Recipe adapts pretrained autoregressive image models to any token order
On LlamaGen and RAR, the method beat MaskGIT inpainting FID 6.21 to 10.44 at 13-33% extra compute.
1 stories, newest first · one card per story
On LlamaGen and RAR, the method beat MaskGIT inpainting FID 6.21 to 10.44 at 13-33% extra compute.
Today 1.2K readers · 1.9K views · 1.5K reads · all time 160K views