Afterimage Color Illusion · публичный навык Open Skill

Afterimage Color Illusion

Afterimage Color Illusion — публичный Open Skill на Digen. Откройте, чтобы увидеть, что создаёт этот процесс.

@LoganPierce

Meme

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284957/2026-10-16/ehmjvb6b.gif

# Afterimage Color Illusion

Stare at the star. Your photo becomes a 15-second afterimage illusion: a center star, then a black-and-white version of your image — keep staring and color seems to flood back.

## When to use

- The user wants an optical-illusion video that makes their photo appear in color after a black-and-white stare (afterimage color trick, mind-bending color fill clip)
- 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 |
| Duration | No | `6` s | 6 or 10 |
| Orientation | No | `3:4` 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='3:4', name='Afterimage Color Illusion 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='3:4', duration=<d>, name='Afterimage Color Illusion', entity_type='final_videos')`. Pass only the keyframe, never the original upload.
5. Reply in one or two sentences, e.g. "Done! Here's your afterimage color illusion. I can also try a 10-second cut if you like." 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: an optical-illusion video built from the uploaded image: open on a centered star marker on a muted field, then cut to a carefully prepared black-and-white version of the same image with a tiny center fixation point; hold long enough for the classic afterimage color-fill effect when the viewer keeps staring, calm locked-off camera, no extra props. 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: an optical-illusion video built from the uploaded image: open on a centered star marker on a muted field, then cut to a carefully prepared black-and-white version of the same image with a tiny center fixation point; hold long enough for the classic afterimage color-fill effect when the viewer keeps staring, calm locked-off camera, no extra props>, 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 "use this pic" with a photo. Use the tuned defaults, 3:4. Reply: "Done! Here's your afterimage color illusion."
**Variation**: "one more please". Keep the same inputs and change one option (a 10-second cut).
**Missing input**: no photo was sent. Ask: "I need one clear, front-f