Figurine Escapes Box · publiczny skill Open Skill

Figurine Escapes Box

Figurine Escapes Box to publiczny Open Skill w Digen. Otwórz go, by zobaczyć, co tworzy ten workflow.

@RileyHauls

Product

1 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321751/2026-10-20/9mmgtgge.webp

# Figurine Escapes Box

Your collectible peeks out, climbs free and waves. One playful miniature clip with the face, colors, costume and accessories kept exactly as they are.

## When to use

- The user wants their collectible figurine or character design to come alive and climb out of its toy box (figurine comes to life, toy box escape clip, collectible animation)
- Another take with a different length or orientation

Not for: Still images only.

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Image | Yes | — | The picture to animate; one clear main subject |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Box | No | `kraft-brown cardboard toy box` | kraft-brown cardboard toy box (default), pale blue and orange illustrated box, glossy black collector box, or user-described |
| Gesture | No | `waving hand` | waving hand (default), two-handed cheer, salute, or user-described |
| Duration | No | `6 s` | 6 s (default), or 10 s |
| 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. `recognize_image(image_url=<image>, prompt='Describe the main subject, style and composition in one line')`.
3. `generate_video(prompt=<MOTION>, input_urls=[image], model='i2v', orientation='portrait', aspect_ratio='9:16', duration=<d>, name='Figurine Escapes Box', entity_type='final_videos')`.
4. Reply in one or two sentences, e.g. "Your figurine escapes box is ready. Want another take with pale blue and orange illustrated box?" Results appear on the canvas; never paste URLs.

## Prompt templates

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

```text
Starting from this exact frame: the figurine's head pops up over the rim of the box, both hands gripping the edge; it hauls itself up and over in one smooth comedic push, plants both feet on the desk, wobbles once, then straightens into a confident <gesture: waving hand (default), two-handed cheer, salute, or user-described> that peaks around the fourth second and holds with a small settle bounce as the head tilts toward camera. The camera performs a single slow arc around the figurine from the box side toward the front, ending in a gentle push in. Keep the figurine's sculpted face, colors, costume and accessories exactly as shown: same design, same materials, no morphing, no extra limbs, no change of proportions, matte collectible toy look throughout. Box, desk and lamp light stay consistent. No humans enter the frame.
```

## 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 "here's my selfie, do it" with a photo. Use box `kraft-brown cardboard toy box`, gesture `waving hand`, 9:16. Reply: "Your figurine escapes box is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (pale blue and orange illustrated box).
**Missing input**: no photo was sent. Ask: "Send one clear photo where your face is easy to see, and I'll start."

## References

- `references/video-motion.md`