# Linum releases experimental image model from $21K training run

_Published Thursday, November 5, 2026 at 4:19 PM EST · AI, Science · Latest · Tier 2 — Notable_

![Training a Text-to-Image Model for $21K — Primary](https://linum.ai/field-notes/pjit-21k/opengraph-image/card?26d65478f85b1e16)

Linum released an experimental image-generation model from a $21K training run, describing it as a proof of concept for its next video model. The two-person lab says its Pyramid-JiT architecture converges in 11× fewer samples than Linum v2, with 4× more aggressive token reduction.

The model generates directly in pixel space and uses intermediate predictions of lower-resolution images to strengthen learning earlier in the network. It cannot write text or generate posters because text-heavy training images were excluded, and it struggles with crowds, full bodies and interactions between people.

## Sources

- [linum.ai](https://www.linum.ai/field-notes/pjit-21k)

---
Canonical: https://techandbusiness.org/newswire/ZkXzp0fGN6Sodqlo7-EC43
Published: 2026-11-05T21:19:04.394Z
Story chronology: 2026-11-04T16:45:11.000Z
Retrieved: 2026-11-06T22:50:37.065Z
Publisher: Tech & Business (techandbusiness.org)