SEED Multimodal
Powered by CV Center, Tencent AI Lab, and ARC Lab, Tencent PCG.
Usage
Dependencies
- Python >= 3.8 (Recommend to use Anaconda)
- PyTorch >= 1.11.0
- NVIDIA GPU + CUDA
Installation
Clone the repo and install dependent packages
git clone https://github.com/AILab-CVC/SEED.git
cd SEED
pip install -r requirements.txt
Model Weights
We release the pretrained SEED Tokenizer and De-Tokenizer, pre-trained and instruction tuned SEED-LLaMA-8B and SEED-LLaMA-14B in SEED Hugging Face.
Please download the checkpoints and save under the folder ./pretrained.
You can also download them separately as below,
- Check the SEED tokenizer weights in AILab-CVC/seed-tokenizer-2
- Check the SEED LLaMA(pre-trained 8B) weights in AILab-CVC/seed-llama-8b-pretrain
- Check the SEED LLaMA(sft 8B) weights in AILab-CVC/seed-llama-8b-sft
- Check the SEED LLaMA(pre-trained 14B) weights in AILab-CVC/seed-llama-14b-pretrain
- Check the SEED LLaMA(sft 14B) weights in AILab-CVC/seed-llama-14b-sft
cd pretrained # SEED/pretrained
git lfs install
git clone https://huggingface.co/AILab-CVC/SEED
mv SEED/* ./
To reconstruct the image from the SEED visual codes using unCLIP SD-UNet, please download the pretrained unCLIP SD. Rename the checkpoint directory to "diffusion_model" and create a soft link to the "pretrained/seed_tokenizer" directory.
# SEED/pretrained
git lfs install
git clone https://huggingface.co/stabilityai/stable-diffusion-2-1-unclip
mv stable-diffusion-2-1-unclip seed_tokenizer/diffusion_model
Inference for visual tokenization and de-tokenization
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
Launching Gradio Demo of SEED-LLaMA-14B Locally
Building the local demo of SEED-LLaMA-14B currently requires 2*32GB devices.
# SEED/
# in first terminal
sh scripts/start_backend.sh
# in second terminal
sh scripts/start_frontend.sh
Then the demo can be accessed through http://127.0.0.1:80
Citation
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. Stay tuned for more updates!
License
SEED is released under Apache License Version 2.0.
SEED-LLaMA is released under the original License of LLaMA2.