MOSS Image 5B lands in Maestro with raw JSON prompting for precise layout control
cocktailpeanut · x · 2026-10-21
MOSS Image 5B, one of the best open-weight T2I models, is now available in Maestro v3.1 (free, local, open). cocktailpeanut demonstrated that you can feed raw JSON prompts directly — using bbox coordinates per room — to control exact layout, producing a six-room apartment cutaway where each room matches its specified scene.
Related event: OpenMOSS releases open-weight text-to-image model MOSS-Image(3 posts)→
More from Multimodal
- Fully code-generated video: Claude researches and scripts, NumPy music, MiniMax voice — technollama · 2026-10-21
- AI still life lesson: a plastic dust sheet beats a list of mood words — tisch_eins · 2026-10-21
- Nano Banana 2.1 character renders surface with Midjourney-style dark fairytale looks — azed_ai · 2026-10-21
- Ex-Google Brain/DeepMind team launches Vyb, an AI design model with editable layered output — testingcatalog · 2026-10-21
- Making a classroom case-explainer video with Opus 5.5 — technollama · 2026-10-21
- FastVideo releases FastH3 Omni weight collection with FP8 and NVFP4 ComfyUI builds — multimodalart · 2026-10-21