This repo implements UniTok, a unified visual tokenizer well-suited for both generation and understanding tasks. It is compatiable with autoregressive generative models (e.g. LlamaGen), multimodal understanding models (e.g. LLaVA), and unified MLLMs (e.g. Chameleon and Liquid).

teaser

Built upon UniTok, we construct an MLLM capable of both multimodal generation and understanding with the Liquid framework, which sets a new state-of-the-art among unified autoregressive MLLMs.

teaser

2025年09月18日: UniTok is accepted at NeurIPS 2025 as a spotlight.

2025年05月19日: We find UniTok favors generation without classifier-free-guidance -- it reduces gFID (without cfg) from 14.6 to 2.51 on ImageNet 256x256 using LlamaGen-XXL as the generator. Please refer to the updated EVAL.md for more details.

2025年04月15日: The gradio demo of UniTok MLLM is available on Huggingface now!

2025年04月02日: A new checkpoint of UniTok is released, which has better downstream task performance by replacing the causal attention projection layer with full attention. The model weights of our unified MLLM are also available on Huggingface now!

2025年02月28日: Paper, code, model, and project page for UniTok are all released.

† indicates the model uses pretrained CLIP weights for initialization. Although CLIP weight initialization boosts ImageNet zero-shot accuracy, we notice that random initialization leads to better downstream understanding performance. We thus release the model checkpoint of UniTok that is trained from scratch.

• Python ≥ 3.10
• PyTorch ≥ 2.3.1

git clone https://github.com/FoundationVision/UniTok.git
cd UniTok
pip install -r requirements.txt

Please download the checkpoint and fill in the ckpt_path.

python inference.py \
 --ckpt_path /path/to/unitok_tokenizer.pth \
 --src_img /path/to/test_img --rec_img /path/to/rec_img

• We train UniTok on DataComp-1B. Please follow the instructions to download and prepare the data.

• Download the models used for loss calculation and put them under ./external.

• Download the ImageNet validation set for zero-shot accuracy evaluation.

• Download the ImageNet 256$\times256ドル reference batch for FID evaluation.

Configure nnodes, nproc_per_node, node_rank, master_addr, master_port in launch.sh and run:

bash launch.sh \
 --output_dir '/path/to/save/checkpoints/' \
 --train_data '/path/to/datacomp/shards/{00000000..00140146}.tar' \
 --imagenet_val '/path/to/imagenet_val/' \
 --fid_eval_src '/path/to/imagenet_reference_batch' \
 --fid_eval_dst '/path/to/save/imagenet_reconstructed_batch'

Note: For more hyper-parameter configurations, please check utils/config.py.

We show that UniTok significantly boosts the performance of unified MLLMs.

Visual Understanding Performance on VQA Benchmarks.

Visual Generation Performance on GenAI-Bench.

Please refer to EVAL.md for more details.

We also benchmark UniTok in terms of both understanding performance using the LLaVA framework and generation performance using the LLamaGen framework. Please refer to EVAL.md for more details.

UniTok is built upon the awesome works VAR, DataComp, Liquid, LLaVA, LlamaGen, and ViTamin.

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

If you find this project useful, please consider citing:

@article{unitok,
 title={UniTok: A Unified Tokenizer for Visual Generation and Understanding},
 author={Ma, Chuofan and Jiang, Yi and Wu, Junfeng and Yang, Jihan and Yu, Xin and Yuan, Zehuan and Peng, Bingyue and Qi, Xiaojuan},
 journal={arXiv preprint arXiv:2502.20321},
 year={2025}
}