
[Overall Style] 1:1 square composition, a single standalone image, hyper-realistic Korean-style adult female indoor portrait photography, cool and gentle temperament, low-saturation creamy warm white tones, soft natural light, delicate skin texture, slight natural soft focus, authentic smartphone photography feel. [Facial Features] A beautiful adult East Asian woman aged 23 to 25, delicate small oval face, soft and smooth jawline, small rounded chin, clear cool white skin, light peach pink blush. Bright and clear dark brown almond eyes, natural double eyelids, subtle aegyo-sal, long curled eyelashes, light pink-brown eyeshadow, soft slightly upturned thin eyeliner. Slender straight nose bridge, small natural nose tip, soft full rose bean-paste pink lips with a natural dewy glow. Lips naturally closed, eyes looking directly at the camera, quiet, gentle expression with a slight cool aloofness, retaining realistic subtle skin texture. [Hair — Core] Thick, smooth dark black-tea-colored waist-length hair with a natural dark chocolate brown sheen. Voluminous at the crown, styled in a loose half-up look, natural slightly off-center part in the front, a few thin light wispy curtain bangs falling down. Some hair on both sides naturally gathered toward the back, revealing the ears and pearl earrings, with the rest of the long hair draping over the shoulders and chest. The long hair is overall smooth, with slight natural waves at the ends, retaining realistic individual strands, natural volume, and a few loose flyaway hairs. [Clothing and Jewelry] Wearing a light cherry blossom pink thin-strap camisole top, soft fine cotton fabric, simple shallow curved neckline. Layered with a creamy white loose knit cardigan, soft fine knit texture, front naturally open, revealing the light pink camisole and natural collarbone lines. Long sleeves slightly covering the wrists, with realistic soft fabric wrinkles. Wearing small white pearl teardrop earrings and an extremely thin silver collarbone chain. [Pose] The person is sitting on the edge of a bed in a bedroom, upper body naturally upright, body facing slightly sideways toward the camera. Head gently tilted, chin naturally slightly tucked, eyes softly looking directly at the camera. One hand on the left side of the frame is naturally raised, palm gently resting against the cheek, fingers softly extended along the jawline, forming a gentle face-cradling pose. The other hand is raised beside the shoulder, gently tidying the falling long hair, fingers naturally curved. Shoulders relaxed, posture loose and natural, both hands with realistic structure. [Background Environment] A clean and warm modern creamy white bedroom, behind the person is a large bed with pure white bedding and soft white pillows. The background is a light beige-white wall and a cream-colored upholstered headboard, the room is clean and quiet with no cluttered decorations. [Lens and Lighting] 1:1 square, equivalent 50mm portrait lens, eye-level straight-on angle, close-range chest-up half-body close-up, face centered in the frame. Soft cool white frontal natural fill light illuminates the face, nose bridge, cheeks, and collarbone. Skin appears clear cool white, cheeks have a faint peach pink flush, lips have a delicate natural reflection. Dark black-tea long hair has soft dark brown highlights, the background retains a faint warm white ambient light. Low-saturation creamy white and light pink tones, soft contrast, realistic depth of field, slight natural grain, no excessive skin smoothing or sharpening. [Negative Prompts] Anime, illustration, 3D render, CG fake face, plastic skin, excessive skin smoothing, exaggerated large eyes, overly pointed chin, misaligned features, asymmetrical eyes, wig, clumped hair, stiff strands, extra fingers, deformed palms, twisted wrists, misaligned shoulders, abnormal body proportions, clothing clipping, severe overexposure, strong HDR, excessive sharpening, obvious AI feel, text, watermark, LOGO, collage.
This image was generated with GPT Image 2.5 by OpenAI. The prompt on this page is the exact text used to create it.
The example was generated with GPT Image 2.5 using: 1:1 · Fashion · Realistic · Portrait. Reusing these settings gives the closest match.
Copy the prompt as-is first, then replace only the subject while keeping the style, lighting, and composition keywords. Generate a few variations — outputs differ between runs.
Yes. Prompts work best as starting points — adjust descriptors, aspect ratio, or style tags to make the output your own.