Warm Hug POV · Open Skill 公开技能

Warm Hug POV

was: A close-up waiting for warmth. now: I build a first-person hug from one adult photo. The subject smiles, walks toward me, and gives me a gentle embrace. Photo -> first-person 9:16 portrait clip Options: Upload one clear adult photo, ideally with the face visible. Portrait orientation and a 9:16 ratio are set on every generation. Setting: I can redo the hug with a different setting for a different mood.

@JordanReyes

Meme

2 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284951/2026-10-15/mwpxsy3d.gif

# Warm Hug POV

A first-person moment that feels like coming home: the person in your photo smiles, walks toward you and wraps you in a gentle hug.

## When to use

- The user wants a short first-person video where the person in their photo walks up to the camera and gives a warm hug (POV hug, comforting embrace 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 | `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='Warm Hug POV 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='Warm Hug POV', entity_type='final_videos')`. Pass only the keyframe, never the original upload.
5. Reply in one or two sentences, e.g. "Your warm hug pov 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: walking toward the camera with a warm smile in a softly lit cozy room and gently embracing the viewer; first-person POV camera, the shot ends close and warm. 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: walking toward the camera with a warm smile in a softly lit cozy room and gently embracing the viewer; first-person POV camera, the shot ends close and warm>, 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 warm hug pov 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`