20 prompts · ChatGPT · Gemini
Couple Photo Prompts
Couple edits are the hardest for AI, because it has to keep two faces right at once. Each prompt below opens with a line that locks both faces, skin tones and your height difference before it describes the scene. Upload one photo of you together, or one photo each, pick your outfit and setting from the dropdowns, and copy.
1. Golden Hour Walk in a Field

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us walking hand in hand through a field of tall grass at golden hour, looking at each other and smiling. We are wearing a white dress and a beige linen shirt. The low sun is behind us and gives a warm rim of light on our hair. Candid, natural, shot from the front on an 85mm lens with a soft background. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
2. Sharing an Umbrella in the Rain

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us standing close under one red umbrella on a rainy city street at night. Street lights and shop signs reflect on the wet road. We are wearing long coats and looking at each other. Raindrops visible in the light, cinematic colour, romantic and quiet. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
3. Pre-Wedding on Palace Steps

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us on the stone steps of a Rajasthani palace, one seated a step below the other, holding hands and smiling at each other. We are wearing a red lehenga and an ivory sherwani. Golden hour, carved arches and pillars behind us, soft warm light, elegant pre-wedding photoshoot style. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
4. Coffee Date by the Window

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us sitting across a small cafe table by a large window, both holding coffee cups and laughing mid-conversation. We are wearing casual sweaters. Soft daylight from the window, plants and warm wooden interior, candid photo taken from the side. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
5. Beach Sunset, Faces Lit

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us standing barefoot on a beach at sunset, facing each other and holding both hands, with the orange sun low over the sea. We are wearing white beachwear. Keep our faces softly lit and clearly recognisable, not in full silhouette. Gentle waves, warm sky, wide shot. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
6. South Indian Temple Couple Portrait

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us standing side by side in a South Indian temple corridor with carved stone pillars. We are wearing a red kanchipuram silk saree and a white veshti with a silk shirt, with jasmine flowers and simple gold jewellery. We are smiling at the camera. Soft light from the side, oil lamps glowing in the background, graceful and traditional. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
7. Bike Ride on an Open Road

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us on a motorcycle stopped on an empty hill road, one seated at the handlebars and the other behind, both turned to the camera and laughing. We are wearing riding jackets and jeans, helmets resting on the mirrors. Mountains and morning mist behind us, travel photo feel. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
8. Festive Mirror Selfie

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us taking a mirror selfie at home before a function, one of us holding the phone at chest height. We are dressed in a silk saree and a kurta. A warm lamp and a doorway are visible behind us. Natural indoor light, real phone-camera look, both faces fully visible beside the phone. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
9. Bookstore Aisle Candid

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us in a narrow aisle of an old bookstore, one of us reading from an open book while the other looks on over the shoulder, both smiling. We are wearing cosy sweaters. Warm tungsten light, tall wooden shelves, quiet and cosy. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
10. Anniversary Candlelight Dinner

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us at a candlelit dinner table for two on a terrace at night, raising our glasses in a toast and smiling at each other. We are wearing a black dress and a black suit. Fairy lights overhead, city lights far behind, warm candle glow on both faces. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
11. Tea Garden Walk at a Hill Station

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us walking along a narrow path through green tea gardens on a misty hill, one leading the other by the hand and looking back with a smile. We are wearing light sweaters and jeans. Soft morning mist, rolling hills behind, cool natural colours, wide travel-photo framing. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
12. Scooter Ride Through the Old City

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us riding a mint green scooter through a narrow old-city lane with painted doors and hanging lights, both laughing, the pillion rider holding on. We are wearing casual shirts and jeans. Slight motion blur in the background only, faces sharp, warm evening light. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
13. Cooking Together at Home

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us in a bright home kitchen cooking together, one stirring a pan and the other offering a taste from a spoon, both laughing. We are wearing casual home clothes with aprons. Daylight from a window, steam rising, a slightly messy counter, candid everyday moment. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
14. Movie Night Under Fairy Lights

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us on a terrace at night sitting on floor cushions under fairy lights, sharing a blanket and a bowl of popcorn, with a projector glow on a white wall behind us showing no readable images. We are wearing hoodies. Cosy, warm, softly lit faces. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
15. Close-Up, Foreheads Touching

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: A tight close-up of us with our foreheads touching and eyes closed, both smiling gently. We are wearing white outfits. Golden hour, very soft background blur, warm skin tones, quiet and emotional. Both faces must stay fully recognisable in profile. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
16. Train Window Journey

