Powered by CV Center, Tencent AI Lab, and ARC Lab, Tencent PCG.

The repository provides the official implementation of SEED, SEED-LLaMA. For any inquiries, please email [email protected].

🍻 We are actively looking for self-motivated interns. Please feel free to reach out if you are interested. 🍻

• 2023-10-23 🤗 We have optimized the memory overhead. Through 8bit quantization and dynamic loading, SEED-LLaMA 8b/14B can run on single 16GB/24GB GPU.
• 2023-10-23 🤗 All model weights will be downloaded automatically when starting the demo.
• 2023-10-20 🤗 We release the checkpoints and code of the SEED-2 tokenizer, and SEED-LLaMA-8B/14B.
• 2023-10-20 👾 We release an online gradio demo, feel free to use it by yourself.
• 2023-10-02 📎 We release the technical report of SEED-LLaMA on arXiv, which is empowered by the improved SEED-2 tokenizer.
• 2023-07-29 We release the checkpoint of the SEED tokenizer and its inference code. Check it out via SEED-1.
• 2023-07-16 📎 We release the technical report of SEED on arXiv.

Stay tuned for the updates!

It is recommended to check out our papers for technical details.

SEED-LLaMA is capable of both multimodal comprehension and generation, exhibiting compositional emergent abilities such as multi-turn in-context multimodal generation, acting like your AI assistant. [Compare to SOTA] [More examples on X]

The core of SEED-LLaMA is the tailored SEED tokenizer, which properly quantized visual signals into discrete visual tokens, capturing necessary semantics while being produced under 1D causal dependence. [SEED-2 vs. SEED-1]

• Python >= 3.8 (Recommend to use Anaconda)
• PyTorch >= 1.11.0
• NVIDIA GPU + CUDA

Clone the repo and install dependent packages

git clone https://github.com/AILab-CVC/SEED.git
cd SEED
pip install -r requirements.txt

We release the pretrained SEED Tokenizer and De-Tokenizer, pretrained and instruction tuned SEED-LLaMA-8B and SEED-LLaMA-14B in SEED Hugging Face.

• Check the SEED tokenizer weights in AILab-CVC/seed-tokenizer-2
• Check the SEED LLaMA(8B) weights in AILab-CVC/seed-llama-8b-sft
• Check the SEED LLaMA(14B) weights in AILab-CVC/seed-llama-14b-sft

The model weights of unCLIP SD-UNet which are used to reconstruct the image will be downloaded automatically.

To discretize an image to 1D visual codes with causal dependency, and reconstruct the image from the visual codes using the off-the-shelf unCLIP SD-UNet:

cd ..   # SEED/ 
python scripts/seed_tokenizer_inference.py

Given that SEED-LLaMA-8B is based on Vicuna-7B and SEED-LLaMA-14B based on LLaMA2-Chat-13B, we use Vicuna-7B's ("USER:", "ASSISTANT:") and LLaMA2-Chat-13B's ([INST] [/INST]) prompts for respective instruction tuning.

# Inference for SEED-LLaMA-8B
python scripts/seed_llama_inference_8B.py

# Inference for SEED-LLaMA-14B
python scripts/seed_llama_inference_14B.py

1. Building the local demo of SEED-LLaMA-14B currently requires single 24GB GPU.

# SEED/
# in first terminal
bash scripts/start_backend_14b.sh
# in second terminal
bash scripts/start_frontend_14b.sh

2. Building the local demo of SEED-LLaMA-8B currently requires single 16GB GPU.

# SEED/
# in first terminal
bash scripts/start_backend_8b.sh
# in second terminal
bash scripts/start_frontend_8b.sh

Then the demo can be accessed through http://127.0.0.1:80

If you find the work helpful, please consider citing:

@article{ge2023making,
  title={Making LLaMA SEE and Draw with SEED Tokenizer},
  author={Ge, Yuying and Zhao, Sijie and Zeng, Ziyun and Ge, Yixiao and Li, Chen and Wang, Xintao and Shan, Ying},
  journal={arXiv preprint arXiv:2310.01218},
  year={2023}
}

@article{ge2023planting,
  title={Planting a seed of vision in large language model},
  author={Ge, Yuying and Ge, Yixiao and Zeng, Ziyun and Wang, Xintao and Shan, Ying},
  journal={arXiv preprint arXiv:2307.08041},
  year={2023}
}

The project is still in progress.

SEED is released under Apache License Version 2.0.

SEED-LLaMA is released under the original License of LLaMA2.

We thank the great work from unCLIP SD and BLIP2.