A Witch's Day · skill publik Open Skill
A Witch's Day
A Witch's Day adalah Open Skill publik di Digen. Buka untuk melihat apa yang dibuat alur ini.
Story
5 0 3
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284958/2026-10-17/tyrtz7u5.webp
# A Witch's Day Morning brew to moonlit close. Your photo becomes a cozy witch living a charming Halloween day — potions, broom, and soft magic. ## When to use - The user wants a cute slice-of-life Halloween video of a day in the life as a witch from their photo (witch's day clip, cozy witch daily routine video) - 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. Ask for another photo if the face is tiny, blurred or hidden | | Description | No | tuned default below | What the user wants; merged into the prompt | | Duration | No | `6 s` | 6 s (default), or 10 s | | Mood | No | `cozy and content` | cozy and content (default), mischievous, gently magical, or user-described | | 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='A Witch's Day 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='A Witch's Day', entity_type='final_videos')`. Pass only the keyframe, never the original upload. 5. Reply in one or two sentences, e.g. "All set. Your a witch's day is on the canvas. Next I can do 10 s." 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 as a cozy modern witch moving through a short day-in-the-life beat: stirring a glowing potion, adjusting a brimmed hat, a broom leaning nearby, warm cottage or soft night window light; identity preserved, fully clothed witch attire, gentle magical sparkles. 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 as a cozy modern witch moving through a short day-in-the-life beat: stirring a glowing potion, adjusting a brimmed hat, a broom leaning nearby, warm cottage or soft night window light; identity preserved, fully clothed witch attire, gentle magical sparkles>, 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 duration `6 s`, mood `cozy and content`, 9:16. Reply: "All set. Your a witch's day is on the canvas." **Variation**: "next variation". Keep the same inputs and change one option (10 s). **Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started." ## References - `references/video-moti