OpenZhenZhen AI 提示词画廊 · MiniMax H3 · video
实体灯车与双人投影编舞
Physical Light Vehicle and Two-Person Projection Choreography
实体灯车与双人投影编舞,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
0.00秒完全参考 <Picture 1> [Shot 1]首帧。真人灯影编舞,实景排练棚。A为浅蓝舞蹈长衣与黑裤棕发女子;B为右侧黑衣男子;C为独立的米色衣短发女子,在左前景操控轮车上的唯一实体灯。A/B位于左前灯与后白墙之间,墙上可见轮廓对应真实举臂姿势。C在灯旁或后方、避开主要照墙光锥。低木凳、地标、白墙固定;柔日光只补光,不是第二硬影来源。判断影形和位置可读性,不靠衣色、不强制准确影子总数。 [Shot 1] 0–6秒:A转身跨低凳并清晰落地,B侧步绕其开放端,C固定灯,墙影跟随身体。A抬臂形成真实开口,B蹲穿,A转身配合,任何可见影形对应真实姿势。A/B在分开的地标上短暂保持不同身体姿势,C侧步将灯车横推一小段,此时投影变化由灯移动驱动。 [Shot 2] 6.000秒在完整事件边界切同动作轴一侧连续匹配中广景,无时间跳跃。6–12秒:C停灯车,A小跳并双脚清晰落地,B在外侧绕她,影姿对应起跳落地。B跨凳落地,A从外侧蹲绕,可读影轮廓仍对应当下运动。A/B短暂静持当前不同姿势,C把灯推回原地;依据当前身体位置判断投影,不强制回到开场影形。 [Shot 3] 12.000秒切更广连续空间关系。A/B沿独立路径交叉、朝不同方向转身并分开停住,C固定灯;几何可见处保留对应可读墙影。14–15秒保持最终不同姿势和持有状态。面孔、服装、布景一致,关键接触/交接/落地连续可见,不靠切镜隐藏。实时物理编舞,无慢动作、魔法闪光、能量束、字幕、额外演员或复制道具。 声音:舞鞋步、软落地、衣料运动、仅C真实推动时的短脚轮声和棚内底噪。无对白、歌唱或人工激光声。配乐:无。
English prompt
For the target video, at 0.00 seconds into the target video, <Picture 1> (from [Shot 1]) is fully referenced. integrated_multimodal_description: [Shot 1] Live-action light-and-shadow choreography in the practical rehearsal studio from <Picture 1>. A is the brown-haired woman in a pale-blue dance tunic and black trousers; B is the black-clothed man to her right. C is the distinct cream-clothed short-haired woman operating the ONE real lamp on its wheeled cart at far LEFT foreground. A and B are between that left-front lamp and the white rear wall; their visible wall silhouettes correspond to their real raised-arm poses. C remains beside or behind the lamp outside its main wall cone. Keep the low wooden bench, fixed floor marks and white wall registered. Ambient daylight is soft fill, not a second hard shadow source. Judge readable shadow contours and position, never clothing color or a forced exact total shadow count. From 0 to 6 seconds: A turns and steps across the low bench with a visible landing, while B sidesteps around its open end; C holds the lamp still and their readable wall silhouettes follow the real bodies. A lifts one arm to form a real open gap; B crouches through that gap as A turns in support, with any visible silhouettes corresponding to those actual poses. A and B briefly hold two different body poses on separate marks while C sidesteps and pushes the real lamp cart a short lateral distance; the visible projection changes now follow that lamp movement. [Shot 2] At 00:06.000, cut at the completed event boundary to a medium-wide continuity-matched view on the same side of the action axis, without a time jump. From 6 to 12 seconds: C stops the cart; A makes one small jump and visibly lands on both feet as B turns around her outside, with the visible shadow pose following takeoff and landing. B steps across the low bench and lands while A crouches around its outside, and their legible wall contours continue to follow the current real motion. A and B briefly hold their