Pumpkin Spotlight Pet · सार्वजनिक Open Skill
Pumpkin Spotlight Pet
Pumpkin Spotlight Pet Digen पर एक सार्वजनिक Open Skill है। खोलें और जानें कि यह वर्कफ़्लो क्या बनाता है।
Meme
0 0 2
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321704/2026-10-21/2emayzpk.gif
# Pumpkin Spotlight Pet A cheeky glowing jack-o'-lantern hops into frame and steals the show. Your pet peeks around it in a witch hat and cape — fur, eyes and that unmistakable face kept. ## When to use - The user wants their pet photo turned into a short Halloween clip where a cheeky glowing jack-o'-lantern hops into the foreground and steals the spotlight while the pet peeks around it in a witch hat and cape (pet pumpkin photobomb clip, Halloween pet spotlight, pet witch costume video) - Another take with a different length or orientation Not for: Still images only. ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Image | Yes | — | The picture to animate; one clear main subject | | Description | No | tuned default below | What the user wants; merged into the prompt | | Duration | No | `6 s` | 6 s (default), or 10 s | | Costume | No | `purple star-print witch hat and cape` | purple star-print witch hat and cape (default), orange-gold witch set, black-and-gold cape | | Pumpkin | No | `grinning carved jack-o'-lantern` | grinning carved jack-o'-lantern (default), winking lantern, sleepy-toothed pumpkin | | Pet pose | No | `peeking around the pumpkin` | peeking around the pumpkin (default), sitting proud beside it, mid-hop surprise | | 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. `recognize_image(image_url=<image>, prompt='Describe the main subject, style and composition in one line')`. 3. `generate_video(prompt=<MOTION>, input_urls=[image], model='i2v', orientation='portrait', aspect_ratio='9:16', duration=<d>, name='Pumpkin Spotlight Pet', entity_type='final_videos')`. 4. Reply in one or two sentences, e.g. "All set. Your pumpkin spotlight pet is on the canvas. Next I can do 10 s." Results appear on the canvas; never paste URLs. ## Prompt templates **MOTION** (motion only; the frame already shows the look) ```text Starting from this exact frame: a glowing carved jack-o'-lantern <pumpkin: grinning carved jack-o'-lantern (default), winking lantern, sleepy-toothed pumpkin> hops up from the lower foreground, bounces once and settles front-center, its warm light swelling to steal the spotlight; the pet tilts its head, then leans out from behind the pumpkin in a quick peek, ears perking, before easing back into a calm proud sit in a <costume: purple star-print witch hat and cape (default), orange-gold witch set, black-and-gold cape>. The camera makes one slow push in, keeping both the pumpkin and the pet's face in frame throughout. Preserve the pet's exact fur colours, markings, eyes, muzzle and proportions, and keep the costume props identical in every frame; no morphing of the animal. Cozy lantern light, playful Halloween warmth, single continuous shot, 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`, costume `purple star-print witch hat and cape`, 9:16. Reply: "All set. Your pumpkin spotlight pet 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-motion.md`