Rooftop Blue Hour Fairy Lights
A cosy blue-hour photo of you two hugging on a rooftop strung with warm fairy lights 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
- 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 couple (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.
Prompt
Use the uploaded photo as the reference for both people. Preserve both people's recognisable faces, natural skin tones and relative heights as closely as the model permits; check each person against the reference. Scene: a home rooftop terrace in Delhi at blue hour, strings of warm fairy lights overhead, potted plants, floor cushions, city lights coming on in the distance. Moment or Pose: one partner hugs the other from behind, chin resting on their shoulder; both look out at the skyline, then turn their faces slightly toward the camera with soft smiles. Clothing: a soft beige cardigan over a white dress, and a charcoal hoodie. Light: deep blue evening sky with warm fairy-light glow on faces, round bokeh from the lights in the background. Camera: 85mm at f/1.8, slightly to the side, faces sharp, lights melting into bokeh. Style: warm lifestyle photograph, blue and amber contrast, clean skin tones. Format: vertical 4:5. Avoid: changed faces, arms merging, extra fingers, plastic skin, text, watermarks.
Customise
For example: Jaipur.
For example: a soft beige cardigan over a white dress, and a charcoal hoodie.
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
- Blue hour is dim, so some models add noise or smooth skin too much; ask for a little more light on faces if needed.
- Use reference photos you have the right to use; get consent from identifiable people.
