InputExample result
Example Example made on our own Mac with open models: Z-Image made the made-up input photo, FLUX.2 klein ran this prompt on it. Your result in the AI above will look different. How we make examples
Couple portrait as a film still
You and your partner in a cinematic still from a made-up film, with moody light and widescreen framing. You need 1-2 photos.
- You need
- 2 photos of yours
- Written for
- Gemini, ChatGPT
- Result
- Image
Prompt
Use the attached photos of me and my partner to create a still from a made-up genre film starring us. We're together in scene, moment. Frame it in widescreen with cinematic composition, dramatic but natural light, shallow depth of field and the color and grain of real film. Keep both faces exactly as in our photos: same identity, features, skin tone, age, hairstyle and body proportions. Don't swap or blend our faces.
Create a film still using the attached photos of me and my partner.
Film: made-up genre.
Scene: scene, moment.
Camera: widescreen 2.39:1 framing, cinematic composition, shallow depth of field.
Lighting and color: dramatic but natural light, real film color and grain.
Constraints: keep both faces, identity, skin tone, age, hairstyle and proportions exactly as in our photos. Don't swap or blend faces.
Fill in, or keep the brackets and change them later
genre
scene
moment
How to use it
- Open Gemini or ChatGPT and choose the image model.
- Attach one photo of the two of you (or one of each), then paste the prompt.
- A face looks wrong? Run it again in a new chat rather than editing many times.
What to expectTwo faces in one image are harder to keep, so either face can still change a little.
Tips
- Use only photos of you and your real partner, with their OK.
- A photo of the two of you together keeps heights and poses more natural.
- Your photo is uploaded to Google or OpenAI. Read their data policy before you share a face.
Editor: Ali Dezhami · Updated November 18, 2026