Translate the following AI generation prompt into English. Output ONLY the translated text — no quotes, no markdown, no explanations. Preserve line breaks and formatting. Use the uploaded reference image as the exact character identity reference. Keep the same woman throughout the entire video — identical face, hairstyle, skin tone, body proportions, makeup style, and recognizable appearance. She is a professional adult fashion model preparing for a stylish outdoor photoshoot. Create a fast-paced, cinematic fashion behind-the-scenes sequence where the photographer is never visible in frame. The camera is always positioned from the photographer's perspective, making it feel like we are seeing the photoshoot through their camera. The video opens inside a stylish bedroom or makeup studio. She finishes her makeup, fixes her hair, checks herself in the mirror, puts on her accessories, grabs a small fashion bag, and confidently walks outside for the shoot. She arrives at the first location: a beautiful street-side café. Wearing a stylish fitted crop top with a mini skirt, she stands beside the café window, adjusts her hair and looks directly toward the unseen photographer. She says naturally: “Okay, here… now click.” A realistic camera shutter sound plays — CLICK. Instant cinematic transition to the next location. Now she is sitting casually on a vintage scooter parked along a charming street, wearing a different fashionable outfit. She crosses one leg over the other, turns her face toward the camera, plays with her hair and gives several confident poses. She looks toward the unseen photographer and says: “This angle… now click.” CLICK. Quick flash-style transition. Next, she appears in a glamorous resort-style outfit with a tasteful two-piece swimwear look, posing beside a luxurious poolside setting. She walks toward the camera, turns over her shoulder, then gives a confident editorial pose. She smiles and says: “Wait… this one. Click.” CLICK. Cut to a busy urban street. She is now wearing fitted jeans with a stylish crop top and heels. She leans casually against a street pole, changes poses with every camera movement, looks away, then suddenly looks directly into the lens. “Okay, hold it… now click.” CLICK. Rapid transition to another location: a colorful outdoor café terrace. She wears a completely different elegant outfit, sits at a table with a coffee, crosses her legs, takes a small sip, then poses naturally while looking toward the unseen photographer. “One more… click.” CLICK. Final location: golden-hour city street. She wears her strongest fashion look, walks toward the camera, stops under warm sunlight, turns slightly, lets her hair move naturally in the breeze and gives a confident final model pose. She looks directly into the camera with a playful smile: “That’s the one.” One final realistic camera shutter — CLICK. Use seamless match cuts, camera-flash transitions, natural body movement, realistic hair and clothing physics, shallow depth of field, cinematic lens changes, handheld photographer perspective, natural street ambience, realistic lighting, premium fashion-commercial aesthetics, photorealistic skin texture, elegant color grading, strong temporal consistency, and smooth transitions between locations. No photographer visible, no camera visible, no logos, no subtitles, no watermarks, no distorted hands or face, no identity changes. 16:9 cinematic composition, high-end fashion editorial photography, realistic camera shutter sounds and natural location ambience.
This clip was generated with Seedance 2.5 by ByteDance. The prompt on this page is the exact text used to create it.
The example was generated with Seedance 2.5 using: 16:9 · 0:15 · Character · Cinematic · Fashion. Reusing these settings gives the closest match.
Copy the prompt as-is first, then change the subject while keeping the camera, motion, and lighting terms. Video models are sensitive to wording, so expect a few runs.
Yes. Prompts work best as starting points — swap scenes, adjust pacing terms, or change the aspect ratio to fit your project.