Diwali photo with friends on lit steps
You and your friends sitting on steps lined with diyas, laughing on Diwali night. 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 Diwali AI photo 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 picture of four fictional adult friends (not real persons), 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.
Prompt
Use the uploaded photo as the reference for me and my friends; everyone shown has agreed to this edit. Preserve each person's recognisable face, natural skin tone, hairline and body proportions as closely as the model permits; check the result against the reference. Scene: friends sitting together on the stone steps of a housing society lined with rows of lit diyas, strings of lights overhead, a festive night. Pose: sitting on two levels of steps, leaning in, mid-laugh, one person holding a plate of sweets. Clothing: bright festive kurtas and sarees. Light: warm diya light from the steps, soft string-light glow overhead, dark background. Style: candid photorealistic festival snapshot, natural skin texture, gentle motion in the light, warm colours. Format: vertical 4:5 Avoid: changing anyone's face or identity, adding or removing people, fire near clothes or hair, extra fingers, text, logos, watermarks.
Customise
For example: the stone steps of a housing society.
For example: bright festive kurtas and sarees.
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
- With four or more people, small faces can lose detail; keep the group small or crop closer.
- Use reference photos you have the right to use; get consent from identifiable people.
