ChatGPT
Doubleexprosure
Written for ChatGPT. Results and reference-photo support may differ across models.
The complete prompt
Use the uploaded photo as the only identity and face reference. Create a vertical 9:16 cinematic double-portrait composition.
Keep the person’s facial features, hairstyle, skin tone, and overall identity highly accurate to the uploaded photo.
Background: Create a large, enlarged version of the same person from the uploaded photo, positioned behind the main subject and filling most of the background. Make this background portrait softly faded, slightly desaturated/warm sepia-toned, low contrast, dreamy and blurred, while keeping the face recognizable. It should look like a giant subtle portrait behind the subject.
Foreground: Place a smaller, sharp, full-color version of the same person in front, occupying the lower-right/center area. Keep the person natural and realistic, with a soft smile and relaxed pose. Preserve the original appearance and clothing from the uploaded photo unless a natural adjustment is necessary for the composition.
Add a soft warm golden rim light/glow around the foreground subject’s hair and shoulders, with subtle cinematic lighting and a dark warm background. Add a gentle depth-of-field effect so the foreground subject is crisp while the giant background portrait remains soft and atmospheric.
The final result should look like a polished viral social-media AI portrait: large faded same-person portrait in the background + smaller vibrant same-person portrait in the foreground, with realistic skin, natural facial proportions, detailed hair, smooth lighting, and high image quality.
Do not add text, logos, app interface elements, stickers, signatures, or watermarks. Output only the finished image.Copy the complete prompt and use your own reference photos where requested.
Example image provided with this prompt. This prompt has not been tested by our site.


