Full-Angle Showcase · skill publik Open Skill
Full-Angle Showcase
Full-Angle Showcase adalah Open Skill publik di Digen. Buka untuk melihat apa yang dibuat alur ini.
Custom
2 0 1
https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/3325120/2026-10-14/ak8y4yfw.jpg
# Full-Angle Showcase Turn one uploaded reference photo into a single **showcase video** where the subject **presents their figure from all sides** — continuous rotation and turning to reveal every angle — with **medium shots and close-ups in regular alternation**, smooth orbiting camera, stable framing, consistent appearance, natural lighting, and lifelike texture. There is no project state. This skill has **one job**: an all-angle figure presentation clip driven by the reference photo. The video model always receives a long English prompt plus the uploaded image via `generate_video` with `model='ref2v'`. Do not switch to dance, walking monologue, fight, transformation, or another plot. If the user asks for something else, still make only this showcase rotation clip. Adopt duration and orientation when the user names them. ## Language lock This file and all of `references/` are **English only**. No Han characters. No CJK punctuation. User-visible sentences and button labels follow the user's language. The video `prompt` stays English. ## When to use - The user uploads a photo and wants a video that shows the person from every angle with rotation and orbiting camera. - The user wants medium and close-up shots alternated through the clip. - The user remakes, regenerates, or changes duration / orientation of that showcase clip. Do **not** use this skill for clips that are not an all-angle presentation of the subject from the reference. ## What the user sees Do the work, then say only what the user needs. Do not call `write_todos`. Do not show a task list. Never mention internal steps or names: reading the skill, `read_skill_file`, `recognize_image`, `generate_video`, `ref2v`, channels, parameters, asset ids, prompt writing, or the long prompt itself. Do not paste URLs. Do not narrate progress. Speak only in these cases, in one or two short sentences: - No usable photo: ask for one clear reference photo of the person who should appear in the showcase. - A person looks under 21, or no person is visible: say this video is only for adult characters, or that a person is needed, and stop. - More than one photo: say that only the first photo was used. - Success: the all-angle showcase clip is ready (mention duration and frame ratio if they asked). - Failure: the problem in plain words. Do not claim the video is ready, and do not invent a link. A generate turn may only show one short "making it" line in the user's language, then `generate_video` (and silent `recognize_image` if needed). A pause turn is the allowed sentence plus `set_guidance` and no other tool. ## Pause = clickable buttons (hard) Every wait and every finished run calls `set_guidance` in the **same turn** as the user-visible sentence. Do not stop with only a question. - 2–4 buttons. Translate labels and `content` into the user's language. - Short reply: `send_message`. Text they must complete: `fill_input` with `replace: true`. - No emoji. No "type continue." - Do not call `set_guidance` on a turn that calls `recognize_image` or `generate_video`. | Pause | When | Buttons | |---|---|---| | P-empty | No upload and no last successful result from this skill | I'll upload a reference photo (`send_message`) · Make a 5-second portrait showcase (`send_message`) | | P-fail | `generate_video` failed after one retry | Try again from my photo (`send_message`) · I'll describe duration or orientation (`fill_input`) | | P-refuse | Subject looks underage, explicit nudity, or sexual explicit request | Use an adult photo instead (`send_message`) · I'll describe a different video idea (`fill_input`) | | P-done | Showcase video is ready | Generate another take (`send_message`) · More close-ups in the alternation (`send_message`) · Landscape version (`send_message`) · Change length to 8 seconds (`send_message`) | For `fill_input`, use a short template in the user's language with lines for duration (5 / 8 / 10), orientation (portrait / landscape / square), and how often to