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
- 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。