Classical Chinese Ribbon Dance · Open Skill 공개 스킬

Classical Chinese Ribbon Dance

Classical Chinese Ribbon Dance은 Digen의 공개 Open Skill입니다. 열어 보면 이 워크플로가 무엇을 만드는지 알 수 있습니다.

@BrookeHollis

Film

0 1 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284958/2026-10-16/nxw5pe4k.webp

# Classical Chinese Ribbon Dance

Silk in the mist. Your photo becomes a graceful classical Chinese dance: flowing hanfu sleeves and a long silk ribbon arc through blossom-lit mountain air.

## When to use

- The user wants a soft classical Chinese ribbon-dance video from their photo (hanfu dance clip, silk-ribbon choreography)
- Another take with a different length or orientation

Not for: Still images only.

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult with the face clearly visible. Ask for another photo if the face is tiny, blurred, heavily covered or in profile |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| End pose | No | `graceful ribbon arc` | graceful ribbon arc (default), or user-described closing pose |
| Prompt notes | No | `optional mood` | optional mood or costume color |
| Duration | No | `6` s | 6 or 10 |
| Orientation | No | `9:16` portrait | Other ratios on request |

- If the person may be under 18, stop and decline politely. Real-person photos must be of adults the user has the right to use.
- Video does not allow NSFW content: keep wardrobe fully covering and refuse sexual requests. Suggestive fashion looks stay as still images.

## Steps

1. Read `references/video-motion.md`.
2. **Identity read**: `recognize_image(image_url=<photo>, prompt='Describe this adult for identity preservation: face shape, eye shape and color, brows, nose, lips, skin tone, apparent age range, hair color and length, distinctive marks, glasses. One compact line.')`.
3. **Keyframe**: `generate_image(prompt=<KEYFRAME>, input_urls=[photo], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Classical Chinese Ribbon Dance keyframe', entity_type='work_in_progress')`. If the face drifts, regenerate once.
4. **Video**: `generate_video(prompt=<MOTION>, input_urls=[keyframe], model='i2v', orientation='portrait', aspect_ratio='9:16', duration=<d>, name='Classical Chinese Ribbon Dance', entity_type='final_videos')`. Pass only the keyframe, never the original upload.
5. Reply in one or two sentences, e.g. "All set. Your classical chinese ribbon dance is on the canvas. Next I can do a 10-second cut." Results appear on the canvas; never paste URLs.

## Prompt templates

**KEYFRAME**

```text
The same adult from the reference: <identity line>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Opening frame of this scene: the same adult person performs a soft graceful classical Chinese ribbon dance in flowing pastel hanfu, long silk ribbon drawing wide arcs, cherry blossoms and misty golden mountains behind, serene expression, elegant slow turns, cinematic wuxia-dance energy. Posed for motion, clear subject, cinematic light. Nothing from the original photo's background remains.
```

**MOTION** (motion only; the frame already shows the look)

```text
Starting from this exact frame: <one clear motion arc for this concept: the same adult person performs a soft graceful classical Chinese ribbon dance in flowing pastel hanfu, long silk ribbon drawing wide arcs, cherry blossoms and misty golden mountains behind, serene expression, elegant slow turns, cinematic wuxia-dance energy>, beginning, peak and settle in one continuous shot. Camera: <one move: slow push-in, gentle orbit, or static>. The same face and outfit throughout. Cinematic, no text.
```

## Failure handling

- `success=false`: say what failed in one sentence; retry once only if transient; never invent links.
- Content-policy rejection on video: soften wording and retry once; otherwise offer the keyframe as a still.
- Identity drifts: offer to regenerate.

## Examples

**Default**: the user says "this one" with a photo. Use end pose `graceful ribbon arc`, prompt notes `optional mood`, 9:16. Reply: "All set. Your classical chinese ribbon dance is on the canvas."
**Variation**: "next variation". Keep the same inputs and chan