LaunchAI ModelsOctober 17, 2026

OpenMOSS releases MOSS-Image open diffusion transformer

Read original source →arxiv.org

MOSS-Image is an open diffusion transformer combining 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 lists LongLongTextBench and RealLayoutArena; the Comfy-Org port has 90,456 downloads.

How this story unfolded

13 days · 4 reports · 68 community posts · 72 of 73 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 26
  12. Oct 27
  13. Oct 28
  14. Oct 29

More stories today

Open the live feed