Seedance Pet Animal

Pets and animals as the lead · 宠物动物当主角

The animal is the lead and a phone is the only camera. Lock the count to exactly one, keep the animal behaving like an animal, and let the payoff come from it closing in on the lens.

This Skill carries one prompt structure distilled from 15 human-verified Seedance cases on goodcase.ai. It is a sibling of seedance-prompt-library (all templates in one Skill); install this one when you only want this kind of clip. Do not invent structure from general video-generation knowledge: follow the structure below and ground the draft in one anchor case from references/cases.md.

Use when

• Selfie and vlog clips where a cat, dog or wild animal hijacks the frame, plus photoreal wildlife comedy built on one real animal behaviour.
• 中文：猫狗或野生动物抢镜的自拍、vlog 片段，以及靠一个真实动物行为撑起来的写实喜剧。

Workflow

1. Collect inputs. Ask only for what is missing: subject or product, setting, duration, aspect ratio, whether reference images / audio exist, and which language the final prompt should be in.
2. Pick one anchor case. Read references/cases.md, choose the case closest to the request, and name it in the reply. One anchor, never an average of several.
3. Fill the structure block by block. Every block below must be present in the final prompt; an empty block is where prompts go vague.
   1. Reference and subject block: lock the person with a reference image if anyone is on camera, and state that there is exactly one animal, the same one throughout
   2. Format block: duration, vertical 9:16, handheld front-camera selfie, indoor daylight, no grading and no beauty filter
   3. Camera block: arm drift, imperfect framing, autofocus hunting, no cuts, no zoom, no third-person operator
   4. Body split by seconds, each block pushing the animal one step further: notices, reaches, steals, climbs, attacks the lens
   5. The human reaction and a half-finished line written into the same beat
   6. Audio block: a list of on-set sounds, no music, no subtitles, no watermark
   7. Strict constraints to close: one person, one animal, no second animal, correct mirror physics, no camera operator
4. Apply the guidance and check the pitfalls (next two sections) before returning anything.
5. Return the finished prompt as one copy-pasteable block, the anchor case link, and a three-line checklist of what to verify in the generated video.

Guidance (from the cases)

• Write the count as a hard number and make that one animal physically continuous. The dog mirror case says Use exactly ONE small playful dog throughout the entire video plus No duplicate animal; the kitten vlog case itemises consistent fur pattern, eye color, size, whiskers, ears, paws.
• Give the animal its own behaviour paragraph. The macaque case opens an ANIMAL BEHAVIOR block with No talking, no human clothing, no human-like walking, and rests the whole joke on the monkey copying the hiker's head tilt.
• Buy realism with a list of camera defects. The cat day-in-the-life vlog asks for Natural handheld shake, Occasional autofocus hunting and Natural front-camera lens distortion, then bans No cinematic camera movements.
• Escalate beat by beat and land on the lens. The dog case closes with Its nose fills a large part of the frame, the image losing focus and regaining it; the rainy-day kitten ends with a paw at the corner of the lens and the clip cutting off mid-laugh.
• Keep the audio diegetic. The cat vlog's closing audio block lists only meows, purring, chirping and footsteps and states No background music; the dog case says Natural room ambience only.