Proofsheet
Tilt-shift miniature of a market street — example resultReal example
Download example imageOpen full image

Downloads the original example, not your own edited photo. On phones that open it instead, touch and hold the full image to save it.

Made with this exact default prompt; output can vary.

Photo editTravelArt

Tilt-shift miniature of a market street

A crowded market street from above that looks like a busy model village. Upload a clear photo, paste this prompt into ChatGPT, Gemini or Grok, change the parts in brackets to suit you, and generate.

Part of the Tilt-shift miniature world trend

Written for
ChatGPT, Gemini, Grok
You'll need
A clear photo to upload
Status
Tested 19 Oct 2026 in grok-imagine-image-2.0
Test settings
Reference photo: an AI-generated photo of a fictional place, made in Grok for this test. Uploaded with the default copy text unchanged. Aspect ratio 3:4 (no 4:5 preset). First result used; resized to 1200x1600 and converted to WebP.
Variability
Faces, poses and small details vary between runs; always compare the result with your own photo of the place.
Share on WhatsApp Report an issue
Prompt
Use the uploaded photo of a real place as the reference. Keep the layout, buildings, roads, trees and landmarks where they are in the photo and change only the look; check the result against the reference.
Scene: the same market street seen from a high window, fruit and flower stalls under striped awnings, awnings and tiny shoppers like painted figurines.
Light: warm late-afternoon light, long soft shadows.
Style: tilt-shift miniature photo, sharp band across the middle row of stalls, strong blur above and below, saturated toy colours.
Format: vertical 4:5
Avoid: adding or moving buildings, recognisable faces, readable shop names, logos, text, watermarks.

Customise

For example: fruit and flower stalls under striped awnings.

For example: middle row of stalls.

Fields start with illustrative values; replace them with your own facts. The prompt updates as you type. Copy prompt copies your version.

How to use it

  1. Open an external image tool listed above. The tested model, if any, is named in Status.
  2. Upload a clear reference photo of the subject. If it includes identifiable people, get their consent and check each face.
  3. Customise the fields, copy your version, paste it with the photo and generate.
  4. Compare the result with the reference. If a face, pose or detail changes, ask for one correction or try again; an exact match is not guaranteed.
How to use this prompt
  1. This prompt changes your own photo. Choose a clear reference photo, and get permission from people who can be identified.
  2. Upload the photo in the external AI app you chose. Fill Customise, press Copy prompt and paste the prompt with the photo.
  3. Compare the new picture with the original. Face, hands, clothes and pose can change. An exact likeness is not guaranteed.

Full guide: Search, Copy, Save and test labels

Good to know

  • Crowds can turn into odd shapes; regenerate if tiny figures look strange.
  • Use reference photos you have the right to use; get consent from identifiable people.

Try next

Related prompts

Tilt-shift miniature of a market street
Prompt copied