Halloween Mirror Wink · Open Skill 공개 스킬
Halloween Mirror Wink
Halloween Mirror Wink은 Digen의 공개 Open Skill입니다. 열어 보면 이 워크플로가 무엇을 만드는지 알 수 있습니다.
Film
1 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284956/2026-10-16/weq6qdjv.gif
# Halloween Mirror Wink Look twice. Your photo becomes a haunted-mirror clip: you admire yourself, then the reflection flashes a full vampire look, winks, and when you turn back only a mischievous fang grin remains. ## When to use - The user wants a short Halloween mirror-scare video from their photo (vampire reflection wink, haunted mirror prank 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 | | Reflection costume | No | `classic vampire` | classic vampire (default), or user-described Halloween look | | 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='Halloween Mirror Wink 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='Halloween Mirror Wink', entity_type='final_videos')`. Pass only the keyframe, never the original upload. 5. Reply in one or two sentences, e.g. "All set. Your halloween mirror wink is on the canvas. Next I can do 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: the same adult person stands before an ornate antique mirror in a dim gothic room; their reflection suddenly wears a full vampire Halloween outfit with cape and pale makeup, playfully winks, then when the person turns around the reflection is gone leaving only a mischievous little fang grin on the glass, cinematic candlelight, short spooky narrative clip. 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: the same adult person stands before an ornate antique mirror in a dim gothic room; their reflection suddenly wears a full vampire Halloween outfit with cape and pale makeup, playfully winks, then when the person turns around the reflection is gone leaving only a mischievous little fang grin on the glass, cinematic candlelight, short spooky narrative clip>, 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 reflection costume `classic vampire`, 9:16. Reply: "All set. Your halloween mirror wink is on the canvas." **Variation**: "next variation". Keep the same inputs