wbh123/dar

Direction-Aware Diagonal Autoregressive Image Generation

We propose Direction-Aware Diagonal Autoregressive Image Generation (DAR) method, which generates image tokens following a diagonal scanning order. The proposed diagonal scanning order ensures that tokens with adjacent indices remain in close proximity while enabling causal attention to gather information from a broader range of directions. Additionally, two direction-aware modules: 4D-RoPE and direction embeddings are introduced, enhancing the model's capability to handle frequent changes in generation direction. To leverage the representational capacity of the image tokenizer, we use its codebook as the image token embeddings.

This repo is used for hosting DAR's checkpoints.

Paper: https://arxiv.org/abs/2503.11129