GPT Image Prompt
Use the active LoRA identity reference as the absolute authority for the final subject’s face and full-body identity. Preserve the exact same woman from the reference, including her recognizable facial geometry, eye spacing, soft jaw and cheek structure, warm fair skin tone, long pale blonde hair with pink-purple lower sections, and the same full-body proportions and physical presence: same shoulder width, shoulder-to-head relationship, torso length, torso-to-leg balance, waist thickness, hip width, thigh volume, leg length ratio, and overall body mass distribution. Do not beautify, slim, elongate, narrow, or redesign her body or face.
She is standing beside an open white car door on a coastal roadside near sunset, leaning casually into the car in a believable, weight-aware way. One arm is naturally braced on the open car door and the other is lifted, holding a small silver flip-style phone close to her face with realistic grip alignment and natural finger spacing. Her expression should feel caught in a fresh candid moment: a playful side glance toward the phone, relaxed eyelids, and an open uneven smile as if she was mid-laugh, alive and spontaneous rather than stiff or posed. Keep the white cropped ribbed tank top with pink “WEST COAST” lettering, light-wash denim mini skirt with pockets and side ties, pink sunglasses resting on her head, layered necklaces including a small heart pendant, hoop earrings, belly piercing, pink nails, white fuzzy wrist cuffs, and a metallic silver shoulder bag. Subtle coastal wind should move a few loose hair strands naturally.
All expression, gesture, outfit, pose, scene, camera behavior, lighting, and realism treatment remain subordinate to the active LoRA identity reference. The final image must still be unmistakably the exact same LoRA subject, not a similar-looking substitute, not a beautified replacement, and not a generic attractive version of the prompt. Preserve both her facial identity and body geometry exactly while applying the requested candid human moment.
Shoot it as a realistic vertical iPhone-style smartphone photo with close handheld social framing, slight wide-angle phone perspective, mild framing imbalance, and a casually imperfect crop. Use bright frontal smartphone flash mixed with the warm dusk sky so the image feels like a real social snapshot, not a cinematic setup. Show ocean and palm trees in the background with ordinary roadside clutter and believable environmental depth. Preserve realistic flash highlights on skin, nails, the white car paint, the flip phone, and the metallic bag. Keep contact physics believable: natural pressure where her arm braces against the door, realistic hand-to-phone connection, stable standing balance, grounded feet, natural clothing tension, and coherent contact shadows. Allow slight uneven sharpness, mild compression, small smartphone-processing imperfections, and ordinary handheld capture inconsistency. Avoid cinematic polish, DSLR blur, fake portrait-mode separation, beauty-filter skin, fake HDR, influencer/editorial styling, over-clean rendering, exaggerated body proportions, perfect symmetry, mannequin stiffness, over-sharpening, and any smartphone angle or perspective that changes her reference body identity.
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”.