Pet in a tiny café
A whimsical photo of your pet as the only customer in a miniature café. Upload a clear photo, paste this prompt into ChatGPT, Gemini or Grok, change the parts in brackets to suit you, and generate.
- Written for
- ChatGPT, Gemini, Grok
- You'll need
- A clear photo to upload
- Status
- Tested 28 Sep 2026 in Gemini app (web), Flash mode with built-in image generation
- Test settings
- Reference photo: an AI-generated picture of an orange tabby cat, made in Gemini for this test. Uploaded with the default copy text unchanged in a new Gemini chat. First result used; only converted to WebP.
- Variability
- Shape, colours and small details can vary between runs; compare with your own photo. Gemini adds a small sparkle watermark in the corner.
Prompt
Use the uploaded photo as the reference for the pet. Preserve its breed, coat colour and texture, markings, eye colour, ear shape and body proportions as closely as the model permits; check the result against the reference. Scene: a pet-sized café with a small counter, a chalk-style menu board with blank lines (no readable text), potted plants and a window to a rainy Kolkata street with a yellow taxi. Moment or Pose: the pet seated at a tiny round table with a pet-safe biscuit on a little plate and a mini cup, looking at the camera with a curious tilt. Light: soft morning light through the window, warm interior glow. Camera: 35mm lens at the pet's eye level, f/2.8, café details softly blurred. Style: whimsical but realistic photograph, as if the café set was built by hand. Format: vertical 4:5. Avoid: human-like hands holding cups, readable text or brand names, changed markings or eye colour, extra legs, watermarks, foods unsafe for pets shown as being eaten.
Customise
For example: rainy Kolkata street with a yellow taxi.
For example: a pet-safe biscuit.
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
- Open an external image tool listed above. The tested model, if any, is named in Status.
- Upload a clear reference photo of the subject. If it includes identifiable people, get their consent and check each face.
- Customise the fields, copy your version, paste it with the photo and generate.
- 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
- This prompt changes your own photo. Choose a clear reference photo, and get permission from people who can be identified.
- Upload the photo in the external AI app you chose. Fill Customise, press Copy prompt and paste the prompt with the photo.
- Compare the new picture with the original. Face, hands, clothes and pose can change. An exact likeness is not guaranteed.
Good to know
- Scale can go wrong, making the pet look huge or tiny against the furniture; regenerate or ask for 'furniture sized to the pet'.
- Use reference photos you have the right to use; get consent from identifiable people.
