Objects After Dark · skill pública Open Skill

Objects After Dark

Q: Ask: My desk gets ideas after-hours. I upload a room photo and tell the objects what to do. A: Get: I get a 5-second video. I can choose 10 seconds for a longer scene. Q: Ask: How do I direct the objects? A: Get: I add a description with details, scene ideas, or odd behavior. The image is required. Q: Ask: Why does it come back landscape? A: Get: Every video uses a 16:9 landscape frame, even with a vertical source image.

@MayaCalloway

Story

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/vptn67n6.webp

# Objects After Dark

When the lights go off, the mug yawns, the lamp peeks around and the stapler gets ideas. Your ordinary room comes alive with mischievous personality.

## When to use

- The user wants a photo of a room or desk turned into a video where everyday objects come alive (animated objects, magical living items)
- 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 |
| Duration | No | `5` | 5 or 10 seconds (default 5) |
| Orientation | No | `16:9` landscape | 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='landscape', aspect_ratio='16:9', duration=<d>, name='Objects After Dark', entity_type='final_videos')`.
4. Reply in one or two sentences, e.g. "All set. Your objects after dark is on the canvas. Next I can do 10 seconds (default 5)." 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: <one clear motion arc for this concept: the same room at night where everyday objects come alive with playful personality (mugs, lamps, books moving and reacting), whimsical animation, cinematic camera>, 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 `5`, 16:9. Reply: "All set. Your objects after dark is on the canvas."
**Variation**: "next variation". Keep the same inputs and change one option (10 seconds (default 5)).
**Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started."

## References

- `references/video-motion.md`