Prompt 1
A scene featuring the woman in the uploaded reference image (DO NOT TOUCH FACE). Image 1 is an identity-neutral scene template containing a bright green mannequin placeholder. Image 2 is the target character identity reference for Mila. Replace the green mannequin completely with Mila from Image 2. FACE EXPRESSION IS THE HIGHEST PRIORITY. Reproduce this exact facial performance: Her body faces away from the camera and her head turns left in profile toward the water. The visible facial expression is mostly obscured; keep the relaxed side-profile head angle and downward, calm gaze. Use Image 1 for the exact head yaw, pitch, roll, eyelid geometry, brow position, mouth geometry, facial tension, body pose, and scene composition. Use Image 2 exclusively for facial identity, facial proportions, skin, eye appearance, and hair identity. Do not copy any normalized mannequin facial proportions as identity, and do not reconstruct the original source person's identity. Remove all green color, mannequin material, plastic texture, blank-face artifacts, and placeholder traces. After the face expression, preserve the exact scene from Image 1: pose, body orientation, scale, crop, clothing, props, lighting, shadows, background, and camera angle. The output must contain one real adult woman only, not both a mannequin and a person. 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









