Halloween Mirror Maze Clip · Open Skill 공개 스킬

Halloween Mirror Maze Clip

Halloween Mirror Maze Clip은 Digen의 공개 Open Skill입니다. 열어 보면 이 워크플로가 무엇을 만드는지 알 수 있습니다.

@BrookeHollis

Film

0 0 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284958/2026-10-18/x4uw37ge.webp

# Halloween Mirror Maze Clip

Mist, candles, endless you. Your photo steps into a Halloween mirror maze — reflections multiply while you stay unmistakably yourself.

## When to use

- The user wants a Halloween video of themselves inside a foggy mirror maze (halloween mirror maze clip, candlelit reflection maze video, eerie hall of mirrors photo-to-video)
- Another take with a different length or orientation

Not for: Still images only.

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo | Yes | — | One adult, face clear. Ask for another photo if the face is tiny, blurred or hidden |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Duration | No | `6 s` | 6 s (default), or 10 s |
| Mood | No | `eerie wonder` | eerie wonder (default), tense dread, playful spooky |
| 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='Halloween Mirror Maze Clip 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='Halloween Mirror Maze Clip', entity_type='final_videos')`. Pass only the keyframe, never the original upload.
5. Reply in one or two sentences, e.g. "All set. Your halloween mirror maze clip is on the canvas. Next I can do 10 s." 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 walking a candlelit Halloween mirror maze: fog rolling between infinite reflections, warm candle flicker on glass, cool purple night fill, a slow push-in as reflections shift, fully clothed everyday or festive outfit, identity locked in every reflection. 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 walking a candlelit Halloween mirror maze: fog rolling between infinite reflections, warm candle flicker on glass, cool purple night fill, a slow push-in as reflections shift, fully clothed everyday or festive outfit, identity locked in every reflection>, 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 duration `6 s`, mood `eerie wonder`, 9:16. Reply: "All set. Your halloween mirror maze clip is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (10 s).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) t