一位年轻女性的逼真高对比度肖像(9:16),她留着短而光滑的黑色精灵短发,皮肤白皙,站在一条向下倾斜的日本城市街道上,回望过肩。面部细节和纹身清晰锐利,景深较浅:左侧颈部到下颌线和脸颊处有黑色墨水叶状藤蔓纹身,右臂有黑色图案袖套,肩部是曼荼罗图案,过渡到前臂的流畅波浪图案。她穿着一件黑色细肩带连衣裙,露背高开衩,右手拿着一部银色智能手机,指甲涂着深红色。背景:米色中层建筑的强烈散景,红色防滑路面车道,围栏上的一张粉色海报,模糊的行人,以及温暖的店面招牌灯光。柔和的日光,右上角有非常细微的蓝色镜头光斑(非晴朗蓝天)。

Use the uploaded reference image as the STRICT PRIMARY visual reference for the clearly ADULT Japanese woman’s FACE, HAIRSTYLE, BODY PROPORTIONS, POSE, CAMERA ANGLE, FRAMING, living room and lighting. If anything conflicts, ALWAYS follow th

3:4 vertical aspect ratio, balcony, heavy rain, hurriedly collecting clothes, anxious expression, diagonal front composition, instead of wearing clothes using one hand to hold a large amount of laundry, firmly covering from below the chest




一部以《疯狂的麦克斯》风格呈现的关于出埃及记故事的多镜头高动作史诗视频。

9:16 vertical orientation, close-up composition from mid-thigh to upper body, CCD direct flash documentary photography, busy city intersection at night after rain, authentic life-like snapshot feel, with a touch of Japanese film and millenn

Create an ultra-photorealistic cinematic fashion photograph using the same young woman from the reference image. Preserve her facial identity, facial structure, hairstyle, skin tone, and overall appearance so she remains unmistakably the sa

**目标:** 你是一位专精于 **Seedance 2.0** 模型架构的专家级视频提示词工程师。你的任务是将简单的用户想法转换为高度结构化、电影感且技术精确的 JSON 提示词,利用 Seedance 原生的视听能力、多镜头一致性和物理引擎。 **输入:** 来自用户的简短描述或概念(例如,“赛博朋克侦探在雨中行走”)。 **输出:** 一个单一、有效的 JSON 代码块,遵循下方的 `Songguoxs/Seedance` 架构。 ## 架构(需严格遵守)