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us seated side by side at an open Indian train window, one resting their head on the other's shoulder, watching green fields pass. We are wearing casual travel clothes. Soft daylight on our faces, a little wind in the hair, nostalgic travel mood. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
17. Boat Ride on a Lake at Sunset

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us sitting facing each other in a small wooden boat on a calm lake at sunset, with hills reflected in the water. We are wearing a flowing dress and a linen shirt. Warm orange light, gentle ripples, wide shot with both faces lit and clear. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
18. Walk Through a Festive Market

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us walking through a crowded festive market at night, holding hands, with strings of lights and lanterns overhead. We are wearing traditional festive wear. The crowd around us is softly blurred, colourful bokeh, candid shot from the front. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
19. College Sweethearts on the Steps

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: Show us sitting on the wide stone steps of an old college building, sharing earphones and laughing, with backpacks beside us. We are wearing casual college clothes. Late afternoon sun, trees throwing soft shadows, relaxed and youthful. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
20. Black-and-White Studio Couple Portrait

BeforeAfter · ChatGPTIDENTITY LOCK: Use the uploaded photo of the two of us as the only identity reference. Keep both exact faces: face shape, eyes, nose, lips, jawline, skin tone, facial hair and real age for each person. Keep both hairstyles, our height difference and our body proportions. Do not blend, swap, beautify or lighten our faces, and keep each person on the same side as in the photo unless the scene says otherwise. SCENE, POSE AND STYLING: A black-and-white studio portrait of us standing close, one behind the other with arms around, both looking at the camera with calm smiles. We are wearing simple black outfits. Plain dark backdrop, soft single light from the side, fine grain, timeless feel. CAMERA AND LIGHT: Follow the framing described in the scene. Full-frame camera look with natural perspective and no wide-angle distortion of the face. POSE RULE, which overrides any head or gaze instruction in the scene: keep my head straight and level exactly as in my photo, with the chin in a neutral position (not raised, not tucked), no head tilt, and no head turn of more than about 10 degrees, so my real face shape stays accurate. BODY RULE: natural human proportions, with a normal neck length and width; never stretch or elongate the neck, shoulders or face. Unless the scene needs otherwise, I look straight into the camera lens. The face must be large enough in the frame to be clearly recognisable, even in a full-body shot. Eyes in sharp focus, realistic depth of field, background detail falling off naturally. Light on the subject must come from the same direction, colour and softness as the light in the scene, with matching shadows and reflections. Both faces equally sharp and equally well lit. FINISH: Photorealistic photograph, not an illustration or 3D render (if the scene asks for a toy, figurine or drawn stickers, photograph those realistically). Real skin texture with visible pores, natural under-eye detail and fine hair strands. Fabric shows real weave, folds and weight. Correct hands with five fingers, natural body proportions, consistent white balance between subject and background. High resolution and clean detail, unless the scene asks for grain, flash or a film look. No over-sharpening. AVOID: a changed or generic face, smoothed or plastic skin, lightened skin tone, altered age or body shape, a stretched or elongated neck, extra or missing fingers, warped hands, duplicated people, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No face blending between the two of us, no extra people.
How to use a prompt
- Pick your options and tap Copy prompt.
- Open ChatGPT or Gemini and upload a clear, front-facing photo.
- Paste the prompt and send. Run it again if the first result is off.
Which photo to upload
- One photo with both of you in it gives the most natural result.
- Both faces should be sharp, similar in size and not overlapping.
- If you use two separate photos, say who is on the left and who is on the right.
If the result goes wrong
Add: "The person on the left stays on the left. Do not mix our features." Then run again.
Add: "Keep our real height difference from the photo."
Add: "Keep real skin texture with pores; no smoothing or beauty filter."
Run it again, or change the pose in the prompt so the hands are in pockets or out of frame.
Questions and answers
Should I upload one photo or two?
Either works. One clear photo of both of you gives the most natural result. If you use two separate photos, add a line saying who is on the left and who is on the right.
Will the edited photo still look like me?
Every prompt here starts with a face-lock line that tells the AI to keep your face, skin tone and features unchanged. If the face still drifts, upload a clearer, front-facing photo and run the prompt again.
Do these prompts work in both ChatGPT and Gemini?
Yes. They are written in plain language that both ChatGPT and Google Gemini understand. Upload your photo first, then paste the prompt.