geminiprompts.world

animal pet animal ugc Seedance 2.0 prompt

Realistic Cat Talks at Dinner Table in Vertical Short

A 10-second vertical live-action style short featuring a single realistic cat at a bright home dining table, lip-synced to Chinese dialogue with a childlike cat voice and an adult woman's off-screen voice. The cat uses its front paws to hold chopsticks, sulks, jumps down, then tearfully runs back toward the camera across four fixed-camera shots.

This clip could not be loaded — it may have been removed from X.

探路AI @TanLuAI · Original post: Aug 13, 2026

Prompt

生成视频：风格】竖屏真人实拍萌宠搞笑短视频，真实家居餐厅质感，柔和自然日光，手机固定机位、轻微手持感；拟人化表演但猫的身体比例、走路、毛发、光影和口型都是真实写实质感。无字幕、无文字、无水印，不穿模。
【时长】10 秒，9:16 竖屏。
【场景】明亮现代家居餐厅。浅木色餐桌位于画面下半部，桌上有白瓷饭碗、筷子、盛牛肉和配菜的白盘；背景放一张浅色儿童餐椅。镜头从餐桌对面平视拍摄，前半段拍到猫坐在餐椅，后半段拍猫从桌侧地面走近镜头。
【角色】一只真实猫；全片只出现这一只猫。它可拟人化地用前爪扶筷子、做出委屈和撒娇反应，但仍是四足真实猫，不站立成人形，不出现人手。猫的嘴巴必须与中文原声严格同步。猫的声音模仿小孩可爱的声音，主人是成年女性的声音
[00:00-00:02] 镜头 1：餐椅上的试探 固定中近景。猫坐在儿童餐椅内，餐桌前摆着饭碗和筷子；一只前爪轻扶筷子，抬眼认真看向镜头，语气带一点期待和试探，嘴巴自然同步。 台词口型： [00:00.15-00:01.03] “你爱我吗？” [00:01.07-00:01.83] 画外音女生的声音：“我不爱了。”
[00:02-00:04.2] 镜头 2：生气离席 镜头保持原机位。猫皱眉、耳朵略向后、眼神不满，前爪放开筷子，边回怼边从餐椅跳到地面，从餐桌侧边走开；跳下与落地动作必须符合真实猫的身体运动。 台词口型： [00:02.07-00:04.19] 猫气呼呼、语速稍快：“那你不爱我，我也不爱你了。”
[00:04.2-00:06.5] 镜头 3：撒娇哭着挽回 短暂停顿。猫走到餐桌侧前方后忽然回头望向镜头，刚才的生气瞬间转成委屈：眼眶湿润、眉眼耷拉、嘴角向下，鼻头轻轻抽动。它不是夸张嚎哭，而是可爱地带着哭腔、着急求和；一只前爪轻抬，像想挽留镜头外的人。 台词口型： [00:04.95-00:06.47] 画外音，急切地说：“我爱我爱，快回来吧。”
[00:06.5-00:10] 镜头 4：哭着走近，傲娇答应 猫从餐桌侧边继续朝镜头小跑靠近，眼睛还带泪光，边走边有轻微委屈抽泣；镜头内猫脸逐渐变大、最后近距离占满画面。 台词口型： [00:08.03-00:08.27] 猫带鼻音、轻轻回应：“嗯。”（哭腔） [00:08.27-00:10.00] 不再说话，猫委屈巴巴地直视镜头，保留原声尾部的安静停顿，自然收尾。，9:16，10s

? How to use this prompt ▾

Copy the prompt using the green "Copy prompt" button above.
Open your model — launch Seedance 2.0 on its official interface.
Paste & generate — keep the verbatim prompt text for best adherence. Set aspect ratio to 9:16 and clip duration to 10s.

Spec sheet

Duration	10s
Camera	handheld · static/fixed · medium shot · close-up
Lighting	natural light · soft light
Mood	playful
Aspect ratio	9:16
Difficulty	intermediate
Model	Seedance 2.0
Prompt language	Chinese
Includes	Not specified

Categories

animal pet animal ugc

Filter by technique

handheld static/fixed medium shot close-up natural light soft light playful

Filter thousands of prompts by camera movement, lighting, duration, aspect ratio and category.

Browse complete prompt library →

What makes this prompt work

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

CAMERA: "handheld" is a core cinematic camera technique for establishing spatial immersion and subject framing. Also present: "static/fixed", "medium shot", "close-up".
LIGHTING: "natural light, soft light" establishes luminance depth, volumetric shadow falloff, and tonal contrast across the generation.
MOOD: "playful" — Mood and aesthetic tone are explicitly directed to maintain emotional consistency throughout the scene.
DURATION: At 10s, 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.