OpenZhenZhen AI 提示词画廊 · MiniMax H3 · video

男友视角·说要保护却先躲起来

Boyfriend's View: Promises to Protect, But Hides First

男友视角·说要保护却先躲起来,使用同名原始提示词配对并提供中英文版本

男友视角·说要保护却先躲起来 — AI video creation
男友视角·说要保护却先躲起来

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。 男女坐在L形沙发转角相邻等高座位,共看画外恐怖电影;男友坐姿眼高与她双眼水平。她保持参考脸、长发、黑色细肩带上衣,胸前抱锈红色靠垫。中景始终见她完整面容、肩膀与靠垫;男友右前臂自然搁在两人之间的软坐垫上,从画面下角连接,左手及身体不入画。柔和电视光与暖侧灯。前3秒她从电影转眼看他,自信微笑说「你怕就抱我。」再看电视;男友沉默、手臂不示意。电视传出一次突然敲击,她一惊,举靠垫挡脸;声过后放到腿上,露出整张脸,发现男友正看她。短暂尴尬后承认「刚才那句,不算。」说完才主动握住男友原本搁着的右前臂,轻靠过去;男友不用举手等她。结尾她继续握着前臂,看电影再偷瞄男友,忍不住笑;不出现第二次惊吓。低声室内及非语言电影声、一次敲击、布料声和两句对白;无新增对白、字幕或音乐。 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 facial identity, long dark-brown hair and black thin-strap top. The image supplies identity and visible clothing, not the sofa or opening pose. summary: [reference generation] A 15-second, 16:9 live-action male eye-POV scene. Watching a frightening movie together, <Subject 1> confidently offers to protect the viewer, then hides behind a cushion at a sudden noise. She retracts her boast and chooses to hold his already-resting forearm for comfort. <Picture 1> supplies her identity. retention_analysis: <Subject 1> (appears in [Shot 1]): fully_preserved - retain the defined face, hair and top. The living room, sofa, cushion and television lighting are original scene elements. detailed_description: mpov, first-person perspective pov video, eye level. Natural live-action, soft television light and a warm side lamp, 15 seconds, 16:9. One continuous seated eye-POV shot, without text or captions. [Shot 1] I sit with <Subject 1> at the inside corner of an L-shaped sofa, on adjacent seats of equal height. I turn my head toward her. Our eyes are level: her eyes look straight into mine, not upward. The medium framing includes her entire face, shoulders and the rust-coloured cushion she holds against her chest. The television is off-screen just to the side of our shared viewing direction. My right forearm rests quietly on the soft seat between us, connected to the lower corner of the image. It is within her easy reach. My left hand and the rest of my body are outside the frame. During the opening three seconds, she looks from the movie to me. With easy confidence, <Subject 1> (S1) says in a clear adult female voice, <d>[Chinese] 你怕就抱我。</d> She gives a small assured smile and turns her attention back toward the television. I remain silent; the resting forearm does not gesture. One sudden knocking impact comes from the television. Hearing it, she flinches and raises the cushion in front of her face. When the sound passes, she lowers it onto her lap, revealing her whole face. She discovers that I am watching her. The earlier confidence subsides; after a brief embarrassed pause, <Subject 1> (S1) admits, <d>[Chinese] 刚才那句,不算。</d> Once she finishes, she reaches directly for my resting forearm and closes her hand around it. I do not lift a hand for her to chase or wait for her to accept an offer. The cushion rests on her lap while she chooses the nearby support and leans slightly toward me. The touch remains gentle and physically connected to my arm at the lower image edge. In the final seconds, still holding my forearm, she looks toward the movie again, then steals one small glance back at me, trying and failing to suppress a smile. End on this changed relationship rather than a second scare. Her full face remains unobstructed. My viewpoint stays at her seated eye level; only my same resting right forearm and hand can appear, never my face, torso or left hand. overall_soundscape: Low living-room ambience and faint nonverbal movie sound. One isolated knocking impact occurs before she hides behind the cushion. Soft fabric movement and her two short lines; no further dialogue, loud scare or audience laughter. non_diegetic_music: N/A

