Subway Selfie Sing-Along · skill Open Skill công khai
Subway Selfie Sing-Along
Subway Selfie Sing-Along là một Open Skill công khai trên Digen. Mở ra để xem workflow này tạo gì.
Film
1 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4321701/2026-10-22/4uce2gkg.gif
# Subway Selfie Sing-Along One arm out, trolley straps swinging behind you. A single continuous handheld selfie take where you shut your eyes, tip your head back and belt the long note before grinning back at the lens. ## When to use - The user wants a handheld selfie video of themselves singing inside a subway carriage (subway sing-along clip, train selfie performance, singing selfie short) - 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 front-facing; head-and-shoulders or half-body works best. Ask for another photo if the face is tiny, turned away, blurred or hidden | | Description | No | tuned default below | What the user wants; merged into the prompt | | Setting | No | `bright daytime city subway car` | bright daytime city subway car (default), quiet late-night empty car, or user-described transit interior | | Outfit | No | `black satin wrap dress` | black satin wrap dress (default), oversized knit and jeans, casual streetwear, 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='Subway Selfie Sing-Along 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='Subway Selfie Sing-Along', entity_type='final_videos')`. Pass only the keyframe, never the original upload. 5. Reply in one or two sentences, e.g. "Your subway selfie sing-along is ready. Want another take with quiet late-night empty car?" 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 in a handheld front-facing selfie inside a <setting: bright daytime city subway car (default), quiet late-night empty car, or user-described transit interior> with blue bench seating, chrome poles and hanging grab straps, wearing <outfit: black satin wrap dress (default), oversized knit and jeans, casual streetwear, or user-described fully clothed outfit>; starts smiling into the lens, eyes close, head tilts back to sing, one hand rises for the long note, then a warm smile to camera; natural car lighting, slight phone-camera compression, one continuous take. 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 subject keeps the selfie arm slightly extended and begins a slow sway with the carriage rock, eyes closing and head tipping back as the sing-along kicks in; around the midpoint both the sway and the breath peak into the long note, one hand rising into frame while the trolley straps swing behind; then the note settles as the head comes back level and a warm smile lands straight into the lens. One continuous handheld take with a gentle drift-push in and a faint na