OpenZhenZhen AI 提示词画廊 · MiniMax H3 · video
男友视角·定格鞠躬与迟来的掌声
Boyfriend's View: A Frozen Bow and Belated Applause
男友视角·定格鞠躬与迟来的掌声，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。 小排练室，男友坐前排低凳略仰视一至两米外女方；她保持参考脸、白皙皮肤、深色眼睛和长发，穿宽松酒红衬衫、深色长裤与鞋。整张脸、双臂与上身动作一直可见；男友膝盖不入画。她先站直看他，说「你喊停，我就定格。」随后只迈一小步，摆夸张谢幕双臂姿势并从腰前俯身。经过一臂高一臂低、姿势尴尬的半鞠躬时，男友从镜头位置喊「停！」她就在原位置定住，没有换姿。男友笑着把双前臂举到画面下方准备鼓掌，双掌相距约一掌宽，尚未碰触。她保持半弯，看见手后反击说「换你，停！」男友双掌在接触前立刻停下，所以之前没有掌声。她随即顺畅完成原本被打断的同一个鞠躬，变成得体谢幕，不转身不走远；脸与姿势清楚后说「现在拍。」这时男友两掌才合上一次，发出唯一一声拍手，再分开。她在自己选择的姿势中接受鼓掌。只有男友手及前臂可从下缘进入。排练室空气声、四句对白、少量脚步衣料声、末尾仅一声掌声；无之前掌声、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 visible facial identity, fair skin, dark eyes and long center-parted dark-brown hair. Her burgundy loose shirt, dark full-length trousers, shoes and small rehearsal space are original episode design; the identity picture is not the story's opening frame. summary: [reference generation] A 15-second, 16:9 live-action boyfriend eye-POV rehearsal game. <Subject 1> agrees to freeze when he calls stop. He catches her halfway through a theatrical bow and raises his hands to clap at the awkward pose. Before his palms meet, she reverses the command and freezes his impending applause. She completes a graceful bow on her terms, releases him and receives exactly one clap. retention_analysis: <Subject 1> (appears in [Shot 1]): fully_preserved - her facial identity and long hair from <Picture 1> remain recognizable; this modest outfit and rehearsal setting are original. detailed_description: mpov, first-person perspective pov video, low angle. One continuous 15-second 16:9 live-action shot from my eyes while I remain seated on a low stool in the front of a small rehearsal room. <Subject 1> stands one to two meters ahead on clear floor, above my seated eye level, wearing a loose burgundy shirt, dark full-length trousers and shoes. I look slightly upward at her; her entire face, arms and the upper part of her posture stay readable. The room and floor do not take over the view, and my knees do not appear. [Shot 1] She looks to my eyes and proposes the rule, <Subject 1> (S1), <d>[Chinese] 你喊停，我就定格。</d> Starting upright, she takes only one small stage step and sweeps her arms into an exaggerated curtain-call gesture. In that same movement she begins to bow forward from her waist. As she passes through a naturally awkward half-bent position with one arm high and the other low, I deliberately call from behind my own eye position, me (S2), <d>[Chinese] 停！</d> She halts exactly where the bow has reached, still half-bent; no new pose appears after my call. Amused, I lift both forearms from my near sides into the lower part of the picture to applaud. My two palms face each other but remain about a palm's width apart, below her visible face. She notices those still-separate hands while holding the bent pose and counters, <Subject 1> (S1), <d>[Chinese] 换你，停！</d> My palms stop before contact; there has been no clap. With the instruction now passed to me, she smoothly finishes the same interrupted bow into a poised curtain-call finish, without another turn or walk. Once her face and final pose are clear, she says, <Subject 1> (S1), <d>[Chinese] 现在拍。</d> Only then do my two waiting palms close together once for a single audible clap and separate. She receives that one clap in her chosen finished pose. Only my two hands and forearms enter at the lower edge; my face, legs and body are not shown, and the viewpoint never becomes an external camera. overall_soundscape: Quiet rehearsal-room air, her three short Mandarin lines and my one near-camera stop command, a little clothing and foot movement during the bow, then exactly one handclap after she releases me. No earlier applause, narration, captions or music. 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。