OpenZhenZhen AI 提示词画廊 · MiniMax H3 · video
男友视角·耳机没听见却听见布丁
Boyfriend's View: Didn't Hear Through Headphones, But Heard the Pudding
男友视角·耳机没听见却听见布丁，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。 温暖餐桌两人坐在等高椅上面对面，男友眼线与她平齐，一镜到底。她保持参考面容、长发、黑色细肩带上衣，戴普通包耳耳机；脸、肩和少量桌面始终同框。桌中央只有一杯未开封、无文字盖子的布丁；干净黄色海绵另放在她右手旁，双手开场空闲放桌上。前3秒男友从镜头位置说「该洗碗了。」她看他却故作无辜，轻晃脑袋不回应，像没听见。男友以同样音量说「那布丁我全吃了。」她立刻停止晃头，抢答「给我留一半！」同时自己把同一副耳机降到脖子上，直视男友。男友不碰布丁也不递物品，接着问「碗呢？」她瞄未开的布丁，再看右手边原有海绵，在结尾三分之一时自己右手拿起海绵至脸下胸前，带无奈笑意说「成交。」结尾耳机仍在颈上、布丁仍未打开、她举海绵对视；还不吃也不洗。男友手脸身体不入画，镜头不俯拍布丁。安静餐厅环境、清晰交替对白、微弱耳机漏音和真实耳机海绵摩擦；无旁白、字幕、笑声或配乐。 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 reference is for her identity and visible wardrobe only. Headphones, furniture and food props belong to this original scene. summary: [reference generation] A 15-second, 16:9 live-action male eye-POV comedy. <Subject 1> appears unable to hear a request to wash dishes while wearing headphones, but immediately hears that her boyfriend will eat all the pudding. Caught out, she chooses to take the washing-up sponge in exchange for her share. Her active decision, not an explanation, ends the exchange. <Picture 1> supplies her identity. retention_analysis: <Subject 1> (appears in [Shot 1]): fully_preserved - retain her defined face, hair and top. The dining nook, headphones, pudding and sponge are original. detailed_description: mpov, first-person perspective pov video, eye level. Warm natural live-action, 15 seconds, 16:9, one continuous seated eye-POV conversation. No captions, floating text or reverse shots. [Shot 1] I sit directly opposite <Subject 1> at a narrow dining table, both seated on equal-height chairs. Our eyes meet horizontally. Her full face, shoulders and a small strip of tabletop remain in the same composition. She wears ordinary over-ear headphones; her hands are free on the table. A single unopened pudding cup stands near the centre, with a clean yellow sponge lying separately beside her right hand. The pudding has a plain unmarked lid. Both objects are already present and remain easily reachable. There are no visible screens, complicated stacks of dishes or other people. In the opening three seconds, I (S1), an adult male speaking from the camera position, say, <d>[Chinese] 该洗碗了。</d> She looks at me, maintains a deliberately innocent face and continues a small relaxed head sway, choosing not to answer. This is a short beat of apparent non-hearing, not a long silent introduction. Keep her eyes visible; the headphones do not cover her face. I (S1) then say in the same ordinary speaking voice, <d>[Chinese] 那布丁我全吃了。</d> Only after the threat to the pudding does her head sway stop. <Subject 1> (S2), in a clear adult female voice, responds promptly, <d>[Chinese] 给我留一半！</d> As she responds, she uses her own hands to lower the headphones from her ears to rest around her neck. The same headphones remain there, freeing her ears. She looks directly at me with an alert expression that makes the change from her earlier indifference easy to read. I do not reach for the pudding or pass her anything. After she has lowered the headphones and placed her hands back near the tabletop, I (S1) ask, <d>[Chinese] 碗呢？</d> She briefly glances at the untouched pudding, then at the yellow sponge already beside her right hand. During the final third of the shot, she makes her own choice: her right hand takes the sponge from the table and lifts it to lower-chest height, within the frame below her face. <Subject 1> (S2) answers with amused resignation, <d>[Chinese] 成交。</d> For the remaining moment, she holds the sponge and meets my gaze; the unopened pudding remains between us and the headphones remain around her neck. The concrete result is her taking responsibility in return for a share, not a repeated plea or an extra handover. Neither person begins eating or washing before the clip ends. My face, body and hands remain outside the frame; my spoken choice is my participation. The camera stays at her eye line rather than drifting into an overhead view of the cup. overall_soundscape: Quiet dining-room ambience and clearly alternating off-screen male and on-screen female Mandarin dialogue. A faint muffled beat may leak from her headphones without masking words. Subtle headphone and sponge handling sounds accompany their actual movements. No narration or added 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。