10 prompts · ChatGPT · Gemini
Photo Collage Prompts
One photo in, a whole collage out. These prompts ask for a single image laid out as a grid, film strip, polaroid wall or magazine spread, with you in every frame. Each one says exactly how many frames, what happens in each, and to keep your face the same person throughout.
1. Four Moods Grid Collage

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image laid out as a clean 2×2 grid of four portraits of me, each with a different expression: a wide laugh, a calm serious look, a playful wink and a soft smile looking away. Same outfit in all four: a plain white tee. Same plain warm beige backdrop and the same soft studio light in every frame, thin white gutters between the frames, each frame cropped from the chest up. 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
💡 My face must be the same person in all four frames. Run again if one frame drifts.
2. Film Strip Contact Sheet

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image styled as a 35mm film contact sheet: three horizontal strips of four small frames each, with black film borders, sprocket holes and tiny frame numbers. Every frame is a different candid of me in a white shirt and jeans on a city street: walking, turning, laughing, adjusting my hair, looking into the lens. Black-and-white film look with grain, and one frame circled in red wax pencil as the chosen 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
3. Polaroid Wall of Memories

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image of a wall with nine instant photos of me pinned on a string with small wooden clips, lit by warm fairy lights. Each instant photo shows me in a different everyday moment: at a cafe, on a beach, with a bicycle, reading, laughing, at a market, on a terrace at sunset, in the rain with an umbrella, and a close-up smile. White instant-photo borders, slightly uneven angles, soft 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
💡 Ask for "six photos" instead of nine if the faces come out too small.
4. Magazine Editorial Layout

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image laid out like a fashion magazine spread: one large full-height portrait of me on the left in a tailored black suit, and on the right a column of three smaller frames: a close-up of my face, a detail shot of my hands and accessories, and a full-body walking shot. Clean white page margins, a thin black rule between frames, a neutral beige and black colour palette, sharp editorial studio light. No masthead and no text. 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
5. Day and Night Split Portrait

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image split vertically down the middle. Left half: me in daylight on a sunny street in a white tee and jeans, bright and warm. Right half: me in the same pose and the same spot at night in a black leather jacket, lit by neon signs and street lights. My face lines up across the split so the two halves form one portrait. A clean thin white line divides the halves. 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
6. Travel Postcard Grid

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image laid out as six travel postcards in a 3×2 grid, each showing me at a different place in Jaipur, in a different pose and casual travel outfit: a wide landmark shot, a street food moment, a walking shot from behind looking back, a selfie-style close-up, a sunset silhouette with my face still visible, and a cafe table shot. Each card has a thin cream border and slightly rounded corners. Bright, warm travel-photo colour. 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
7. Couple Photobooth Strip

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: Create one image of two photobooth strips side by side, four frames each, of the two of us squeezed into a booth: laughing, pulling silly faces, one kissing the other on the cheek, both looking at the camera, whispering, and hiding behind our hands. Black-and-white with direct flash, a plain curtain behind us, white strip borders and slightly uneven print edges. 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, 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. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
8. Birthday Frames Collage

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image as a birthday collage of five frames around one large centre portrait of me holding a cake with lit candles. The smaller frames show me blowing the candles, laughing with confetti falling, holding gold balloons, opening a gift, and a close-up smile in a party hat. Same outfit in every frame: a smart black outfit. Rounded frame corners, a soft gold background between the frames, warm party light. No text. 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
9. Torn Paper Scrapbook Page

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image of a scrapbook page with four photos of me fixed on with strips of washi tape: a portrait, a candid laugh, a full-body shot and a close-up of my eyes. Around them are torn paper pieces, pressed flowers, a ticket stub and small doodled stars, on a cream kraft paper background. Soft overhead daylight, real paper texture and slight shadows under each piece. No readable writing. 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
10. Three Looks Lookbook

BeforeAfter · ChatGPTIDENTITY LOCK: Use my uploaded photo as the only identity reference. Keep my exact face: face shape, eyes, eyebrows, nose, lips, jawline, skin tone, facial hair, moles and marks, and my real age. Keep my exact hair texture, length, parting and hairline, and my body proportions, as they are. Do not beautify, slim, lighten, smooth or age my face, and do not replace it with a similar-looking person. If I wear glasses in the photo, keep them. SCENE, POSE AND STYLING: Create one image as a lookbook with three full-body frames of me side by side, same pose family and same plain light grey studio backdrop, in three different outfits: a casual streetwear look, a formal suit or saree and a festive traditional outfit. Even soft studio light, a faint floor shadow under my feet, equal frame widths with thin white gutters. 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. 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, floating objects, a cut-out look around the hair, text, logos, borders or watermarks unless the scene asks for them. No extra people. Every frame must show the same person or people from my photo, with the same face in each frame; no misspelled captions.
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 clear photo of you alone, face towards the camera.
- Even daylight is best; avoid strong shadows across the face.
- For full-body scenes, upload a photo that shows your build, not only a tight selfie.
If the result goes wrong
Upload a sharper, front-facing photo with no sunglasses or heavy filter, then run the same prompt again. Add: "The face must match my photo exactly."
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.
Add: "Match my skin tone to the uploaded photo exactly. Do not lighten."
Questions and answers
My face looks different in some frames. How do I fix it?
Collages are harder for AI because your face is drawn several times. Run the prompt again, or lower the number of frames in the text. Fewer, larger frames keep the face more accurate.
Can I add text or dates to the collage?
The prompts ask for no text because AI often misspells it. Add names and dates afterwards in any photo editor.
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.