Finger Frame Reveal Clip · مهارة Open Skill عامة

Finger Frame Reveal Clip

one guy, fifty characters, and somehow the face reveal still steals the scene. need: two adult photos, one person framing the other's face with their fingers. get: a clip where a glowing window opens and the second face smiles inside. try: playful surprise, neon lime-cyan glow, 9:16 portrait, 6 seconds.

@TwistTheo

Meme

0 0 0

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321704/2026-10-21/hsqd48wb.gif

# Finger Frame Reveal Clip

Two photos, one magic trick. The first person holds a finger frame to the lens and a glowing window opens inside it — the second person's face appearing there, alive and smiling.

## When to use

- The user wants two photos merged into a clip where the first person frames the second person's face with their fingers (finger frame reveal, hand-frame face swap video, glowing finger portal reveal)
- Another take with a different length or orientation

Not for: Still images only.

## Inputs and gates

| Input | Required | Default | Gate |
|---|---|---|---|
| Photo of person 1 | Yes | — | Clear face, adult |
| Photo of person 2 | Yes | — | Clear face, adult |
| Description | No | tuned default below | What the user wants; merged into the prompt |
| Glow | No | `neon lime-cyan rim` | neon lime-cyan rim (default), hot magenta, warm amber, or user-described |
| Mood | No | `playful surprise` | playful surprise (default), cheeky wink, cool and confident, 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. **Identity read**: `recognize_image` on each photo (one compact identity line each).
3. **Keyframe**: `generate_image(prompt=<KEYFRAME>, input_urls=[photo 1, photo 2], model='i2i.hd', orientation='portrait', aspect_ratio='9:16', name='Finger Frame Reveal Clip 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='Finger Frame Reveal Clip', entity_type='final_videos')`. Pass only the keyframe, never the original upload.
5. Reply in one or two sentences, e.g. "All set. Your finger frame reveal clip is on the canvas. Next I can do hot magenta." Results appear on the canvas; never paste URLs.

## Prompt templates

**KEYFRAME**

```text
Person 1: <identity 1>. Person 2: <identity 2>. Same face structure, eyes, skin tone and recognizable likeness; no beautification or face reshaping. Opening frame of this scene: the same adult <person1: from the first photo (default), or user-described> in <outfit: their original clothing (default), a rich cobalt turtleneck, a soft knit sweater, or user-described>, both hands raised to make an L-shaped finger frame around the face, the finger frame glowing with a bright neon rim and a warm halo, and inside that window the second adult's face (<person2> from the close-up photo, kept exactly) appears framed and lit by the same neon glow, <setting: deep blue-to-magenta studio backdrop (default), dark night with neon signage, plain soft gradient wall, or user-described>, saturated rim light, glossy skin, front-facing playful reveal, fully clothed, both people adults. 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: the performer's hands begin steady, then the fingertips curl slightly inward as a soft pulse of <glow: neon lime-cyan rim (default), hot magenta, warm amber, or user-described> light blooms along the finger frame; the glow peaks and the face inside the window brightens, eyes opening into camera with a slow blink and a growing <mood: playful surprise (default), cheeky wink, cool and confident, or user-described> smile, the performer tilting their head a quarter turn toward the frame as the light settles back to a steady halo by the final beat. The camera pushes in slowly and evenly, holding the finger frame centered. Preserve facial features and id