Pumpkin Spirit Awakening · skill pública Open Skill
Pumpkin Spirit Awakening
Pumpkin Spirit Awakening é uma Open Skill pública no Digen. Abra para ver o que este fluxo cria.
Meme
2 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/550336/2026-10-15/buzkq7yp.webp
# Pumpkin Spirit Awakening A roadside jack-o'-lantern stares back. Its carved grin catches fire in swirling emerald and violet witch-light, sparks spiral around you, and you answer with a sly, knowing smirk. ## When to use - The user wants a short vertical Halloween video of their photo meeting a haunted jack-o'-lantern that bursts into magical flame (pumpkin awakening, spooky Halloween character moment) - 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 | | Mood | No | `playful-mischievous` | playful-mischievous (default), cute, eerie, extra sparkle | | 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='Pumpkin Spirit Awakening 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='Pumpkin Spirit Awakening', entity_type='final_videos')`. Pass only the keyframe, never the original upload. 5. Reply in one or two sentences, e.g. "All set. Your pumpkin spirit awakening is on the canvas. Next I can do cute." 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 stands on a misty autumn roadside at dusk holding a carved jack-o'-lantern at chest height; the pumpkin's carved face ignites with emerald and violet magical fire, glowing sparks spiral around them and they break into a mischievous knowing grin. 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 stands on a misty autumn roadside at dusk holding a carved jack-o'-lantern at chest height; the pumpkin's carved face ignites with emerald and violet magical fire, glowing sparks spiral around them and they break into a mischievous knowing grin>, 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 mood `playful-mischievous`, 9:16. Reply: "All set. Your pumpkin spirit awakening is on the canvas." **Variation**: "next variation". Keep the same inputs and change one option (cute). **Missing input**: no photo was sent. Ask: "Drop in one photo of yourself (face clearly visible) to get started." ## References -