OpenZhenZhen AI 提示词画廊 · MiniMax H3 · video
男友视角·行李箱里只带一个玩偶
Boyfriend's View: Only a Doll in the Suitcase
男友视角·行李箱里只带一个玩偶，使用同名原始提示词配对并提供中英文版本
提示词 / Prompt
中文提示词
[参考生成] 15秒、16:9、真人写实、男友第一人称眼睛视角，一镜到底。<Subject 1>来自<Picture 1>，始终保留同一成年女性的脸、肤色、深色眼睛及深棕色长发；参考图片只用于身份与明确可见的衣着，不是本片开场帧。自然表演与真实物理，普通话对白按下述原句发声，不出现字幕或文字。 温暖日光卧室；女方保留黑色细肩带上衣、深色长发，穿深色长裤。男友站在梳妆柜前，人眼高度略高于她；她完整的头、脸、上身与柜上小型敞开行李箱同时入画。箱盖打开在侧面，不挡脸；箱底已有折好的衬衫。一只几乎和她躯干一样宽的棕色大熊放在旁边，开场主要在画外。前4秒男友从镜头位置说「只准带一个玩偶。」她认真点头答「好，一个。」随后双手抱起同一只大熊，保持脸在熊头旁可见，将熊底放进箱内衣服上；熊坐在箱里，头和上身露出箱沿，她扶稳它。男友看着被挤满的箱子，她看看衬衫又看男友，平静说「你的衣服，穿身上。」然后才露出得意微笑。结尾熊仍在箱里，她仍扶着熊；男友手臂、脸和身体全程不入画，镜头不转到地面。安静卧室声、两人共三句对白、衣物和毛绒落下声；无笑声或音乐。 仅指定人物和物件出现，动作因果与位置连续；男友的脸和身体不入画，只在需要时出现指定的手或鞋。环境声及对白与实际动作同步，无旁白、笑声罐头或额外音乐。
English prompt
subject_definitions: <Subject 1> is the adult woman in <Picture 1>. Preserve her face, long dark-brown hair and black thin-strap top. Dark trousers are original clothing. The image provides her identity and visible outfit, not the room or opening pose. summary: [reference generation] A 15-second, 16:9 live-action male eye-POV packing comedy. The viewer tells <Subject 1> she may bring one toy. She agrees, then places one enormous teddy inside their small suitcase, crowding his clothes. Keeping the bear, she tells him to wear his clothes instead. <Picture 1> supplies her identity. retention_analysis: <Subject 1> (appears in [Shot 1]): fully_preserved - retain the defined identity, hair and top. Trousers, room, suitcase and teddy are original scene elements. detailed_description: mpov, first-person perspective pov video, high angle. Natural live-action, warm bedroom daylight, 15 seconds, 16:9. One continuous eye-POV shot with a clean photographic image and no captions. [Shot 1] I stand close to a bedroom dresser. <Subject 1> stands beside it, a little shorter than me. My gaze is gently downward, framing her entire head, face and upper body together with a small open suitcase on the waist-high dresser. Its lid is open to the side, clear of her face. Folded shirts already occupy the bottom. A large tan teddy waits beside her, mostly outside the initial composition. My hands stay outside the picture. During the opening four seconds, I look at her and say in a conversational adult male voice from my eye position (S1), <d>[Chinese] 只准带一个玩偶。</d> <Subject 1> (S2) meets my eyes and replies in a clear adult female voice, with an earnest nod, <d>[Chinese] 好，一个。</d> She reaches beside herself, takes the teddy in both arms and lifts it into view. Its plush body is nearly as wide as her torso. With her face still visible beside its head, she moves the bear across the short gap and lowers its bottom into the suitcase, onto the shirts. The teddy, not the woman, sits inside the case. Its large head and upper body project above the rim. Its weight settles on the clothes, and her arms keep it upright. The reveal and placement take the middle portion of the clip without an intervening gesture from me. I keep looking at the bear filling the luggage. <Subject 1> (S2) glances at the crowded shirts, then back to my eyes and says with calm certainty, <d>[Chinese] 你的衣服，穿身上。