Image1 Identity Lock Morning Brief
A reusable identity template: inherit only the face and hairstyle from Image1, ignore everything else, and play out a groggy morning bathroom routine.
提示词
Subject: Person from Image1. Face and hairstyle must match Image1 exactly; do not change identity. Ignore its outfit, background, pose, and text. Outfit: oversized casual sleepwear, messy morning look. 9:16 vertical. Old iPhone everyday-video aesthetic throughout: static phone propped on bathroom sink, standard 1x lens, no distortion, heavy noise/compression, slight mirror steam, warm/off-white overhead lighting. Natural skin, pores, flyaways, under-eye tiredness. No beauty filter, grading, cinematic/CG look, fisheye, vignette, or legible text. 0–4s: Groggy, walks in yawning, glances at phone/mirror, rubs eyes. 4–8s: Brushes messy hair and mutters, “okay... five more minutes wasn't enough.” 8–12s: Steps on bathroom scale, looks down, gives a subtle eye-roll/sigh/shrug, steps off. 12–16s: Opens small closet, holds up two shirts one after another, indecisive. 16–19s: Chooses the first, tosses the other aside, looks at camera and says softly, “…this one. good enough for today,” with a tired smile; freeze final frame. Bathroom clutter: toothpaste/skincare bottles, but all labels illegible. Sound only: bathroom ambience, hairbrush, scale beep/click, fabric rustle, close muffled sleepy voice with slight bathroom reverb. Keep all cuts and actions; no skipped scenes or on-screen text.
如何为 Seedance 2.5 改写这条提示词
- 1替换主体时保留镜头语言：镜头推进节奏、时间轴分镜（如 0-2s / 2-5s）和光线描述是画面电影感的关键。
- 2注意时长与画幅的匹配——更长的镜头需要更多动作关键帧，竖屏构图更适合紧凑取景和更快节奏。
- 3保留负面约束（无文字水印、不变脸、无 Logo）——它们能避免 AI 视频生成中最常见的瑕疵。
相关提示词
本提示词库中的所有内容均采集自公开互联网，仅供学习交流参考。 如有侵权，请告知我们，我们将第一时间删除。