JSON prompting with MOSS Image 5B: bbox coordinates for exact multi-room layouts
cocktailpeanut · x · 2026-10-21
cocktailpeanut shares the exact JSON prompt behind his MOSS Image 5B six-room apartment cutaway. Structure: a summary block with meta style tags (architectural cutaway, fantasy diorama), canvas and overall caption, plus an items array where each room gets a label, detailed caption, and bbox coordinates (e.g. [-440,-720,-40,-280]) for precise 3x2 grid control.
The output matches the prompt closely — observatory, ballet studio, pizza kitchen, underwater lab, robot workshop, mushroom room — with clean room boundaries. The pattern is directly reusable for any image requiring strict spatial structure.
More from coding & agent
- UC Berkeley releases Actor-Gatherer framework decoupling reasoning from context management — adityagp · 2026-10-21
- Hypothesis Dreamer Agent: A Weekly AI Prompt for Generating Research Ideas — nlarusstone · 2026-10-21
- Dev Builds 'Sandman' Grok Bot to Manage Context Across a 33-Bot Fleet — alexcovo_eth · 2026-10-21
- Hallance launches: an AI aiming to do the work of an entire IT consultancy — TAbrodi · 2026-10-21
- SherpaLabs launches RL environments for finance, coding, quant; top models pass only ~6% on its finance benchmark — ycombinator · 2026-10-21
- The 20x cost trap: AI agents cost 10x traditional AI and 20x conventional software — DavidLinthicum · 2026-10-21