Mitosis Clone Split · публичный навык Open Skill

Mitosis Clone Split

**Was** I had one polished beauty shot in the studio. **Now** the adult subject shimmers, divides like a cell, and steps into identical clones. **Input -> result:** one clear adult photo -> a surreal portrait video with repeated splits. **Options:** Upload one photo. The result stays portrait, 9:16. **Tip:** A visible face gives the cleanest split, and I can redo the effect.

@JordanReyes

Meme

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284951/2026-10-15/sve4bqbz.gif

# Mitosis Clone Split

Blink and there are two of you. The person in your photo shimmers, divides like a cell and steps apart into identical clones, again and again.

## When to use

- The user wants a surreal video where the person in their photo splits into identical copies (mitosis, clone duplication effect)
- 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 | `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='Mitosis Clone Split 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='Mitosis Clone Split', entity_type='final_videos')`. Pass only the keyframe, never the original upload.
5. Reply in one or two sentences, e.g. "Your mitosis clone split is ready. Want another take with 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: standing outdoors when their body shimmers and divides like a cell into two, then four identical copies that step apart and look at each other in surprise, smooth seamless transformation. 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: standing outdoors when their body shimmers and divides like a cell into two, then four identical copies that step apart and look at each other in surprise, smooth seamless transformation>, 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 "here's my selfie, do it" with a photo. Use the tuned defaults, 9:16. Reply: "Your mitosis clone split is ready."
**Variation**: "love it, make another". Keep the same inputs and change one option (a 10-second cut).
**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`