ChatGPT

Royal Burgundy Temple Portrait

Written for ChatGPT. Results and reference-photo support may differ across models.

The complete prompt

Use the uploaded user photo as the ONLY source of the final person's identity. Preserve the user's exact recognizable facial identity, facial structure, proportions, face shape, forehead, hairline, eyebrows, natural eye shape and spacing, nose, lips, cheeks, cheekbones, jawline, chin, skin tone, natural skin texture, hair, and all distinctive facial characteristics. Do not copy the identity or facial features of the reference subject. Do not beautify, reshape, slim, masculinize, feminize, age, de-age, or otherwise reinterpret the user's face. The user's original facial expression, gaze, and head pose must NOT be transferred; use the reference image only to determine how the user's identity should appear in the recreated scene.
Recreate the reference as a highly detailed cinematic Indian/South Asian fashion portrait in a vertical 2:3 composition. Show the user's identity as a full-body woman standing in an ornate historic South Asian temple/palace courtyard, while preserving the user's actual gender and identity exactly as provided by the uploaded photo. The main subject stands slightly left of center, occupying most of the lower and middle frame, with her body in a graceful three-quarter orientation. Her torso is angled slightly toward the right side of the image while her face turns gently toward the left/front, following the reference pose. Her posture is elegant and relaxed, with shoulders naturally lowered, torso upright, one arm bent softly in front of the waist and the hands resting naturally together near the midsection. Reproduce the reference's overall graceful standing posture and body positioning precisely.
Reconstruct the reference facial behavior on the user's identity: a soft, pleasant, confident expression with a subtle natural smile, relaxed cheeks, gently lifted mouth corners, calm eyes, and a warm serene emotional mood. The eyes should gaze slightly toward the left side of the frame rather than directly into the camera, matching the reference. Preserve the reference's gentle head rotation and slight natural head angle. Do not use the expression, gaze, or head position from the user's source photo.
Dress the user in the same style of flowing deep burgundy/maroon traditional South Asian Anarkali-style gown seen in the reference. The outfit is floor-length, richly pleated and voluminous, with a fitted upper bodice and long sleeves. Add intricate antique-gold floral embroidery along the neckline, sleeve cuffs, front/lower hem, and decorative borders. Include a matching sheer maroon dupatta flowing dramatically from the body toward the right side of the frame, creating a large sweeping translucent fabric shape with embroidered edging. Preserve realistic fabric weight, folds, fine textile detail, embroidery, and natural movement. Add ornate traditional silver-toned jhumka earrings and a coordinated decorative hair accessory, while keeping the user's own hairline and recognizable identity intact. If culturally appropriate to the reference, include a tiny maroon/red bindi centered on the forehead without altering the user's facial structure.
Set the scene inside an ancient ornate South Asian architectural courtyard with richly carved stone pillars, weathered carved walls, temple-like arches, stone steps, and decorative masonry. Cover the upper-left and side architectural areas with abundant vivid pink/magenta bougainvillea flowers and green foliage. Scatter numerous delicate pink flower petals naturally across the stone floor and through the air around the subject. In the distant background, show softly blurred historic towers, arches, carved structures, and warm sunlit architecture.
Match the distinctive double-exposure-style composition of the reference: behind and above the main full-body figure, create a large semi-transparent close-up portrait of the SAME USER IDENTITY, occupying much of the upper-right portion of the frame. This enlarged face must unmistakably remain the user's identity, not the reference person's identity. The large portrait should show the same reference-derived warm smile, relaxed eyes, and sideways gaze, with the face angled similarly to the reference. Blend this enlarged portrait softly into the warm architectural background and sunlight so it feels like an intentional cinematic layered photographic composition rather than a separate pasted image.
Use warm golden-hour backlighting coming from the upper-left/center background, producing glowing rim light around the woman's hair, shoulders, and flowing fabric. Create luminous amber highlights, gentle lens glow, soft atmospheric haze, subtle volumetric sunlight, realistic shadows, and warm highlights on the stone architecture. Pink flowers should catch small touches of sunlight. Maintain rich maroon, warm gold, stone-brown, green, and pink color harmony.
Camera: vertical 2:3 aspect ratio, approximately 50mm lens perspective for the main figure, full-body framing from the top of the hair to the feet with enough space around the flowing dress and dupatta. Camera approximately at natural eye/chest height with a slightly cinematic perspective, not extreme wide-angle distortion. Keep the main figure sharply detailed while the distant architecture has moderate depth-of-field blur. The enlarged facial portrait should remain highly detailed but softly blended at its edges. Preserve realistic anatomy, natural hands and fingers, accurate fabric physics, realistic jewelry, photographic skin texture, fine hair strands, cinematic depth, high dynamic range, and premium editorial photography quality.
Composition must closely match the reference: ornate carved pillar and bougainvillea framing the left edge, large translucent close-up face dominating the upper-right, full-body figure in the lower-left/center, sweeping maroon dupatta extending dramatically toward the lower-right, historic architecture receding into the center background, and scattered petals throughout the foreground. The final image should feel romantic, regal, elegant, warm, cinematic, richly detailed, and photorealistic. Do not introduce text, logos, watermarks, extra people, modern objects, facial distortions, duplicated limbs, malformed hands, unnatural anatomy, plastic skin, excessive retouching, or any alteration of the user's recognizable identity.

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.

Photo studio
AI-generated example

A little inspiration for your own photo.

1Add your photos
Person A

Keep the face clearly visible

Person B

Keep the face clearly visible

JPG, PNG or WebP · Max. 10 MB each

Your photos are sent only when you choose Generate. Use photos you have permission to use.

2Make it yours
Change the details
Edit your prompt
Open Gemini

Getting ready…

Sign in to your account

Continue with your Google account.

You can browse and copy prompts without signing in.

How we use your information: Privacy policy