Prompt 1
Image 1 is the identity-neutral chroma-green scene template. Image 2 is the identity reference for Mila. Pose authority: Image 1 controls all scene geometry. Preserve the primary subject's exact shoulder line, neck rotation, head yaw, head pitch, head roll, and eye-gaze direction from Image 1 even when they differ from Image 2. Image 2 controls identity only; never straighten, front-face, recenter, or otherwise normalize the head pose to match Image 2. Scene: Medium shot of the woman in the uploaded reference image (DO NOT TOUCH FACE) kneeling forward on a lounge chair outdoors, body angled toward the camera with torso and thighs visible. Both hands press flat on a towel with pink flower print draped over the chair; long hair falls forward over bare shoulders. Sunny park setting with grass, fruit trees, distant people, and bright daylight. Wardrobe: bikini top with thin straps and a small front bow; lower garment not clearly visible beyond the kneeling pose on the towel. Face: Head faces the camera with slight downward pitch; eyes open and looking forward. Mouth open with tongue extended outward, brows relaxed. Wardrobe: bikini top with thin straps and a small front bow; lower garment not clearly visible beyond the kneeling pose on the towel. Preserve every visible garment and footwear item exactly. Wardrobe geometry authority: Image 1 controls the exact neckline depth and shape, strap placement, visible cleavage and coverage, bust contour created by the garment, hem, fit, fabric tension, and overlap. Do not raise, flatten, widen, or redesign the garment. Wardrobe appearance authority: preserve the garment colors, patterns, sheen, opacity, and fabric texture visible in Image 1; never treat clothing as mannequin material. Hair authority: Image 1 controls hairstyle geometry and style, including length, silhouette, part line, root direction, volume, layered sections, bangs, braids or tied sections, wave or curl groups, separated locks, overlaps, tapered ends, and whether the hair is worn up or down. Image 2 controls the target subject's hair color and identity. Interpret every chroma-green hair section as a geometry guide, not as a solid object. Reconstruct complete photorealistic natural hair with continuous strands and fine texture while preserving the guided section placement and flow. Never return the target subject bald, and never leave a helmet, cap, slab, wedge, faceted polygon shell, or blocky low-poly hair shape. Replace only the primary chroma-green mannequin completely with Mila from Image 2. Replace every secondary chroma-green mannequin with a separate, distinct new adult identity that broadly preserves that secondary subject's visible styling, clothing state, pose, scale, and scene role. Never copy or duplicate Mila onto a secondary person. Use Image 2 exclusively for facial identity, facial proportions, skin, eye appearance, and hair color. Do not copy any normalized mannequin facial proportions as identity, and do not reconstruct the original source person's identity. Match the stated action, camera relationship, face, hand positions and interactions, visible object inventory, person count, pose, crop, clothing state, lighting, background, and composition. Do not add an implied phone, camera, mirror, held prop, person, garment, or text that the Scene does not show. Remove all chroma-green mannequin material, green spill, plastic texture, blank-face artifacts, and placeholder traces from every subject. Preserve legitimate green scene objects and clothing. Photorealistic, natural skin texture, anatomically coherent hands and body, no text.
- Engine
- Seedream V5 Pro
- Dimension
- Portrait (3:4)
- Gender
- Female
- Ethnicity
- White
- Age
- Twenties









