GPT Image Prompt
Preserve the exact same young adult East Asian woman from the active LoRA identity reference images, with unmistakable face-and-body continuity and no beautification drift. Keep her recognizable oval facial structure, natural eye spacing, softly defined cheeks, compact jaw and chin, straight-to-soft nose structure, natural full lip shape, fair skin tone, long dark brown to black hair identity, realistic shoulder width, shoulder-to-head relationship, upper-torso proportions, natural waist thickness, and the same overall body mass distribution and physical presence. Do not replace her with a prettier, slimmer, curvier, longer-legged, narrower-waisted, or more model-like version. Preserve the exact LoRA subject, not a similar-looking substitute.
Create a photorealistic casual iPhone-style close portrait of this same woman. Her expression should feel newly captured and alive rather than copied from a stiff reference: relaxed eyelids, a soft camera-aware glance, subtle calm attention, and a tiny uneven softness in the mouth so she feels quietly present and human. Keep the pose natural and close to the requested behavior: upper torso angled slightly away, face turning gently toward the phone, shoulders relaxed and not stiff, with believable neck and shoulder posture. She is wearing a hot-pink satin strappy camisole with realistic glossy fabric folds, pink sunglasses resting on top of her head, fuzzy pink heart-shaped earrings, small stud earrings, and a short pearl necklace. Use a simple pink background. Hair must remain subordinate to the LoRA identity: preserve her recognizable long dark hair with its natural length, density, fall pattern, and face-framing behavior; do not introduce heavy straight bangs or braided styling if that would change her established hair identity.
All expression, gesture, outfit, pose, background, camera behavior, lighting behavior, and realism treatment remain subordinate to the active LoRA identity reference. The final image must still be unmistakably the exact same LoRA subject in both face and upper-body presence, not a beautified replacement, not a generic attractive version, and not a same-face-on-different-body result.
Shoot it as a handheld smartphone portrait at close distance with believable iPhone-style realism: slight framing imbalance, casual human-operated composition, mild mobile sharpness variation, subtle compression softness, slight uneven detail recovery in hair and accessories, natural skin texture, realistic smartphone processing imperfection, and no cinematic lighting, no polished studio retouching, no influencer beauty aesthetic, no fake HDR perfection, no luxury editorial energy, no mannequin stiffness, and no over-controlled composition. Keep the image socially believable, physically plausible, and naturally imperfect like an ordinary real smartphone capture.
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”.