Hacker News new | ask | show | jobs
by earthnail 389 days ago
From what I can tell, it doesn't look like the recent GPT-4o image generation includes the research of the NeurIPS paper you cited. If it did, we wouldn't see a line-by-line generation of the image, which we do currently in GPT-4o, but rather a decoding similar to progressive JPEG.

I'm not 100% convinced that diffusion models are dead. That paper fixes autoregression for 2D spaces by basically turning the generation problem from pixel-by-pixel to iterative upsampling, but if 2D was the problem (and 1D was not), why don't we have more autoregressive models in 1D spaces like audio?
3 comments
rudedogg 385 days ago
> From what I can tell, it doesn't look like the recent GPT-4o image generation includes the research of the NeurIPS paper you cited. If it did, we wouldn't see a line-by-line generation of the image, which we do currently in GPT-4o, but rather a decoding similar to progressive JPEG.

Going off my bad memory, but I think I remember a comment saying the line-by-line generation was just a visual effect.

link
famouswaffles 389 days ago
>From what I can tell, it doesn't look like the recent GPT-4o image generation includes the research of the NeurIPS paper you cited. If it did, we wouldn't see a line-by-line generation of the image, which we do currently in GPT-4o, but rather a decoding similar to progressive JPEG.

You could, because it's still autoregressive. It still generates patches left to right, top to bottom. It's just that we're not starting with patches at the target resolution.

link
cubefox 389 days ago
> From what I can tell, it doesn't look like the recent GPT-4o image generation includes the research of the NeurIPS paper you cited.

Which means autoregressive image models are even ahead of diffusion on multiple fronts, i.e. both in whatever GPT-4o is doing and in the method described in the VAR paper.

link