Rainy-night café window portrait
Turns an everyday selfie into a moody film still with neon rain 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 woman (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 only reference for the person's face. Create a cinematic portrait of them seated beside a rain-streaked café window at night. Preserve their recognisable facial structure, natural skin tone, eye shape and hairstyle as closely as the model permits; inspect the result against the original. Do not beautify or slim the face. Scene: blurred teal and magenta neon from the street outside, warm tungsten lamp as the key light from the left, raindrops sharp on the glass. Mood: quiet and thoughtful, looking just past the camera Outfit: dark wool coat over a cream sweater Camera: 85mm lens look, shallow depth of field, eye-level, subtle film grain. Format: vertical 4:5. Avoid: plastic skin, extra fingers, text, logos, heavy makeup changes.
Customise
For example: quiet and thoughtful, looking just past the camera.
For example: dark wool coat over a cream sweater.
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
- Face likeness varies by model and photo quality. A clear, front-lit photo gives the closest match.
- Use reference photos you have the right to use; get consent from identifiable people.
