OpenMOSS-Team/MOSS-Image-Base
Text-to-Image • 5B • Updated • 10.9k • 607
Official MOSS Base and SFT checkpoints, alphaBell spatial prompt editor, and browser-local blind layout check for one generated image pair.
Note Official Base checkpoint. Use its model card for current usage and license details.
Note Official SFT checkpoint. Keep generation settings matched before interpreting a Base/SFT pair.
Draw MOSS layouts and blind-check two generated outputs
Note Build and preview a strict spatial layout prompt. The Studio also contains the blind check.
Blind A/B check of MOSS text and placement from local images
Note Direct entry to the browser-local blind A/B workflow. Supply two generated images; annotate text and boxes manually, then reveal labels and export a record.