current different poses still while C pushes the lamp back to its original floor position; judge projections for these current body positions, not a forced return to their opening shapes. [Shot 3] At 00:12.000, cut to a wider continuity-matched view of the final spatial relationship. A and B cross on separate paths, turn in different directions and stop apart while C holds the lamp still; retain corresponding readable wall silhouettes wherever geometrically visible. From 14 to 15 seconds, hold the distinct final poses and ownership states. Keep faces, clothing and fixed scenery consistent. Show every critical contact, transfer and landing continuously rather than hiding it across a cut. Real-time physical choreography, no slow-motion filler, magical flashes, energy beams, captions, extra actors or duplicated props. overall_soundscape: Dance-shoe steps, soft landings, cloth movement, brief caster-wheel rolls only when C pushes the actual cart, and low studio ambience. No dialogue, singing or artificial laser sounds. 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
- 南瓜灯下的奇幻重逢
制作一段20秒、16:9画幅的电影感超写实万圣节爱情短片,氛围梦幻而神秘。每个场景中,成年女性的面容与外观都以所提供的身份参考图为准,并保持身份一致、服装完整不变。场景1(0–3秒):在一间深森林绿墙面、摆有古董家具、暖色台灯和秋日装饰的复古房间里,长发女子静静坐着,木桌上放着一盏发光的南瓜灯。她慢慢伸手靠近南瓜。场景2(3–6秒):特写她的手和一幅精致相框里的成年男子肖像;男子穿着青绿色毛衣。肖像仿佛活了过来:他睁开眼睛,温柔地微笑,她则带着羞涩而温柔的神情凝望着他。场景3(6–9秒):女子微笑起来;肖像泛起琥珀色光芒,化作一道边缘闪烁暖光的门。她起身,迈步穿过门。场景4(9–13秒):在温
- 石屋里的小龙与秘密馈赠
制作一段20秒的电影感黑暗奇幻场景,背景为质朴的中世纪石屋,16:9宽屏。成年女性角色必须与提供的身份参考图一致;服装保持统一:奶油色蕾丝边连衣裙和深色羊毛斗篷。一只长着半透明粉色皮肤、精致褶鳍、明亮深色眼睛和小爪子的幼龙蹲在粗糙的木桌上,好奇地嗅闻旁边一枚闪亮的金币。冷色日光从小石窗照入,与炉火摇曳的暖光形成对比。女人俯身靠近,轻轻递上一小块食物。幼龙兴奋地张开嘴,露出细小的牙齿,振动褶鳍并伸向她的手。结尾以亲密近景呈现幼龙接过食物,女人温柔地微笑。生物纹理与解剖结构写实,人物表情自然,动作可信,电影感镜头运动,浅景深,低饱和大地色调,轻微胶片颗粒。避免卡通风格。全程保持角色与场景视觉统一。
- 白石采石场的孤身之战
制作一段15秒、16:9的写实真人武打场景:阴天日光下,一座广阔、废弃的白石采石场中,一名成年亚洲女性与一群身穿深红色战斗服的成年男性武士交锋。女性留着高马尾黑色长发,穿合身的黑色武术服。以提供的身份参考图作为女性角色外貌依据;全程保持身份一致,服装完整不变。0–3秒:低机位动态广角展现武士们包围她,并踏过龟裂石地冲来,尘土扬起。3–6秒:转为中景,她格挡一名袭击者的拳头,转身反击;动作精准、扎实,马尾自然甩动。6–9秒:她施展旋踢,将数名袭击者踢得后退,其中一人短暂腾空;在撞击瞬间以克制的慢动作突出冲击感,并呈现真实动作、尘土与少量碎石。9–12秒:快速跟拍她闪避攻击、扫倒一名对手并旋身再次
- 红光机房对决
创作一段15秒、16:9的写实真人电影风格动作场景,地点为高科技服务器机房。所有女性角色的外观均参考提供的身份参考图;参考图仅用于身份与外貌,不作为服装参考。两位角色均为成年人。服装全程保持完整:一位穿橄榄绿色短袖上衣、棕色工装短裤、作战靴和战术腰带;另一位穿黑色战术上衣、黑裤和战术背带。红色应急灯映照玻璃隔断、电脑显示器与荧光顶灯。0–3秒:绿衣女子在桌旁接近黑衣女子。3–8秒:两人近身交手,进行拳击、格挡与扭斗,手持跟拍动态明显但动作清晰。8–11秒:绿衣女子踢出高踢,将对手逼向显示器墙;出现短暂火花和少量碎屑,不表现血腥伤害。11–13秒:她将对手带倒在地并稳妥压制。13–15秒:特写绿
- 暖光舞室中的优雅独舞
20秒、16:9写实手机风格舞蹈视频,仅有一名成年女性。仅使用所提供的身份参考图来保持她可辨认的面部身份和自然五官;全程保持脸部与身份一致,不要复制参考图的服装。她全程穿同一套灰玫瑰色短款罗纹针织毛衣、高腰飘逸不对称黑色中长裙、简洁黑色踝靴、小珍珠耳饰和细手表,头发为带自然碎发的宽松半扎发。场景是宽敞极简的舞蹈教室:暖米色墙面、抛光木地板、高窗、柔和午后阳光、整面墙镜和简易长椅。采用带轻微稳定的自然手持手机运动,横向16:9构图,真实皮肤与人体比例,裙摆和头发运动自然。0:00–0:03:广角,她站在中央,对镜头微笑,以轻柔侧步和肩部动作开始。0:03–0:06:中景,交替挥臂、小幅后撤步组合
- 月光吸血鬼轮滑
制作一段20秒、9:16竖屏的电影感奇幻视频:一位身着经典德古拉风格服装、外形英俊的男性吸血鬼,独自在复古轮滑场内滑轮滑。明亮的满月从大窗户照入,在抛光地板上投下冷银色光束与长长的阴影。展现他的全身动作,包括优雅而受控的滑行、偶尔的转身,以及自信而神秘的表情。采用高度细致的面部特征、精巧的服装纹理、真实的人体结构、戏剧性的电影灯光、富有氛围感的景深、精致的超写实奇幻艺术风格和考究的复古插画质感,但不要模仿任何特定在世艺术家。全程保持角色与场景的视觉一致性,使用平滑的跟拍镜头和细节丰富的环境。