One thing i'd add is that generating the tokens at the target resolution from the start is no longer the only approach to autoregressive image generation.
Rather than predicting each patch at the target resolution right away, it starts with the image (as patches) at a very small resolution and increasingly scales up.
Paper here - https://arxiv.org/abs/2404.02905
One thing i'd add is that generating the tokens at the target resolution from the start is no longer the only approach to autoregressive image generation.
Rather than predicting each patch at the target resolution right away, it starts with the image (as patches) at a very small resolution and increasingly scales up. Paper here - https://arxiv.org/abs/2404.02905