Lance: Unified Multimodal Modeling by Multi-Task Synergy

Fengyi Fu^*, Mengqi Huang^*,✉, Shaojin Wu^*, Yunsheng Jiang^*, Yufei Huo, Jianzhu Guo^✉,§
Hao Li, Yinghang Song, Fei Ding, Qian He, Zheren Fu, Zhendong Mao, Yongdong Zhang
ByteDance
^* Equal contribution    ^✉ Corresponding authors    ^§ Project lead

English | 简体中文

Note: Lance is a research project rather than a polished product model. The released checkpoint was trained with up to 128 A100 GPUs, with training conducted up to 768x768 image generation and 480p, 12 FPS video generation. Our goal is to share a research artifact for studying unified image/video understanding, generation, and editing under a relatively small model and limited compute budget. Output quality may vary across prompts, resolutions, duration, motion complexity, and editing scenarios, and we see further opportunities to improve the post-training recipe. We appreciate constructive feedback from the community as we continue improving the project.

🔥 Updates

• 2026/05/26: 🎨 The Gradio interface now supports image and video generation, editing, and understanding. Try it out!
• 2026/05/25: ✨ The Hugging Face Space is now live, thanks to the HF team!
• 2026/05/19: 🤗 The technical report is now available on arXiv.
• 2026/05/18: 🔥 We launched the project homepage and released the initial inference code and model weights on GitHub and Hugging Face.

🌟 Highlights

Lance is a 3B native unified multimodal model that supports image and video understanding, generation, and editing within a single framework.

• Efficient at 3B scale. With only 3B active parameters, Lance achieves competitive performance across image generation, image editing, and video generation benchmarks.
• Training from scratch. Lance is trained from scratch with a staged multi-task recipe and within a budget of up to 128 A100 GPUs.

We are actively updating and improving this repository. If you find any bugs or have suggestions, please feel free to open an issue or submit a pull request (PR) 💖.

📅 Roadmap

• Release the fine-tuning code.
• Add support for image-to-video generation code.

🎨 Demo

Show demo results 🔥 We recommend visiting our homepage for more visual results. 🔥

Text-to-Video

Video Editing

Multi-turn Consistency Editing

Intelligent Video Generation

🚀 Installation

Recommended Environment

• Software: Python 3.10+, CUDA 12.4+ (required)
• Hardware: A GPU with at least 40GB VRAM is required for inference

We have tested the following dependency combinations on NVIDIA A100:

• PyTorch 2.8.0 + cu126 + flash-attn 2.8.3
• PyTorch 2.5.1 + cu124 + flash-attn 2.6.3

The default installation commands use the PyTorch 2.8.0 + cu126 setup. For other GPU models, please choose and validate a PyTorch build and a matching flash-attn version according to your driver, CUDA runtime, Python version, and GPU architecture.

Installation Steps

First, clone the repository:

git clone https://github.com/bytedance/Lance.git
cd Lance

Then, set up the environment:

conda create -n Lance python=3.11 -y
conda activate Lance
pip install torch==2.8.0 torchvision==0.23.0 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu126
pip install -r requirements.txt
pip install flash-attn==2.8.3 --no-build-isolation

Note: If installing flash-attn from source fails, you can install a prebuilt wheel instead. The wheelhouse below is from a third-party repository and is provided for reference only; please verify that any wheel you install matches your Python, PyTorch and CUDA versions.

pip install --no-cache-dir --no-deps --force-reinstall \
"https://huggingface.co/strangertoolshf/flash_attention_2_wheelhouse/resolve/main/wheelhouse-flash_attn-2.8.3/linux_x86_64/torch2.8/cu12/abiTRUE/cp311/flash_attn-2.8.3+cu12torch2.8cxx11abiTRUE-cp311-cp311-linux_x86_64.whl"

Then, download the model weights from Lance-3B on Hugging Face and place them in the downloads/ directory:

from huggingface_hub import snapshot_download

save_dir = "./downloads/"
repo_id = "bytedance-research/Lance" 
cache_dir = save_dir + "/cache"

snapshot_download(cache_dir=cache_dir,
  local_dir=save_dir,
  repo_id=repo_id,
  local_dir_use_symlinks=False,
  resume_download=True,
  allow_patterns=["*.json", "*.safetensors", "*.bin", "*.py", "*.md", "*.txt","*.pth",],
)

📚 Usage

Inference

Basic Usage

bash inference_lance.sh

• Before running, please configure the inference parameters at the top of inference_lance.sh.
• Supported tasks: t2i, t2v, image_edit, video_edit, x2t_image, and x2t_video. You can modify TASK_DEFAULT_CONFIGS in inference_lance.py to customize the default data samples for each task.
• Note: For all tasks, we recommend following the prompt format used in the provided examples when writing input prompts, as this typically leads to better generation quality.

