Autoregressive Model Beats Diffusion: 🦙 Llama for Scalable Image Generation

     

main LlamaGen repository link -->

To Run

To run the LlamaGen_local model, follow these steps:

1. clone the repository

git clone https://github.com/Hasnat79/LlamaGen_local.git

2. setup the environment

source setup.sh

3. download the checkpoints

source pretrained_models/download_ckpts.sh

4. run the text 2 image sample

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

5. play with sample_t2i.py file.

For more detailed instructions, please refer to the documentation.