Family caricature at the dinner table
A warm, funny caricature of your family sharing a big meal. 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 19 Oct 2026 in grok-imagine-image-2.0
- Test settings
- Reference photo: an AI-generated picture of a fictional family of four adults (not real persons), made in Grok for this test. Uploaded with the default copy text unchanged. Aspect ratio 3:2. First result used; resized to 1600x1067 and converted to WebP.
- Variability
- Faces, poses and small details vary between runs; always compare the result with your own photo.
Use the uploaded photo as the reference for everyone in it; everyone shown has agreed to this edit. Keep each person clearly recognisable: face shape, skin tone, hairline, glasses and smile, as closely as the model permits; keep everyone's ages as they are in the photo; exaggerate gently and kindly, never in a mocking way; check the result against the reference. Scene: the family around a dinner table piled with rotis, dal, rice and a big bowl of kheer, in a cosy cartoon dining room. Pose: everyone doing something typical: one serving seconds, one telling a story, one sneaking a sweet. Clothing: outfits from the photo, simplified. Light: warm, even indoor light. Style: warm hand-drawn family caricature, big heads and small bodies, soft colours, kind and flattering. Format: horizontal 3:2 Avoid: mocking exaggeration, changing anyone's skin tone or age, adding or removing people, brand names, logos, extra fingers, text, watermarks.
Customise
For example: rotis, dal, rice and a big bowl of kheer.
For example: one serving seconds, one telling a story, one sneaking a sweet.
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
- Larger families make every face smaller; five people is a sensible maximum.
- Use reference photos you have the right to use; get consent from identifiable people.




