GPT Image Prompt
Photorealistic 2:3 vertical close-up editorial fashion portrait of the same female character identity from the Knowledge reference set, preserving her recognizable facial geometry, natural face proportions, realistic neck-and-shoulder structure, and overall identity consistency while styling her with a short platinum blonde bowl-cut bob, smooth texture, straight blunt micro bangs, and close-cropped hair around the ears and nape. She wears oversized glossy bubblegum pink square sunglasses with translucent magenta-pink lenses, small stud earrings, and visible black tattoo details on the neck and shoulder. Her expression is calm, confident, and editorially neutral, with slightly parted lips and a sideways gaze through the tinted lenses, looking slightly off-camera.
She is shown in a tight head-and-shoulders close-up with head, neck, upper shoulders, and partial upper chest visible. Pose her in a clean editorial head-and-shoulders pose, front three-quarter orientation, with the head tilted slightly upward and turned toward the camera, one shoulder closer to the lens and the bare shoulder line angled diagonally to create subtle fashion tension. Hands must not be visible and should not be invented. Preserve natural portrait proportions, realistic jawline and ear placement, symmetrical but natural eyes behind the lenses, and believable portrait geometry with no oversized head or twisted neck.
For outfit safety, replace any implied topless styling with a smooth opaque strapless fashion top or clean off-shoulder bandeau top in soft nude, ivory, or pale blush fabric, fitted neatly across the upper chest while preserving the bare-shoulder editorial silhouette. Keep the minimal fashion-editorial styling, soft skin-toned palette, pink eyewear accent, and visible tattoos.
Camera and composition: close portrait distance, slightly below eye-level camera height, front three-quarter close-up angle, 50mm natural portrait lens feel with slight compression and no extreme distortion. The subject should fill most of the frame, with the face slightly above center and only minimal negative space. Use shallow depth of field with the subject sharply focused and the background softly blurred.
Lighting: natural daylight or soft studio daylight simulation, with strong side light from the upper left and subtle fill. Keep the light soft but directional, with realistic shadows under the sunglasses, nose, chin, and neck, and controlled highlights on the cheek, lips, shoulder, and glossy sunglass frames. The translucent lenses should catch bright believable reflections. Use soft neutral daylight white balance with warm skin tones, medium contrast, and moderate saturation, with platinum blonde hair, bubblegum pink sunglasses, pale green-gray or soft ivory wall tones, and clean black tattoo ink.
Environment: minimal indoor portrait setting with a plain pale wall, a soft diagonal light shape on the background, and a clean, uncluttered modern editorial mood. The wall texture and shadow transition should remain realistic and subtle, with believable indoor scale and no fake backdrop look.
Quality: highest photorealistic quality, crisp natural subject detail, realistic skin texture with visible pores and micro-detail, natural lip texture, realistic eyelashes visible through the tinted lenses, clean hair strand detail in the blunt bangs, realistic glossy plastic sunglass frames, transparent tinted lens material, believable tattoo texture, and realistic opaque fabric texture. Negative prompt: low quality, blurry, over-smoothed skin, plastic skin, doll-like skin, bad anatomy, distorted hands, extra fingers, missing fingers, fused fingers, warped limbs, broken joints, deformed face, asymmetrical eyes, fake background, inconsistent lighting, wrong perspective, duplicated objects, warped architecture, CGI, anime, cartoon, excessive HDR, over-sharpening, watermark, text artifacts, logo errors, nude, topless, see-through clothing, lingerie, underwear.
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”.