OpenZhenZhen AI 提示词画廊 · MiniMax H3 · video
男友视角·露馅的红丝巾魔术
Boyfriend's View: The Red Silk Scarf Magic Revealed
男友视角·露馅的红丝巾魔术，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。 小游乐场舞台旁，男女站立眼高一致，暖色灯光远处虚化，没有其他观众。女方保持参考脸与长发，穿海军蓝开衫。她右拳在胸上部、完整面容下方，握着同一条红丝巾，鲜红短尾从小指下明显露出；左手放松且空。男友视线与她及拳同框，不俯看桌面。开头她自信宣布「消失了。」却尚未发现露出的尾巴。男友稍看红尾再看她的眼，认真配合说「真没了。」她循他的视线看向自己拳头，发现失误后短暂停顿，不能在发现前会心地笑。中段她不重做魔术，而是打开右拳，用左手拉出同一条丝巾另一端，双手展开；丝巾从未消失或复制。她看着男友，把失误变谢幕，双手在腰部握两端浅浅鞠躬，说「谢谢唯一的观众。」脸仍可见。男友仅在她道谢后于画外拍手两次，她抬眼淡笑，丝巾一直在双手之间至结尾。游乐场轻微远声、两人对白、布料声及恰好两下近处掌声；没有他人掌声、旁白、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 and long dark-brown hair. Her casual navy cardigan, red silk scarf and the small fairground performance corner are original story elements, not reference-image contents. summary: [reference generation] A 15-second, 16:9 live-action male eye-POV scene. <Subject 1> announces a vanishing scarf trick despite a plainly visible red tail. Her boyfriend knowingly plays along. When she notices the exposed tail, she chooses to stop hiding it, opens the scarf and bows to her only audience member. His applause completes their small, imperfect performance. <Picture 1> supplies her identity. retention_analysis: <Subject 1> (appears in [Shot 1]): fully_preserved - preserve her defined face and hair while using the original outfit and fairground location. detailed_description: mpov, first-person perspective pov video, eye level. Natural live-action, 15 seconds, 16:9, a continuous intimate eye-POV shot. No subtitles, written instructions or external reverse angle. [Shot 1] I stand facing <Subject 1> at matching eye height beside a small fairground stage. The fair's warm lights sit softly in the distance; no crowd is watching this private demonstration. She wears a navy cardigan and holds her closed right fist at upper-chest height, next to but below her fully visible face. A short bright-red tail of one small silk scarf protrudes conspicuously below her little finger. The rest is bunched inside that same fist. Her left hand is relaxed and empty. Her full head and hands are readable together; I do not need to look down at a table. At the opening, <Subject 1> (S1), a clear adult female voice, declares with modest magician-like pride, <d>[Chinese] 消失了。</d> She keeps presenting the fist, initially unaware of its obvious red tail. My attention briefly settles on that tail, then returns to her eyes without changing height. I (S2), an adult male speaking from the camera position, answer with straight-faced support, <d>[Chinese] 真没了。</d> Her eyes follow the direction of my brief glance down to her own fist. She sees the exposed fabric and pauses. Her confident presentation falters for a moment; do not make her smile knowingly at the mistake before she has noticed it. In the middle of the shot, she makes a visible new choice rather than attempting the trick again. She opens the right fist and uses her left hand to draw out the other end of the same scarf, spreading it openly between her two hands. The red cloth has never vanished or multiplied. After opening it, she looks at me, accepts the failed concealment and turns it into a deliberate curtain call. Holding the ends at waist height, she gives a small bow and says as <Subject 1> (S1), <d>[Chinese] 谢谢唯一的观众。</d> Keep the bow shallow enough that her face remains visible; my standing viewpoint does not descend with her. Only after her thanks, I clap twice below my field of view. The two audible claps are my response to her choice, not applause from another audience. She keeps the small bow, lifts her eyes to meet mine and allows a restrained smile. The openly displayed red scarf hangs visibly between her own hands until the end. We complete the performance without another trick or another reveal. My face and body never appear. My hands stay below the picture during the claps; the attention remains on her receiving them at the same standing eye position. overall_soundscape: Soft distant fairground ambience, near-camera adult male speech and on-screen adult female speech in Mandarin. A light cloth rustle accompanies her unfolding. Two close claps come from the observer only after her thanks. No other applause, narrator or laughter 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
- 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。
- 小鸟落地飞行
生成一个时长20秒、画幅比例16:9的视频。一只小鸟平静地停在自然环境中的树枝上，先保持片刻静止，然后突然从树枝起飞，以流畅且清晰可见的动作向下飞行，并降落在树下的地面上。始终让小鸟及其运动保持在画面中，翅膀动作真实，光线自然，构图稳定，采用连续镜头。结尾时小鸟站在地面上。不要使用或要求任何源视频或音频作为输入。