Rainy city crossing at night
A moody night photo of you under a clear umbrella on a rain-soaked neon crossing. 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 man (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 the person. Preserve their recognisable face, natural skin tone, hairline and body proportions as closely as the model permits; check the result against the reference. Scene: a busy pedestrian scramble crossing in a dense Asian megacity at night, wet asphalt reflecting coloured neon, tall buildings with glowing panels, crowds blurred in motion. Moment or Pose: standing still in the middle of the crossing holding a clear umbrella, rain drops on the canopy, looking slightly off-camera. Clothing: a long black trench coat over a grey hoodie. Light: mixed pink and cyan neon from the signs, soft rim light on hair, glossy reflections on the ground. Camera: 85mm lens, shallow depth of field, slow shutter feel so the crowd streaks while the subject stays sharp. Style: cinematic film still, deep blacks, subtle grain. Format: vertical 9:16 Avoid: changed face, plastic skin, extra fingers on the umbrella handle, readable signs or brand logos, text, warped umbrella, watermarks.
Customise
For example: a long black trench coat over a grey hoodie.
For example: pink and cyan.
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
- Signs may carry gibberish lettering; ask for unlit or out-of-focus signs if it appears. Umbrella handles and hands can distort.
- Use reference photos you have the right to use; get consent from identifiable people.
