Image-to-JSON prompt extractor
@dotey challenges Nano Banana builders to reverse-engineer any photo into a clean JSON schema. The workflow inspects wardrobe, pose, lighting, gear, and styling so you can tweak individual keys (like background or accessories) without rewriting the entire prompt when recreating the shot in Gemini 3 Pro.

Prompt
Provide a detailed and comprehensive JSON prompt describing all aspects necessary for accurately replicating the original image. Include specifics about objects, clothing, hairstyles, intricate details, accessories, photographic equipment, environment, lighting, style, body poses, and any other relevant elements, ensuring that every detail of the original image can be precisely recreated.
Actions
Recommended settings
- Gemini 3 Pro • text + vision
- Nano Banana JSON export
- Detail completeness pass
Execution notes
- Attach the original reference image so Nano Banana can extract attribute-by-attribute notes into JSON sections.
- Keep consistent section keys (subject, attire, lighting, camera) so downstream automations can edit specific fields fast.


