White Studio High-Key Fashion — Emerald Slip Dress

MiniMax H3VerticalFashionRealisticHandheld Camera6s
A vertical fashion short in a bright, high-key white studio: a high-angle overhead shot combined with a slightly wide-angle selfie perspective. The prompt locks down every detail from facial features to hairstyle, jewelry, and dress — a textbook example of writing for character consistency.

PROMPT · Prompt

Create with AI
9:16 vertical, approximately 6 seconds, ultra-realistic real-person fashion short video, bright high-key white studio environment, high-angle overhead shot, slight wide-angle selfie perspective, clean high-exposure portrait photography. The frame features a clearly adult young East Asian woman, approximately 20–24 years old, tall and slender build, defined waist, long limbs, overall natural and proportionate model figure. She has a delicate, small oval face, narrow and smooth face shape, clear and soft jawline, fair and translucent skin tone, face retains natural skin texture, delicate features, slightly large eyes, black irises, naturally long lashes, soft eyebrow shape, thin straight nose bridge, naturally rosy lips. She has long, dark brown-black wavy hair, voluminous at the crown, airy bangs, ends forming natural large waves, long hair draped mainly over her right shoulder and chest, hair naturally swings when she turns. She wears a pair of simple, eye-catching gold hoop earrings, and an extremely thin gold necklace, with a small gold pendant on her chest. She wears an emerald green or dark green thin-strap tight-fitting dress, thin straps, low square-neck design, with noticeable vertical gathering and slight cinching structure at the chest, fabric is soft, slightly glossy satin or stretch material, the garment fits closely to the waist and body curves, the hem is relatively short, overall style simple, refined, leaning towards summer light-mature fashion. She wears light brown or caramel-colored pointed-toe low-heel shoes. The scene is a pure white or off-white minimalist photo studio, white floor and white background almost blending together, no obvious wall corner boundaries, the entire environment is highly bright, clean, and soft. Only a very small amount of white soft furnishing or low white objects appear in the background, kept minimalist, not stealing focus from the main subject. The camera is positioned about 30–50 cm above and in front of the subject's head, high-angle overhead shot, viewing angle about 30–45 degrees, using approximately 24–28mm slight wide-angle perspective, making the subject's eyes appear slightly closer to the camera, with the body naturally extending downward, forming a typical high-angle fashion selfie effect. The subject actively looks up at the camera most of the time. 0–1 second The subject quickly approaches the camera from a slightly farther position on the left side of the frame. The camera maintains a high-angle overhead shot. She steps forward, body slightly leaning forward, right leg stepping forward, long hair gently swaying. As she approaches, the subject quickly transitions from a near full-body composition to a mostly upper-body composition. She looks up at the camera, expression natural and relaxed. 1–2 seconds The subject has now approached the camera. Her body tilts slightly to the left, hands naturally placed on either side of her hips or behind her back. Her face lifts, looking directly at the camera. A slight smile appears at the corners of her mouth. Long hair falls over her right shoulder. The camera shows a very slight floating sensation, but overall remains stable. 2–3 seconds The subject begins to turn toward her own left side. Shoulders and upper body rotate first, face turns away from the camera afterward. The camera briefly catches her side profile and the back of her head. The long wavy hair swings noticeably but naturally as the body rotates. The movement is light and fluid, not a sudden rapid spin. 3–4 seconds After completing a half turn, she turns back to face forward again. Her body moves slightly closer to the camera. Her face re-enters the center of the frame. Hands clasped behind her back or lightly resting on her waist. She looks up directly at the camera, showing a noticeable but natural sweet smile. Her head tilts gently to one side. 4–5 seconds The subject lowers her head briefly to look to one side of her body. Then slowly raises her eyes. Right shoulder slightly forward. Waist forms a natural S-curve. Long hair falls naturally along the right shoulder. The earrings sway slightly with the movement. 5–6 seconds The subject approaches the camera again. Upper body occupies most of the frame. One hand naturally rests on the waist. The other hand stays behind the body or at hip level. She first looks to the left of the frame, then quickly turns her gaze back to the camera. Finally settling into a pose with a slight upward tilt of the head, body leaning to the side, looking directly at the camera. Expression maintains a natural smile with a slight playful feel. The entire video emphasizes the sense of interaction between the subject and the camera. Movements include natural stepping, slight turning, looking back, raising the eyes, tilting the head, lowering then raising the head, resting hands on the waist, slight side-to-side swaying of the body. Exaggerated dancing is prohibited. The camera essentially maintains a high-angle overhead shot, but follows the subject with very subtle movement and slight orbiting. As the subject approaches, the camera shows natural perspective changes. Overall it resembles a fashion short video shot by a friend holding a phone from above the subject's head, pointing downward. Lighting uses a large softbox or shadowless studio top light, the white environment creates abundant soft diffuse reflection. The subject's face exposure is bright and even. Skin has a clean, translucent cool-white tone. Eyes have natural catchlights. Hair maintains dark color and clear strand detail. The green dress color is saturated but not fluorescent. Overall color tone is white background with emerald green main subject, clean, upscale, refreshing. 4K ultra-high-definition, realistic phone photography texture, high-definition face, realistic hair strands, realistic skin texture, soft highlights, high dynamic range, slight depth of field, upscale fashion editorial texture, TikTok fashion short video, realistic natural movement, consistent character identity throughout. The subject's facial features, face shape, hairstyle, clothing, jewelry, and body type must remain completely consistent from the first frame to the last frame. No face shape drift, no changes to facial features, no sudden face swaps, no hairstyle changes, no dress color changes, no clothing structure changes, no body proportion changes, no waist deformity, no abnormal fingers, no extra hands or feet, no twisted limbs, no sudden changes in breast shape, no disappearing earrings, no background changes, no obvious camera shake, no anime feel, no plastic skin, no excessive skin smoothing, no overexposure causing loss of facial features, no severe motion blur, no sudden teleportation of the subject.

✍️ Editor’s Notes

Choosing MiniMax H3 here is aimed squarely at its strength in photorealistic human portraiture, but it also exposes that category of model's biggest weakness — facial and body-type consistency. That's why the back half stacks an extremely long negative list — “no face-shape drift, no changes to facial features, no sudden face swaps” — which is essentially brute-forcing a lock on the exact points where the model is most likely to break. The front half breaks the action into six timed beats — step forward, turn, profile, face front again, look down then up, lean into the lens — writing the high-angle selfie camera logic in extreme detail. This kind of elevated-angle, light-wide-angle fashion short demands a lot of angular precision, and if the character's face breaks even once the whole clip is ruined, so the more exhaustive the negative list, the safer the outcome actually is.

Create with AI

Alt. Take

Related Works

׋›
↑