This repo contains pre-trained model weights and training/sampling PyTorch(torch>=2.1.0) codes used in
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Peize Sun, Yi Jiang, Shoufa Chen, Shilong Zhang, Bingyue Peng, Ping Luo, Zehuan Yuan
HKU, ByteDance
You can find more visualizations on
- [2024.10.23] Code are preparing !
Huggingface download: https://huggingface.co/Qwen/Qwen2.5-1.5B
| Method | params | tokens | data | weight |
|---|---|---|---|---|
| vq_ds16_t2i | 72M | 16x16 | LAION COCO (50M) + internal data (10M) | vq_ds16_t2i.pt |
| Method | params | tokens | data | weight |
|---|---|---|---|---|
| LlamaGen-XL | 775M | 16x16 | LAION COCO (50M) | t2i_XL_stage1_256.pt |
| LlamaGen-XL | 775M | 32x32 | internal data (10M) | t2i_XL_stage2_512.pt |
Before running demo, please refer to language readme to install the required packages and language models.
Please download models, put them in the folder ./pretrained_models, and run
python3 autoregressive/sample/sample_t2i.py --vq-ckpt ./pretrained_models/vq_ds16_t2i.pt --gpt-ckpt ./pretrained_models/t2i_XL_stage1_256.pt --gpt-model GPT-XL --image-size 256
# or
python3 autoregressive/sample/sample_t2i.py --vq-ckpt ./pretrained_models/vq_ds16_t2i.pt --gpt-ckpt ./pretrained_models/t2i_XL_stage2_512.pt --gpt-model GPT-XL --image-size 512
The generated images will be saved to sample_t2i.png.
We use serving framework vLLM to enable higher throughput. Please refer to serving readme to install the required packages.
python3 autoregressive/serve/sample_c2i.py --vq-ckpt ./pretrained_models/vq_ds16_c2i.pt --gpt-ckpt ./pretrained_models/c2i_XXL_384.pt --gpt-model GPT-XXL --from-fsdp --image-size 384
The generated images will be saved to sample_c2i_vllm.png.
See Getting Started for installation, training and evaluation.
The majority of this project is licensed under MIT License. Portions of the project are available under separate license of referred projects, detailed in corresponding files.
@article{sun2024autoregressive,
title={Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation},
author={Sun, Peize and Jiang, Yi and Chen, Shoufa and Zhang, Shilong and Peng, Bingyue and Luo, Ping and Yuan, Zehuan},
journal={arXiv preprint arXiv:2406.06525},
year={2024}
}