OpenZhenZhen AI 提示词画廊 · MiniMax H3 · video

托盘带杯与杯垫同步半转身

Tray with Cup and Coaster in Synchronized Half-Turn

8秒连续动作示例：托盘带杯与杯垫同步半转身。

托盘带杯与杯垫同步半转身 — AI video creation — 托盘带杯与杯垫同步半转身

提示词 / Prompt

中文提示词

8秒连续镜头，动漫电影风格。一名栗棕短发、穿蓝绿色围裙的成年咖啡师，只有一只带白月牙的钴蓝杯、一个托盘、一个木杯垫和一个低隔板。参考图1定义唯一场景的构图和角色身份；参考图2仅为同一地点的环境参考；参考图3是图1中同一件主要道具的设计近景，不是第二件道具。将三图组合成一个连贯场景，不能做成三联画。只使用动作中明确规定的物体数量。她端起载有唯一正立杯子与唯一杯垫的托盘，身体与保持水平的托盘一起旋转半圈，再将整个托盘放回台面。杯子和杯垫全程随托盘移动，始终支撑在托盘上表面。摄影机固定为中广角四分之三视角，使相关双手、道具、接触面与最终状态始终可见。以自然速度连续完整展示动作，不剪切、不转场、不插入其他画面、不增加表演者或魔法效果。遵守实体边界与正常物理支撑。尽快开始指定动作，结束状态短暂停留。无字幕、UI、水印或画面标签。适当而安静的室内环境声和自然接触声，无对白、无背景音乐。

English prompt

summary: [reference generation] One continuous 8-second shot in anime film style. One adult auburn-bob barista in a teal apron; one cobalt mug with one white crescent, one tray, one wooden coaster, one low divider. reference_roles: Picture 1 defines the SINGLE scene composition and character identity. Picture 2 is environment-only reference for that SAME location. Picture 3 is a close-up design reference for the SAME hero object visible in Picture 1, NOT a second object. Combine these references into one coherent scene, not three panels. Use only the object counts explicitly stated in the action. detailed_description: She lifts the tray carrying the single upright mug and the one coaster, rotates her body and the level tray a half-turn together, then sets the whole tray back on the counter. The mug and coaster travel with the tray and remain supported on its top throughout. Camera: locked medium-wide three-quarter view keeping relevant hands, props, contact surfaces and end state visible. Show the entire action continuously at natural speed; no cuts, transitions, cutaways, extra performers or magical effects. Respect solid object boundaries and normal physical support. Start the requested action promptly and hold the final state briefly. No subtitles, UI, watermarks or on-screen labels. overall_soundscape: Quiet appropriate room ambience and natural contact sounds; no speech. non_diegetic_music: None.

主题与风格

查看 API 模型

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

舞蹈
Keyframe Alignment（关键帧对齐） <Picture 1> 对应目标视频 0.00 秒，作为真实首帧。完整保留成年女性的银白色长发、荧光绿色印花抹胸、身体比例、皮肤质感、室内背景、窗边自然光和原始近景构图。人物始终正对镜头，不改变服装，不重新构建人物面部。 integrated_multimodal_description [Shot 1] 0.00–5.00s｜固定近景，一镜到底写实真人舞蹈视频，固定正面近景镜头，画面聚焦女性上半身，保持原图的拍摄距离、角度与自然光照。 0.00–0.50s：动作启动女性从首帧静止姿态开始，肩膀自然放松，腰部基本稳定，上半身轻微蓄力
克劳德-圣光版
工作流+整合包+参考图工程文件：https://my.feishu.cn/wiki/SkTuwaMOUipTjQk6K6icotXwnze B站演示：https://www.bilibili.com/video/BV1YHxS6aE68
claude熊猫拘束
工作流+整合包+参考图工程文件：https://my.feishu.cn/wiki/SkTuwaMOUipTjQk6K6icotXwnze B站演示：https://www.bilibili.com/video/BV1YHxS6aE68
豆包圣光版
工作流+整合包+参考图工程文件：https://my.feishu.cn/wiki/SkTuwaMOUipTjQk6K6icotXwnze B站演示：https://www.bilibili.com/video/BV1YHxS6aE68
暗黑大肥鱼
工作流+整合包+参考图工程文件：https://my.feishu.cn/wiki/SkTuwaMOUipTjQk6K6icotXwnze B站演示：https://www.bilibili.com/video/BV1YHxS6aE68
姬貔啼-暗黑龙卷
工作流+整合包+参考图工程文件：https://my.feishu.cn/wiki/SkTuwaMOUipTjQk6K6icotXwnze B站演示：https://www.bilibili.com/video/BV1YHxS6aE68