Your two pets as human siblings
Your two pets imagined as adult siblings, each keeping its own colours and character. 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 Pet to human trend
- Written for
- ChatGPT, Gemini, Grok
- You'll need
- A clear photo to upload
- Status
- Tested 20 Oct 2026 in Gemini web app, Auto mode (model identifier not shown)
- Test settings
- Reference photos: a fictional AI-generated dog and a fictional AI-generated grey tabby cat, made in the same Gemini chat just before the test (no real pets). The default copy text was then sent unchanged. Earlier runs with a book in the scene printed words on the book, so the default action is now sipping tea; this run's first result is used. Gemini's output size is 1200x896; only converted to WebP, not upscaled.
- Variability
- Faces, poses and small details vary between runs; always compare the result with your own pet's photo.
Use the uploaded photo, or photos, as the reference for my two pets. Carry each pet's coat colours and markings, eye colour and personality into two fictional adult humans; check the result against the references. The humans are invented and not based on any real person. Both results must show completely human heads and faces: human skin, human noses, human ears and human hair, with no animal heads, muzzles, snouts, fur or whiskers anywhere. Each pet shows only through hair colour, eye colour, clothing colours, expression and pose. Scene: the two human versions together at a kitchen table at breakfast. Pose: a sibling moment: one calmly sipping tea, the other trying to grab their toast. Clothing: each in clothes matching their own pet's coat colours. Light: soft daylight, gentle shadows. Style: photorealistic portrait of two adults, natural skin texture, warm humour. Format: horizontal 4:3 Avoid: animal head, muzzle, snout, whiskers, fur on the skin, animal ears, tails, mixing up the two pets' colours, animal ears or fur, resemblance to any real person, children, extra fingers, text, logos, packaging text, watermarks.
Customise
For example: a kitchen table at breakfast.
For example: one calmly sipping tea, the other trying to grab their toast.
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
- The model can swap which colours belong to which pet; say which pet is on the left.
- Use reference photos you have the right to use; get consent from identifiable people.




