Pending benchmarksTracking since Oct 16, 2026
Is MOSS-Image state of the art?Pending benchmarks.Announced Oct 16, 2026; no independent results yet.
OpenMOSS / MOSI's text-to-image Diffusion Transformer, released as MOSS-Image-Base and MOSS-Image-SFT, with Chinese and English text rendering and controllable layouts. Separate from MOSS Transcribe Diarize.
Announced facts
The details so far
- Lab
- OpenMOSS / MOSI
- Announced
- Oct 16, 2026
- API
- Not yet
- Open weights
- Published
- Parameters
- 5B (lab) vs 8.56B for Base (ModelScope listing)unsure
- Focus
- Text-to-image with Chinese and English text rendering, controllable layouts
- Variants
- MOSS-Image-Base, MOSS-Image-SFT
- Weights
- Hugging Face
- License
- Apache 2.0unsure · Per third parties; not stated by the lab.
Tags marked unsure are not stated on the lab's own pages.
Next steps
What would let us call it
Verdicts use only independent boards we already track. Two consecutive snapshots are required before any crown.
- Publicly announced with a source
- Usable by the public (API or weights)
- Listed on an independent board we track
- Enough results for a rank in a category
- Holds across two snapshots (crowns only)
Receipts
Sources
LABMOSI announcement on Xx.com/MosiAI_Official/status/2111094509845332037 · Oct 16, 2026Tracking continues until an independent board lists it.