Task Examples

Text-to-Video

bash inference_lance.sh \
  --TASK_NAME t2v \
  --MODEL_PATH downloads/Lance_3B_Video \
  --RESOLUTION video_480p \
  --NUM_FRAMES 121 \
  --VIDEO_HEIGHT 480 \
  --VIDEO_WIDTH 848 \
  --SAVE_PATH_GEN results/t2v

Text-to-Image

bash inference_lance.sh \
  --TASK_NAME t2i \
  --MODEL_PATH downloads/Lance_3B \
  --RESOLUTION image_768res \
  --VIDEO_HEIGHT 768 \
  --VIDEO_WIDTH 768 \
  --SAVE_PATH_GEN results/t2i

Video Editing

bash inference_lance.sh \
  --TASK_NAME video_edit \
  --MODEL_PATH downloads/Lance_3B_Video \
  --RESOLUTION video_480p \
  --SAVE_PATH_GEN results/video_edit

Image Editing

bash inference_lance.sh \
  --TASK_NAME image_edit \
  --MODEL_PATH downloads/Lance_3B \
  --RESOLUTION image_768res \
  --SAVE_PATH_GEN results/image_edit

Video Understanding

bash inference_lance.sh \
  --TASK_NAME x2t_video \
  --MODEL_PATH downloads/Lance_3B_Video \
  --RESOLUTION video_480p \
  --NUM_FRAMES 50 \
  --SAVE_PATH_GEN results/x2t_video

Image Understanding

bash inference_lance.sh \
  --TASK_NAME x2t_image \
  --MODEL_PATH downloads/Lance_3B \
  --RESOLUTION image_768res \
  --SAVE_PATH_GEN results/x2t_image

Show task and parameter reference

Available Tasks

For understanding examples:

• config/examples/x2t_image_example.json: image understanding examples for visual question answering and image-based reasoning.
• config/examples/x2t_video_example.json: video understanding examples for video question answering and video captioning.

Parameters

You can configure the following hyperparameters at the top of the inference_lance.sh script:

🖥️ Gradio

You can launch the local Gradio demo for video/image generation, editing, and understanding:

python lance_gradio.py --server-name 0.0.0.0 --server-port 7860

Benchmarks

DPG-Bench Evaluation

^† indicates methods that use LLM rewriters for prompt rewriting before generation.

GenEval Evaluation

^† indicates methods that use LLM rewriters for prompt rewriting before generation.

GEdit-Bench Evaluation VBench Evaluation (Video Generation)

Running Benchmarks

Ready-to-run benchmark scripts are provided under benchmarks/:

📄 License

Copyright 2025 ByteDance Ltd. and/or its affiliates.

🙏 Acknowledgements

We would like to thank the contributors of BAGEL, Qwen2.5-VL-3B-Instruct, and Wan2.2 for their open research and contributions.

💖 Citation

If you find Lance useful for your project or research, welcome to 🌟 this repo and cite our work using the following BibTeX:

@misc{fu2026lanceunifiedmultimodalmodeling,
      title         = {Lance: Unified Multimodal Modeling by Multi-Task Synergy},
      author        = {Fengyi Fu and Mengqi Huang and Shaojin Wu and Yunsheng Jiang and Yufei Huo and Hao Li and Yinghang Song and Fei Ding and Jianzhu Guo and Qian He and Zheren Fu and Zhendong Mao and Yongdong Zhang},
      year          = {2026},
      eprint        = {2605.18678},
      archivePrefix = {arXiv},
      primaryClass  = {cs.CV},
      url           = {https://arxiv.org/abs/2605.18678},
}

📞 Contact

For questions, issues, or collaborations, please contact Mengqi Huang and Jianzhu Guo.