Phone Screen Ice Rink · Open Skill 公开技能
Phone Screen Ice Rink
Phone Screen Ice Rink 是 Digen 上的公开 Open Skill。打开后即可了解该工作流能制作什么。
Product
1 0 3
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284955/2026-10-18/q6cjtgsq.webp
# Phone Screen Ice Rink A rink in your pocket. The phone's screen cracks into real ice and a tiny hockey game rages across it, shot like a daylight sports ad on a tabletop. ## When to use - The user wants a smartphone screen turned into a miniature ice-hockey rink with cracked ice and tiny players mid-game (phone-screen hockey miniature, pocket rink diorama, device sports ad) - A variation on a previous result: breakaway shot Not for: Video output (use a video skill). ## Inputs and gates | Input | Required | Default | Gate | |---|---|---|---| | Person photo | No | — | Optional; if given, the face is preserved | | Phone reference | No | — | photo of the handset to match | | Description | No | tuned default below | What the user wants; merged into the prompt | | Moment | No | `face-off near center ice` | face-off near center ice (default), breakaway shot, goalie save, or user-described | | Ratio | No | `3:4 default` | 3:4 default; 4:5, 1:1 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. - Fashion, dark and horror themes are fine as stills; refuse explicit sexual content and anything sexualizing minors. ## Steps 1. Read `references/image-edit.md` for prompt structure. 2. Fill the template below from the user's description. Use the tuned defaults for anything they leave out; ask one short question only if the subject itself is unclear. 3. If a person photo is given: `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.')` and add the identity clause. 4. With reference images: `generate_image(prompt=<PROMPT>, input_urls=[refs...], model='i2i.hd', orientation='portrait', aspect_ratio='3:4', name='Phone Screen Ice Rink', entity_type='skill_generation')`; without: the same call with `model='t2i.hd'` and no `input_urls`. 5. **Self-check, one retry**: look at the result. If a person photo was used and the face no longer reads as the same person, regenerate with the identity clause first. If someone glancing at it would not instantly see the intended change (it reads as a light filter, the old clothes or background remain, or the style is faint), regenerate once with the change described bigger and more concretely. 6. Reply in one or two sentences, e.g. "Your phone screen ice rink is ready. Want another take with breakaway shot?" Results appear on the canvas; never paste URLs. ## Prompt templates **PROMPT** ```text <if photo: The same adult from the reference: <identity line>.> Intentional changes: a lifelike daylight product photo of a smartphone lying on a tabletop whose screen has become a miniature ice-hockey rink: deeply cracked, frosted ice breaking out past the bezel, tiny adult players in <team colors: red-and-white versus navy-and-white (default) or user-described> battling for the puck near center ice, ice shavings spraying, boards and nets compressed into the display, tilted three-quarter perspective, shallow focus, <phone: a graphite flagship with slim bezels (default) or from the phone reference/description>. <user details and options>. Clear focal hierarchy; any text short, in quotes and spelled exactly; no real brands. Lighting and materials described concretely; composition suited to portrait 3:4. Photoreal unless the style says otherwise, fully clothed, no text unless requested. ``` Quality bar: Keep on-image text short and in quotes; no real brand names or logos; one clear focal hierarchy. ## Failure handling - `success=false`: say what failed in one sentence; retry once only if transient; never invent links. - The face changes: regenerate once with the identity clause first; then say so honestly. ## Examples **Default**: the user says "here's my selfie, do it". Use moment `face-off near center ice`, ratio `3:4 default`, 3:4.