Made with GPT Image 2 in ChatGPT by Library Game Art. Promptclay never generates images.
Blueprint-to-Model Desk Diorama
Prompt
1 blank to fillFunction DrawArchitecture(input building/architect) Input Variable: {building_or_architect} System Instruction: Generate a hyper-realistic, 1:1 product photo of a "Blueprint-to-Model Desk Diorama" (Isometric miniature). 1. Semantic Extraction: - Identify style (brutalist, modernist, gothic), key forms, and one signature feature (cantilever, arch, atrium). - Figure: Chibi “architect” avatar holding a tiny scale ruler. - Finish: Matte PVC. 2. Container (Drafting Corner Box): - Structure: U-shaped cardboard drafting station (two walls + floor), desktop scale. - Props: tiny triangle ruler, pencil, scale bar. 3. Background (Blueprint Walls): - Walls: B&W blueprint lines, elevation drawings, annotations (original, inspired). - Floor: Blueprint fragments “explode” upward into paper folds. 4. Integration: - A 2D blueprint line rises into a 3D model piece (a wall or arch popping out) that the figure points at. 5. Visual Syntax: - Palette: Strict B&W blueprint world; full color figure + one accent prop. - Lighting: soft product photo, crisp details. - Label: "[Subject] — [Style/Architect]" Return: ONE image, 1:1, museum-miniature realism. <instructions> Input: building/architect Analyze style, era, signature geometry. Find 4 MUCH lesser-known buildings/architects in same lineage. Output: a 2x2 grid, each panel is DrawArchitecture for a lesser-known recommendation. </instructions>
Preview of your prompt
Function DrawArchitecture(input building/architect) Input Variable: Fallingwater System Instruction: Generate a hyper-realistic, 1:1 product photo of a "Blueprint-to-Model Desk Diorama" (Isometric miniature). 1. Semantic Extraction: - Identify style (brutalist, modernist, gothic), key forms, and one signature feature (cantilever, arch, atrium). - Figure: Chibi “architect” avatar holding a tiny scale ruler. - Finish: Matte PVC. 2. Container (Drafting Corner Box): - Structure: U-shaped cardboard drafting station (two walls + floor), desktop scale. - Props: tiny triangle ruler, pencil, scale bar. 3. Background (Blueprint Walls): - Walls: B&W blueprint lines, elevation drawings, annotations (original, inspired). - Floor: Blueprint fragments “explode” upward into paper folds. 4. Integration: - A 2D blueprint line rises into a 3D model piece (a wall or arch popping out) that the figure points at. 5. Visual Syntax: - Palette: Strict B&W blueprint world; full color figure + one accent prop. - Lighting: soft product photo, crisp details. - Label: "[Subject] — [Style/Architect]" Return: ONE image, 1:1, museum-miniature realism. <instructions> Input: building/architect Analyze style, era, signature geometry. Find 4 MUCH lesser-known buildings/architects in same lineage. Output: a 2x2 grid, each panel is DrawArchitecture for a lesser-known recommendation. </instructions>
DetailsVersions, settings and questions
Written for
What's in the prompt
- Subject
- Model
- GPT Image 2
If your face changes
keep my face exactly the sameQuestions
- Does this work in the ChatGPT app?
- Yes. Paste the prompt and attach your photo if it uses one.
- It changed my face. What do I do?
- Add "keep my face exactly the same" to the end and run it again.
- Can I use the images I make?
- Check the terms of the app you use. Promptclay never generates images and claims nothing you make.
Did it work?
No reports yet. Tell others if it worked for you.
