STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis · HackerPapers discussions

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis — mentioned by godelski

Fri, 08 Aug 2025 00:38:56 GMT

> which is what you get when you look at non-LLM alternatives to General Intelligence. I disagree with this. There are a good ideas that are worth pursuit. I'll give you that few, if any, have been shown to work at scale but I'd say that's a self-fulfilling prophecy. If your bar is that they have to be proven at scale then your bar is that to get investment you'd have to have enough money to not need investment. How do you compete if you're never given the opportunity to compete? You could be the greatest quarterback in the world but if no one will let you play in the NFL then how can you…

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

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis — mentioned by yorwba

Sat, 28 Jun 2025 04:28:31 GMT

Figure 10 in https://arxiv.org/pdf/2506.06276 has a speed comparison. You need fairly large batch sizes for this method to come out ahead. The issue is that the architecture is very sequential, so you need to be generating several images at the same time to make good use of GPU parallelism.

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

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis — mentioned by yorwba

Fri, 27 Jun 2025 07:58:09 GMT

They took a simple technique (normalizing flows), instantiated its basic building blocks with the most general neural network architecture known to work well (transformer blocks), and trained models of different sizes on various datasets to see whether it scales. Looks very bitter-lesson-pilled to me. That they didn't scale beyond AFHQ (high-quality animal faces: cats, dogs and big cats) at 256×256 is probably not due to an explicit preference for small models at the expense of output resolution, but because this is basic research to test the viability of the approach. If this ever makes it…

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