Semi-Realistic 3D Silver Cat Dancing in Coastal Living Room

A 15-second vertical 3:4 silent video of a single semi-realistic 3D silver-shaded kitten performing a continuous small-step dance in a cream-colored seaside living room at dusk. The prompt locks character identity to one reference image, scene and lighting to a second, and the entire motion timeline to a driving video, with a fixed frontal full-body wide shot and no cuts or camera movement.

This clip could not be loaded — it may have been removed from X.
Mr.JI @jjjd77326292 ·
View on X ↗

Prompt

生成15秒、3:4竖版、720p、静音的半写实3D小猫舞蹈视频。固定正面全身中远景,一镜到底;不切镜、不推拉、不摇移、不变焦。

@图片1只负责全片唯一角色的身份:始终是同一只稍瘦银渐层小猫,保持圆脸、灰绿色大眼、粉色鼻子、银白短毛、深灰背部渐层、短腿、圆润猫爪和一条完整粗尾巴。不要使用@图片1的摄影棚背景,也不要保持其静止站姿。

@图片2只负责场景、构图和光线:始终保持同一个奶油色临海客厅、窗户、窗帘、沙发、圆凳、矮柜、台灯、海景、黄昏天空、木地板透视和左侧金色阳光;家具和背景全程稳定。

@视频1是全片唯一的动作时间轴和动作驱动参考。严格跟随@视频1从0.00秒到15.00秒的完整动作顺序、每个动作的开始与结束时刻、左右肢体关系、双脚落点、重心切换、身体下沉回弹、前肢轨迹、头部摆动、眨眼、闭眼、张嘴、吐舌和最后收尾姿势。动作必须按@视频1原有顺序连续发生,不得重新编舞、重排、简化、平均化、循环、遗漏或新增动作。只参考@视频1的动作、表情、运动幅度、固定机位和时间节奏;绝不参考其中角色的青蛙身份、绿色外观、皮肤材质、海滩、海浪、沙地和光线。

重点保持@视频1的小幅贴地顺拐步:脚尖贴地的小交叉、松开、侧点、并回和反向交叉连续衔接,步幅小、重心左右移动,膝踝随动作轻微下沉回弹。前爪只按@视频1的小幅高低位置交替,不得自行变成高抬腿、原地踏步、跑跳、踢腿、双爪长时间举过头顶、敬礼、挥手或普通可爱舞。猫的四肢动作幅度和每一时刻的姿势轮廓都以@视频1为准。

小猫始终位于画面水平中央,完整全身可见,身体占画面高度约52%至58%,宽度不超过40%;保留头顶留白、完整耳朵、双脚、猫爪、尾巴和脚下木地板。角色大小全程恒定,不靠近镜头,不越跳越大。尾巴从根部连续存在,只随重心自然反向轻摆,不能复制或消失。

全程只出现一只猫。保持真实猫科四肢与半写实3D毛发,猫爪不能变成人手或长出手指;每次落脚都与木地板稳定接触,不能滑行、漂浮或穿地。禁止青蛙、其他动物、人物、衣服、项圈、文字、字幕、Logo、UI、水印、多余肢体、重复尾巴、体型变胖、脸部漂移、毛色变化、背景闪烁或家具移动。全片保持静音,不生成任何声音。
? How to use this prompt ▾
  1. Copy the prompt using the green "Copy prompt" button above.
  2. Open your model — launch Seedance 2.0 on its official interface.
  3. Paste & generate — keep the verbatim prompt text for best adherence. Set aspect ratio to 16:9 and clip duration to 15s.

What makes this prompt work

Every insight below is verified against benchmark generation parameters, not asserted. How our prompt engineering benchmarks work →

CAMERA
"zoom" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "static/fixed", "wide shot".
LIGHTING
"golden hour, warm tone, natural light" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD
"playful, cozy" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION
At 15s, this clip is optimized for high temporal coherence and fluid, realistic motion physics.
MODEL
Seedance 2.0 (ByteDance) provides the underlying diffusion and motion architecture. Camera, lighting and duration cues transfer across models — what differs is how literally each model interprets motion.
PROMPT LANGUAGE
The prompt is written in Chinese. This library keeps every prompt in its original language rather than translating it — the exact words are what was conditioned during generation.
Seedance 2.5 BytePlus Cloud Partner

Tell bigger stories with Seedance 2.5

Create AI videos up to 30 seconds long with richer image, video, and audio references. Ideal for complex ideas that need consistency and control.

Explore on BytePlus Official ByteDance Enterprise Cloud