linum.ai on Hacker News

4 stories on the front page, newest first. Scroll down to watch the site change over time.

Screenshot of linum.ai: Training Text-to-Image Models Without a VAE

Training Text-to-Image Models Without a VAE (linum.ai)

49 points by schopra909 19 days ago | 14 comments

Linum research blog post introducing Pyramid-JiT, a multiresolution prediction method to speed convergence of VAE-free pixel-space text-to-image models.

text-to-image diffusion-models pixel-space-generation multiresolution

Screenshot of linum.ai: Training Text-to-Image Models 3.6× Faster

Training Text-to-Image Models 3.6× Faster (linum.ai)

41 points by schopra909 1 month ago | 8 comments

Screenshot of linum.ai: Getting video models to learn better, faster

Getting video models to learn better, faster (linum.ai)

26 points by schopra909 2 months ago | 9 comments

Screenshot of linum.ai: Learnings from 4 months of Image-Video VAE experiments

Learnings from 4 months of Image-Video VAE experiments (linum.ai)

117 points by schopra909 8 months ago | 15 comments

linum.ai on Hacker News

Training Text-to-Image Models Without a VAE(linum.ai)

Training Text-to-Image Models 3.6× Faster(linum.ai)

Getting video models to learn better, faster(linum.ai)

Learnings from 4 months of Image-Video VAE experiments(linum.ai)

Training Text-to-Image Models Without a VAE (linum.ai)

Training Text-to-Image Models 3.6× Faster (linum.ai)

Getting video models to learn better, faster (linum.ai)

Learnings from 4 months of Image-Video VAE experiments (linum.ai)