune-path ckpts/InstructAV2AV/clone_id_voice.safetensors \
  --output outputs/edited.mp4

To achieve optimal editing quality and better text-to-video alignment, you can enhance the instruction by appending a detailed description of the final edited video immediately after your editing command.

python scripts/edit.py \
  --source-video assets/input1.mp4 \
  --instruction "Change the man into a young woman with brown hair, wearing a gray blazer over a light pink top and a necklace with a heart-shaped pendant, and saying, <S>I really think we should give it another chance.<E>. A young woman with long, wavy brown hair and fair skin is engaged in a conversation. She is wearing a gray blazer over a light pink top and has a necklace with a heart-shaped pendant. Her facial expressions change throughout the sequence, showing a range of emotions that suggest she is either explaining something earnestly or reacting to a conversation, and says <S>I really think we should give it another chance.<E> The setting appears to be indoors, with a dimly lit, blurred background that suggests a social environment, possibly a bar or restaurant. The focus remains on the woman's face, capturing her reactions and engagement in the dialogue." \
  --finetune-path ckpts/InstructAV2AV/general.safetensors \
  --output outputs/edited.mp4

InstructAV2AV provides multiple task-specific checkpoints. All checkpoints use the same model architecture, but each checkpoint is fine-tuned for a different editing type. Select the checkpoint that best matches your instruction and provide its path through --finetune-path.

Checkpoint	Editing Type	Description	Example Instruction
general	General Edit	Flexible editing of appearance, scenes, actions, speech, and sound.	Make the horse dark brown with a white saddle.
insertion	Content Insertion	Add an object or other content to the source video.	Add a dark vintage sedan driving from the right to the left.
removal	Content Removal	Remove an object and its associated audiovisual content from the source video.	Remove the chipmunk standing on the stone surface among the peanuts.
clone_id	Identity Cloning	Preserve a person's visual identity while editing other visual or audio attributes.	Keep the person's appearance, change the timbre to a man, and change the spoken words to <S>I understand, but I think we need to consider.<E>.
clone_voice	Voice Cloning	Preserve the speaker's timbre while editing the video or spoken content.	Keep the timbre, change the person's appearance, and change the spoken words to <S>I came here to tell you that you should go.<E>.
clone_id_voice	Identity + Voice Cloning	Preserve both the person's visual identity and the speaker's timbre.	Keep the person's identity and voice, and change the spoken words to <S>This is more than just art, it's a statement.<E>.

Gradio

After downloading all six InstructAV2AV checkpoints and the dependency weights, launch the demo with:

python scripts/demo.py --share

📦 InsAVE-80K Dataset

The training dataset is available at suimu/InsAVE-80K.

🚀 Training

Training manifest format

The trainer accepts CSV, JSON, or JSONL manifests with the following canonical fields:

Field	Description
source_video	Original video
source_audio	Original audio
target_video	Edited video
target_audio	Edited audio
instruction	Editing instruction

Training scripts

The unified training entry point is scripts/train.py, with configuration in ovi/configs/train/train_av_edit.yaml.

Before training, update at least these entries:

ckpt_dir: ./ckpts
finetune_path: ./ckpts/InstructAV2AV/general.safetensors

dataset:
  metadata_path: ./data/InsAVE-80K/path/to/manifest.csv

The manifest and initialization checkpoint can also be overridden from the command line:

accelerate launch \
  --config_file ovi/configs/train/accelerate_config.yaml \
  scripts/train.py \
  --config-file ovi/configs/train/train_av_edit.yaml \
  --data-manifest data/InsAVE-80K/path/to/manifest.csv \
  --finetune-path ckpts/InstructAV2AV/general.safetensors \
  --output-dir outputs/train_av_edit

The provided Accelerate configuration uses DeepSpeed ZeRO-2 and is configured for eight processes. Change num_processes in ovi/configs/train/accelerate_config.yaml to match the number of available GPUs.

The training objective is selected automatically from the modality flags:

has_video	has_audio	Training objective
true	true	Joint audio-video editing
true	false	Video-only editing
false	true	Audio-only editing

🙏 Acknowledgements

This project builds on the following open-source projects:

• Ovi for the audio-video fusion backbone.
• Wan2.2 for the video backbone components, UMT5 text encoder, and video VAE.
• MMAudio for the audio VAE and vocoder.

We thank the authors and contributors of these projects for releasing their work.

✒️ Citation

If you find our work or dataset helpful for your research, please consider citing our paper:

@article{instructav2av2026,
  title={InstructAV2AV: Instruction-Guided Audio-Video Joint Editing},
  author={Zheng, Haojie and Yang, Yixin and Yang, Siqi and Weng, Shuchen and Shi, Boxin},
  journal={arXiv preprint arXiv:2605.18467},
  year={2026}
}