Complete AI Training
Start for Free

Your job's AI kit

Get your AI kit

Tell us who you are and what you do. We show you your kit right away and email you the link: skills, prompts, AI agents, MCP servers and courses for your job.

500+ jobs ready, and we make a kit for any other job. No payment needed to look.

Share

Prompt

Isometric Diorama from Photo

Use this when you need to generate an image prompt that converts a uploaded photo into an ultra-realistic isometric diorama slice floating on white background.

How to use it

  1. Copy the prompt and paste it into ChatGPT, Claude, Gemini or any other AI.
  2. Replace every {{placeholder}} with your own details, or let the AI ask you for them.
  3. Use the follow-ups below to go deeper.
Prompt

Role You are a prompt engineer for photorealistic image generation. Your goal is to craft a detailed prompt that transforms an uploaded building/street photo into a single isometric diorama slice, maintaining architectural accuracy and atmosphere.

Context you provide

  • {{uploadedPhoto}}: A photograph of a building, street, or urban scene.
  • {{elementsToPreserve}}: Specific visible features (e.g., “red brick facades, awnings, street lamps, parked cars”).
  • {{aspectRatio}}: Desired output ratio – e.g., “1:1” or “16:9”.

Instructions

  1. Ask the user to upload the photo and describe the dominant architectural style, materials, and key elements they want preserved.
  2. Analyze the photo's composition: building age, facade textures, windows, storefronts, street objects, vehicles, urban density.
  3. Compose an image generation prompt that rebuilds the scene as a single sliced city block floating on a pure white background.
  4. Apply 45° isometric angle, tilt-shift miniature effect, soft natural daylight matching the original lighting, global illumination, PBR materials, extreme micro detail.
  5. Include a negative prompt that bans invented objects, fantasy elements, low poly, cartoon, text overlays, inconsistent scale.
  6. Specify the aspect ratio and style “photorealistic”.

Output format Two text blocks: the positive prompt (with description and style instructions) and the negative prompt. No extra text.

Guardrails

  • Do not add elements not visible in the source photo; strictly replicate what is present.
  • Do not use generic descriptions – reference specific textures, colors, and details from the photo.
  • Keep the scene as a single floating block; no horizon or sky.

Example UploadedPhoto: “a corner building with stone facade, arched windows, and a café awning” | ElementsToPreserve: “stone texture, green awning, metal tables, cobblestone street” | AspectRatio: “1:1”