Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens — mentioned by zaptrem

Wed, 26 Mar 2025 08:40:55 GMT

Token by token diffusion was done by MAR https://arxiv.org/abs/2406.11838 and Fluid (scaled up MAR) https://arxiv.org/abs/2410.13863 When you randomly pick the locations they found it worked okay, but doing it in raster order (left to right, top to bottom) they found it didn't work as well. We tried it for music and found it was vulnerable to compounding error and lots of oddness relating to the fragility of continuous space CFG.

Paper and discussion history. A mention is not an endorsement.

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens · HackerPapers discussions

Fluid: Scaling Autoregressive Text-to-image Generative Models with Continuous Tokens — mentioned by zaptrem