Rainy afternoon chai at home
A cosy indoor photo of your family sharing chai and snacks while it pours outside. 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 a fictional family of six (not a real person), 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
- Faces, poses and small details vary between runs; always compare the result with your own photo. Gemini adds a small sparkle watermark in the corner.
Use the uploaded photo as the reference for every family member. Preserve each person's recognisable face, natural skin tone, age and relative height as closely as the model permits; check each person against the reference and keep children looking their real age. Scene: a living room by a large window streaked with monsoon rain, a low table with cutting chai in glasses and a plate of hot pakoras, a plant on the sill. Moment or Pose: family gathered on the floor cushions and sofa, one adult pouring chai, kids holding warm glasses with both hands, someone looking out at the rain. Clothing: soft home clothes in muted colours, a shawl over one shoulder. Light: cool grey daylight from the window mixed with a warm table lamp, gentle steam visible from the glasses. Camera: 35mm lens at seated eye level, f/2, rain droplets on the glass slightly in focus at the frame edge. Style: quiet documentary photograph, moody but warm. Format: vertical 4:5. Avoid: changed faces, extra fingers, glasses merging with hands, overly dark faces, plastic skin, text, watermarks.
Customise
For example: a plate of hot pakoras.
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
- Mixed window and lamp light can make skin tones uneven; ask for 'balanced skin tones' if faces look too blue or orange.
- Use reference photos you have the right to use; get consent from identifiable people.