</d> Only then does a pleased smile spread across her face. End with the same bear still seated in the suitcase and her face readable beside it. She keeps supporting the bear, leaving the outcome visible. The camera remains at my standing eye height throughout; no floor view is needed. My hands, arms, face and torso remain outside the composition for the entire shot. overall_soundscape: Quiet bedroom ambience, two distinct conversational voices, clothing rustle and a soft plush settling sound. The three specified lines are the only dialogue; no laugh track. non_diegetic_music: N/A
主题与风格
探索更多图片和视频提示词 · 生成图片 · 生成视频 · 在 AI 画布中创作
相关作品
- 暮色桥面追车
生成一段20秒、16:9画幅的电影感视频。蓝调黄昏时分，在一座延伸很远的混凝土桥上，一辆深色双门轿跑车沿车道标线行驶，并谨慎地绕过一辆较慢的卡车。镜头位于岸边，使用长焦镜头向右进行稳定的横向摇摄，压缩桥面空间，让轿跑车看起来缓慢爬过画面，同时车灯形成轻微拖影。潮湿的沥青映出最后的冷蓝灰天光、温暖的尾灯以及迎面车辆的前灯。采用35毫米变形宽银幕质感、椭圆形散景、细腻胶片颗粒和克制的对比度，车辆运动与反射须真实可信。保持宽阔且连续的构图，不要剪辑、文字、标志或可见车牌。
- 雪山公路上的拉力赛车与雪崩追逐
16:9，15秒电影感真人实拍拉力赛车片段，采用一镜到底的高速追逐感。0-3秒：航拍展现狭窄的积雪公路切入陡峭高山悬崖，锯齿状雪峰和下方云海铺陈开来；一辆红白黑涂装的拉力赛车沿着蜿蜒山路疾驰，松雪飞扬，远处山坡有雪崩云团移动。3-7秒：动态跟拍贴近赛车，车辆在狭窄雪弯中漂移，轮胎将厚重雪粉甩向岩壁，镜头大幅移动并带有强烈运动模糊。7-10秒：从车后方斜侧跟随赛车越过裸露山脊，背景山坡上的雪崩雪雾滚落。10-12秒：短暂切入车内，成年戴头盔的车手穿着赛车服，双手紧握方向盘，神情专注紧张，挡风玻璃外可见积雪道路。12-15秒：镜头回到车后，赛车冲向山体中凿出的黑暗雪洞并驶入其中，以车辆进入隧道结束
- 雾桥精灵少女的动感街舞
制作一段20秒、16:9画幅的单镜头连续长镜头视频，场景是在雾气弥漫、远处可见城市天际线的悬索桥上。使用所提供的身份参考图来确定成年女性精灵舞者的脸部、尖耳朵、金色短发和整体外貌，并严格保留参考图中的服装。她正对镜头表演高能量K-pop舞蹈。0–4秒：从远景全身开始，她在桥面上奔跑并滑步接近镜头，以脚尖点地落步；摄影机向前跟拍并收紧到上半身，她在尖耳朵旁卷起一缕头发，俏皮地直视镜头。4–8秒：摄影机围绕她的躯干快速旋转、甩镜，她完成利落的手臂伸展、胸部重拍、肩部锁定和手指舞动作。8–12秒：摄影机横向扫动，短暂拉远到四分之三身和全身构图，捕捉她的侧向滑步、踢步换重心和宽腿下沉姿态，随后迅速回到
- 飞越悬空山国
制作一个20秒、9:16画幅的超写实真人电影奇幻镜头，始终一致使用所提供的参考图：参考图1定义成年骑士的真实脸部、头发、年龄、身体比例、服装、皮革装备和身份；参考图2定义巨龙的头部、角、眼睛、鳞片、双翼、尾巴、鞍具、颜色与生物结构；参考图3定义山地中世纪王国、悬崖、堡垒、森林、瀑布、河流、云层和自然光线。全程保持角色与环境设计连续一致。 这是一个不间断的连续长镜头，没有剪切、转场、瞬移、空间重置、隐藏切换或不可能的摄影机跳跃。摄影机具有真实惯性、加减速、视差、镜头变化和稳定器限制。0:00开始时已经在陡峭堡垒悬崖旁高速飞行：骑士伏低骑在巨龙背上，抓紧鞍具，头发、披风和皮革带被风吹动。0:00
- 暮色集市追逐至酒馆骑士
制作一段15秒、16:9、写实电影风格的连续镜头，场景是黄昏时分石砌城市中拥挤的中世纪集市。所有成年女性角色都使用所提供的身份参考图来确定外貌，并保持她们的中世纪服装完整。0–3秒：街道低机位拍摄，一名成年女性在木制摊位旁与水果商讨价还价，挑选水果并递出硬币。温暖火把光映在潮湿的鹅卵石上，背景有旗帜、牲畜、薄雾和人群。3–5秒：一辆由马匹拉动的沉重木车突然横穿前景，短暂遮挡画面；镜头自然转移注意力并跟随木车穿过集市。5–7秒：木车在摊位间挤行，擦过一面悬挂的旗幡；旗幡猛烈摆过镜头，移开后露出在街道上四散奔跑的鸡。7–9秒：一个街头男孩追赶逃跑的鸡群，穿过村民，镜头跟随他的运动。9–12秒：男孩
- 雨夜气球与金鱼奇遇
电影感写实奇幻短片，16:9，时长严格20秒。女主为成年女性，脸部与外貌严格参考 supplied identity image；全片保持灰蓝色风衣、白色圆领上衣、深蓝色牛仔裤、黑色短靴、齐肩深色头发和银色圆形耳钉不变。她始终用左手撑透明雨伞：八根银色伞骨、5毫米黑色包边、银色中杆和黑色J形手柄。黄昏雨夜城市路口，建筑布局、斑马线、红色交通灯、粉紫色橱窗光和湿地反光保持一致。镜头始终在道路西侧朝东，屏幕方向连续。背景约20名穿低饱和灰蓝棕服装的行人和6辆汽车，服装不得与女主风衣相同。 0至4秒：镜头高1.6米，35毫米镜头，稳定器平滑跟拍。女主从画面底部中央进入，撑伞沿斑马线向东走4米。前方