Linum AI

What Hacker News says?

1. schopra909 · 2026-10-06

   Hi HN, author here! For context, we're a 2-person lab training generative video models. Goal is a new set of controllable, animation tools (you can read more about that here https://www.linum.ai/about if you're curious). The biggest bottleneck for our last text-to-video model in terms of training and inference cost is attention. Video models are incredibly token dense (e.g. 110K tokens for a several second clip). If…

   Comment linking /about

   on “Training Text-to-Image Models Without a VAE”
2. schopra909 · 2026-09-16

   Submitted Training Text-to-Image Models 3.6× Faster as a story · 56 points

   HN discussion
3. schopra909 · 2026-08-27

   Aah, for this we're just trying to filter not generate. When it comes to conditioning, you'll still need a model that understands text since the primary control is text. In the original Stable Diffusion, CLIP doubled as part of this LAION Aesthetic Filter as well as the text control for the generative model. But in the last couple of years, the field has drifted away from CLIP towards LLM hidden states (e.g. Qwen, M…

   Comment linking /field-notes/vae-reconstruction-vs-generation?from=home

   on “Getting video models to learn better, faster”
4. schopra909 · 2026-10-06

   Submitted Training Text-to-Image Models Without a VAE as a story · 55 points

   HN discussion
5. schopra909 · 2026-01-23

   I think YC just release video on the basics of diffusion, but honestly I don’t have a good end to end guide. We’re going to write up going 0->1 on a video model (all the steps) over the coming months. But it likely won’t be a class or anything like that. https://www.linum.ai/field-notes We want to share our learnings with folks who are curious about the space - but don’t have time to make it a full class experience.…

   Comment linking /field-notes

   on “Show HN: Text-to-video model from scratch (2 brothers, 2 years, 2B params)”
6. schopra909 · 2026-08-27

   Submitted Getting video models to learn better, faster as a story · 36 points

   HN discussion
7. schopra909 · 2026-01-23

   https://www.linum.ai/field-notes

   Comment linking /field-notes

   on “Show HN: Text-to-video model from scratch (2 brothers, 2 years, 2B params)”
8. schopra909 · 2026-03-04

   Submitted We Built an $8/Month GPU-Cluster Monitor as a story · 2 points

   HN discussion
9. schopra909 · 2026-02-24

   Submitted Show HN: Open-Weight Image-Video VAE (Better Reconstruction ≠ Better Generation) as a story · 2 points

   HN discussion
10. samaysharma · 2026-01-22

    Submitted Linum v2 - 2B parameter, Apache 2.0 licensed text-to-video models (360p, 720p) as a story · 1 points

    HN discussion
11. handfuloflight · 2024-05-28

    Submitted Linum (AI Video Gen) as a story · 1 points

    HN discussion

Search all of HN for linum.ai