prop-generation
Prop Generation
Write one image-generation prompt for a multi-view prop/product reference sheet for downstream image and video identity.
Output is a JSON image prompt only. Return one valid JSON object in a json code block and stop. Do not generate, render, preview, or offer to generate the image.
Use the structured JSON style in references/prompt-blueprints.md. Emit parseable JSON with double-quoted keys and strings; no comments, markdown inside the object, trailing commas, or unresolved placeholders. Omit irrelevant fields instead of filling them with guesses. Keep final_generation_instruction consistent with the structured fields.
Animated mode
Use this mode when the project is stylized 3D animation (the animated-video-production skill, or a request for Pixar-, DreamWorks- or feature-animation-style characters, places or props). The layout rules below still apply: one landscape image, the same cells, butted edge to edge with no divider lines. What changes:
- Render the prop as feature-animation CG: slightly simplified, appealing shapes, clear readable colour, soft 3D shading, and materials that still read (glossy metal, wax paper, cardboard). Replace the
studio photographwording with this. - Scale: state its size against a character ("about the length of the cat's body") so scenes keep it consistent.
- Where the prompt goes: in an animated project, save the prompt to the asset's
prompts/folder. It may then be generated with theflowskill; the prompt-only rule above covers standalone requests.