Halloween Creature Selfie Video · Open Skill 公開スキル
Halloween Creature Selfie Video
Halloween Creature Selfie Video は Digen 上の公開 Open Skill です。開くと、このワークフローが何を作るか分かります。
Roleplay
0 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321698/2026-10-22/p7zqkv3r.webp
# Halloween Creature Selfie Video One selfie, one cinematic creature reveal. The camera drifts from your everyday selfie into a fog-soaked gothic world, and the adult in frame turns into a pale moonlit witch or a red-eyed vampire in black lace. ## When to use - The user wants their selfie transformed into a cinematic short video where they become a Halloween witch or vampire creature in a dark-fantasy world (Halloween creature selfie clip, witch vampire makeover video, spooky creature transformation) - Another take with a different length or orientation Not for: Still images only. ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Photo | Yes | — | One adult, face clear and forward-facing like a selfie. Ask for another photo if the face is tiny, blurred, angled away or hidden | | Description | No | tuned default below | What the user wants; merged into the prompt | | Creature | No | `pale gothic vampire` | pale gothic vampire (default), moonlit witch, wraith-like spirit, or user-named | | Mood | No | `eerie and alluring` | eerie and alluring (default), playful spooky, regal and ominous, 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(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 Creature Selfie Video 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 Creature Selfie Video', entity_type='final_videos')`. Pass only the keyframe, never the original upload. 5. Reply in one or two sentences, e.g. "Here it is: your halloween creature selfie video. Shall I do a version with moonlit witch?" 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 becomes <creature: pale gothic vampire (default), moonlit witch, or user-named creature> in a surreal dark-fantasy ruin world: porcelain-pale skin with fine crack-like veins, one glowing amber eye, crimson lips, black high-neck lace gown with a gem pendant, long dark windswept hair, gothic cathedral arches and a huge full moon behind, drifting fog and ember light, fully clothed, tasteful cinematic dark-fantasy look. 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 adult holds a still, confident selfie gaze for a beat, then slowly lowers the phone hand and lifts the chin as drifting fog curls across the frame and ember sparks rise; the glowing amber eye brightens at the peak while dark windswept hair lifts and settles, and by the settle the creature's gaze meets the lens with a faint, alluring half-smile as a huge full moon glows behind the gothic arches. One primary camera move: a slow confident push-in toward the face that eases to a gentle hold. Preserve facial features and identity exactly: same face, makeup, hairstyle,