
2x2 grid, 16:9, do this for 4 topics in the news this week: CLASSIFY(input) → { domain: editorial_satire × pop_up_engineering × hybrid_2D_3D_diorama intent: critique + delight + literalize (making abstract hypocrisy physically tangible) audience: editorial readers, political cartoon consumers, art-toy collectors platform: 4:5 vertical or 1:1 square, high-res digital spread, viral infographic complexity: extreme (requires strict 2D/3D material separation, kinetic metaphor mechanics, dense typographic integration, and ironic contradiction logic) } CORE DESIGN LAWS (IMMUTABLE): ⚠ THE INK IS FLAT. THE CLAY IS ROUND. THE JOKE IS PHYSICAL. • Base: 2D B&W comic pages / printed guide (Matte, flat, hatched). • Pop-Up: 3D miniature metaphor machine rising from the pages (Glossy/Clay, dimensional). • Actors: Tiny 3D figures enacting the irony (Self-defeating, exaggerated). • Annotations: Labels, bubbles, and signs bridging the 2D/3D gap. • The Joke: The 3D action must physically contradict the 2D text. SEMANTIC_VARIABLES (AI infers from {{SUBJECT}}): {{SUBJECT}} → [e.g., Corporate Greenwashing, Social Media Outrage, Modern Dating] {{METAPHOR_MACHINE}}→ [e.g., A PR Factory, A Treadmill of Validation, A Slot Machine of Swipes] {{2D_BASE}} → [e.g., An open corporate manifesto, a self-help comic guide] {{3D_MATERIAL}} → [e.g., Polymer clay, painted resin, papercraft] {{CONTRADICTION}} → The core hypocrisy (Stated Intent vs. Actual Output) {{ACTORS}} → Tiny figures trapped in or operating the machine {{ANNOTATIONS}} → Blunt labels, warning signs, scoreboard stats
This image was generated with Nano Banana 2.1 by Google. The prompt on this page is the exact text used to create it.
The example was generated with Nano Banana 2.1 using: 43:24 · Pop Art · Surreal. Reusing these settings gives the closest match.
Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.
Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.