Liquid: Language Models are Scalable and Unified
Multi-modal Generators

Junfeng Wu^1,2 · Yi Jiang^2† · Chuofan Ma^2,3
Yuliang Liu¹ · Hengshuang Zhao³
Zehuan Yuan² · Song Bai^2* · Xiang Bai^1*

¹HUST   ²ByteDance   ³HKU
†project lead   *corresponding author

This repo implements Liquid, a scalable and unified autoregressive generation paradigm that seamlessly integrates multimodal comprehension and generation.

News

2025-02-28: Paper, demo, model, and project page for Liquid are all released.

📑 Open-Source Plan

• Liquid-7B (Mix-pretrained Multimodal Model with T2I and Language Ability)
  • Web Demo
  • Inference
  • Checkpoints
• Liquid-7B-Multiratio (Multi-Ratio Image Generation Model)
  • Web Demo
  • Inference
  • Checkpoints
• Liquid-7B-IT (Instruction Tuned Multimodal Model with Instruction Following Ability)
  • Web Demo
  • Inference
  • Checkpoints

📖 Introduction

• We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation.

• Unlike previous multimodal large language model (MLLM), Liquid achieves this integration using a single large language model (LLM), eliminating the need for external pretrained visual embeddings such as CLIP.

• For the first time, Liquid uncovers a scaling law that performance drop unavoidably brought by the unified training of visual and language tasks diminishes as the model size increases.

• Furthermore, the unified token space enables visual generation and comprehension tasks to mutually enhance each other

🔥 Multimodal Generation

• Liquid : Scalable and Versatile Unified Multimodal Generator which supports Visual Understanding, Visual Generation and Multi-modal Generation

• Liquid can generate high-quality, photorealistic images of any aspect ratio by language in an autoregressive paradigm.

🔥 Scaling Law for multimodal generation

• Liquid shows clear Scaling Law in multimodal generation across different sizes(0.5B to 32B).

License

This project is licensed under the MIT License - see the LICENSE file for details.

Citation

If you find this project useful, please consider citing:

@article{liquid,
  title={Liquid: Language Models are Scalable and Unified Multi-modal Generators},
  author=author={Wu, Junfeng and Jiang, Yi and Ma, Chuofan and Liu, Yuliang and Zhao, Hengshuang and Yuan, Zehuan and Bai, Song and Bai, Xiang},
  journal={arXiv preprint arXiv:2412.04332},
  year={2024}
}