New Year couple on a rooftop with fireworks
The two of you on a rooftop watching distant New Year fireworks over the city. 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
- Occasion
- New Year · 1 Jan 2027
- Status
- Tested 8 Nov 2026 in Grok Imagine
- Test settings
- Reference photo: an AI-generated picture of fictional adults (not real persons), made in Grok for this test. Default copy text unchanged. Aspect ratio vertical 4:5. First result used; only converted to WebP at 1264×1568, not upscaled.
- 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 exactly two adult people. Preserve each person's recognisable face, natural skin tone, age and height as closely as the model permits; match each person to the reference and never swap or blend faces. Keep exactly the same two people; do not add or remove anyone. Scene: a safe rooftop terrace in an imagined Indian city on New Year's Eve, warm white fairy lights, lit buildings and professional fireworks far away in the sky. Moment or Pose: the couple stands together well away from the edge, smiling and looking towards the distant fireworks; they hold no fireworks. Clothing: evening outfits in midnight blue and burgundy. Light: soft rooftop light mixed with the colourful distant fireworks and city glow. Camera: 35mm, f/2.8, eye level, medium-wide, both faces visible. Style: photorealistic cinematic night photography. Format: vertical 4:5. Avoid: changed faces, skin lightening, extra fingers, text, logos, watermarks, extra people, hands in the flame, burning clothes, fireworks in hands, unsafe edge poses, alcohol, numbers.
Customise
For example: warm white.
For example: midnight blue and burgundy.
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
- Faces in low light may drift from your photo, and fireworks can look unreal; compare before sharing.
- Use reference photos you have the right to use; get consent from identifiable people.
