GPT Image Prompt
Same adult woman from the active LoRA identity reference image, preserving exact face and body identity before any outfit, pose, scene, camera, lighting, or aesthetic instruction: the same recognizable facial geometry, fair skin tone, blonde low ponytail with loose face-framing strands, the same shoulder width, shoulder-to-head relationship, torso length, torso-to-leg balance, natural waist thickness, hip width, thigh volume, body mass distribution, and the same relaxed physical presence. Preserve both facial and body continuity exactly. Do not beautify, slim, elongate, narrow, or replace her with a more model-like or influencer-like body type. Keep her as the same real person, not a similar-looking substitute.
Create a realistic iPhone-style candid daytime travel photo of her in a casual outdoor theme-park street setting. She is seen from behind at close range, with her upper body turned slightly away from the camera while she looks back over her shoulder. Preserve a natural over-shoulder silhouette and believable body twist without exaggeration. Her left arm hangs naturally beside her body with loosely relaxed fingers, and her posture should feel casually caught in motion rather than posed. Her expression should feel fresh and candid: a soft over-shoulder glance, relaxed eyelids slightly narrowed by bright daylight, and a small uneven closed-mouth smile that feels quietly amused and naturally alive rather than stiff or performed.
She wears the same white fitted sleeveless ribbed tank top with thin straps, light blue high-rise jeans with realistic seams and back pockets, a thin necklace, and a white shoulder bag strap over her shoulder. The environment is a lively public theme-park street with a red popcorn cart close behind her, palm trees, café tables, pedestrians, colorful hanging decorations, and patterned pavement. The space should feel socially believable, slightly busy, and naturally imperfect, with ordinary public-space clutter and realistic depth layering.
All expression, gesture, outfit, pose, scene, camera, lighting, and realism behavior remain subordinate to the active LoRA identity reference. The final image must still be unmistakably the exact same LoRA subject in both face and body, not a beautified replacement, not a generic attractive version, and not a same-face result on a different body type. Preserve the requested human moment while keeping the active LoRA identity fully intact.
Use realistic handheld iPhone capture behavior: close from behind with slightly imperfect crop balance, mild smartphone wide-angle perspective, subtle framing asymmetry, and a photographed-not-directed feeling. Keep bright natural daylight exposure with believable public-space lighting, realistic highlight and shadow behavior, mild uneven sharpness between subject and background, slight compression softness, natural hair flyaways, and normal smartphone reconstruction imperfection. Avoid cinematic lighting, editorial polish, fashion-model posing, fake candid energy, beauty-filter skin, fake HDR, over-clean rendering, excessive sharpness, artificial blur, mannequin posture, dead-eyed expression, copied reference stiffness, exaggerated body proportions, waist slimming, hip narrowing, thigh reduction, leg elongation, or sterile AI perfection. Realism always wins over aesthetics.
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.
Nanobanana Prompt
How to use: Copy and paste this prompt into ChatGPT, Gemini, Nano Banana, or your favorite AI image tool. If it mentions LoRA, reference image, uploaded photo, or identity reference, upload your own photo first. No reference photo? Replace the character with a clear age, gender, and nationality, such as “25-year-old Japanese woman” or “30-year-old American man”.