主题与风格

查看 API 模型

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

  • 暮色奢华套房漫游

    生成一段20秒、16:9画幅的电影感豪华酒店顶层套房揭幕镜头。采用平滑的平视Steadicam运动,穿过关闭的双扇门持续推进,优雅连贯且不剪切。按层次展现套房:先展示铺有抛光大理石地面的入口大厅、洁白新鲜的兰花和闪耀的水晶吊灯;随后进入奶油色与金色装潢的客厅,家具整齐无瑕,落地窗外是暮色中闪烁的城市天际线,营造香港、纽约或迪拜的感觉,但不出现可见标识。镜头掠过冰桶中的香槟酒瓶,呈现真实的凝结水珠。穿过卧室门口,展示铺着洁白高支数床品并已掀开的特大床,枕头上放着一块巧克力。最后穿过敞开的推拉玻璃门来到阳台,展现下方灯火璀璨的城市。采用温暖精致的酒店灯光、逼真的材质、细腻反射、高端建筑摄影质感、稳

  • 最后的园丁:地球重生

    制作一部20秒、16:9画幅的写实科幻短片:一台约70厘米高、饱经风霜的小型原创园艺机器人,拥有圆润的旧金属机身、两条机械臂和一只圆形琥珀色眼睛,在被遗弃的地球上恢复生命。全片始终保持恰好一台机器人、一个金属浇水壶、一株幼苗和一株持续生长的植物,并保持机器人的比例及花朵位置一致。场景统一为龟裂干旱土地、毫无生机的土壤、尘雾和远处废墟。采用电影级构图、可触感的陈旧金属、真实植物生长、温暖金色时刻摄影和尘土氛围。时间线:0–3秒,低机位跟拍机器人独自行走,脚下干裂土地前方冒出一株微小绿苗;它停在幼苗旁,全程不剪辑。3–6秒,切镜后机器人跪下,用浇水壶把最后一滴水倒在土壤上,周围土地明显变湿。6–9

  • 圣家堂环绕镜头

    生成一段20秒、16:9画幅的电影感建筑视频。晴朗日光下,摄影机围绕圣家堂平滑连续地进行360度环绕运动,始终让教堂居中且清晰可辨;随着视角变化,展现其华丽塔楼、雕塑立面和精细建筑细节。保持地平线稳定、尺度一致、视差自然、石材纹理真实,并确保整个运动过程中的光照连贯。采用宽幅建立镜头,逐步展示建筑的多个侧面,运镜流畅且具有专业电影质感;不要剪辑,前景不要出现人物,不要文字或标志,也不要依赖音频呈现信息。

  • 小径上的骏马由步行转为疾驰

    生成一段20秒、16:9的电影感野生动物风格镜头:一匹马沿着自然土路小径前进。前10秒,马以稳定速度平静行走,清晰呈现完整身体,并展示真实的蹄部落点。约在中点时,马平顺加速,随后在剩余10秒沿同一条小径充满活力地疾驰。摄像机保持一致的侧后方跟拍角度,让马始终成为主体。使用自然日光、稳定曝光、真实的身体结构与运动,蹄部扬起轻微尘土,并呈现细致的户外环境。全程保持空间和时间连续性,不要剪辑、额外动物、人物、文字、标志或音频。

  • 马匹小跑后饮水

    MiniMax H3 视频生成规格。时长:严格 20 秒。画幅:16:9。制作一个写实的电影感场景:一间整洁、自然采光的马厩内,一匹健康的马围绕马厩持续小跑,清晰呈现有节奏的马蹄声视觉节拍和自然身体运动。画面中段,马逐渐减速,在饮水槽旁完全停下,低头开始饮水。保持连贯统一的镜头与轻柔跟拍,马匹解剖结构稳定,光线一致,环境细节自然。结尾让马平静地饮水;不要剪辑、文字、标志、品牌、源视频或音频输入。

  • 狗狗玩球后躺下

    生成一段时长20秒、画幅比例16:9的视频。一只友善的狗在室内铺有地毯的地面上积极玩球,用鼻子推动、用爪子拍球,并短暂追逐球。视频中段,狗突然停下,放低身体,平静地躺在球旁边的地毯上。使用清晰连续的镜头,呈现自然可信的犬类动作、稳定构图、柔和室内光线和真实纹理。按时间顺序展示:先玩球,随后躺下。不添加文字、标志或人物,也不需要源视频或音频输入。