LaunchAI ModelsOctober 17, 2026

OpenMOSS releases MOSS-Image open diffusion transformer

Read original source →arxiv.org

MOSS-Image is an open diffusion transformer that pairs high-fidelity synthesis with intent-aware prompt enhancement, claiming state-of-the-art open-weight results on long-form text and layout benchmarks. The technical report cites LongLongTextBench and RealLayoutArena; the Comfy-Org port has drawn 90,456 downloads.

How this story unfolded

12 days · 4 reports · 57 community posts · 61 of 62 shown

  1. Oct 16
  2. Oct 17
  3. Oct 18
  4. Oct 19
  5. Oct 20
  6. Oct 21
  7. Oct 22
  8. Oct 23
  9. Oct 24
  10. Oct 25
  11. Oct 27
  12. Oct 28

More stories today

Open the live feed