Wan2 1 Video Conversion Uses · Open Skill 公開技能

Wan2 1 Video Conversion Uses

Wan2 1 Video Conversion Uses 是 Digen 上的公開 Open Skill。開啟後即可了解此工作流能製作什麼。

@l1ror6r0qixd

Custom

3 0 3

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284864/2026-10-21/z36dctv7.jpg

# Wan2 1 Video Conversion Uses

Deliver one **cinematic short video** built from a reference photo of **four people**. The four subjects move through **smooth, delicate pose transitions** with **natural body movement**, while **identity, outfits, and balanced group framing stay locked** across every frame. Output is **high-definition** with **dramatic cinematic lighting** and **elegant camera drift**.

**Upload path:** user photo drives identity and outfit of all four people; run **`i2v`** with the locked motion timeline. **Direct generate:** text-to-image **four-person cinematic pose still** (default invented group), then the same **`i2v`** pipeline — **upload is never strictly required**.

Prompt templates and motion beats live in `references/`. No structured project state.

**Language lock:** This file and all of `references/` are **English only**. Reply in the **user's language**. Every `generate_image` and `generate_video` prompt is **English**.

Do not tell the user tool names, channel names, or dump full prompts.

## User-visible speech (hard)

**Allowed lines only:**

- Need input: one short note that they may **upload a four-person photo**, **describe the group**, or **tap direct generate** — then pause **P-empty** or **P-brief**.
- Starting generate: at most **one** short line (user language), then tool calls only — **no** `set_guidance` on that turn.
- Success: one or two sentences that the **four-person cinematic video** is ready — no URL, no prompt dump. Pause **P-done**.
- Tool failure: brief honest note. Pause **P-fail**.
- Safety block: one polite refusal. Pause **P-refuse**.

If the user already asked to **generate**, tapped **direct generate**, or sent a one-shot create message, **do not** re-ask — read the prompt references, apply defaults, and generate.

## Pause = clickable buttons (hard)

Any turn that **stops without a new shown final video**, and **every success turn**, must end with:

1. One or two short sentences (user language).
2. **`set_guidance`** in the **same turn**, with **at least two** clickable options. **No tool calls after `set_guidance`.**

Do **not** call `set_guidance` in the same turn as `generate_image`, `generate_video`, or `recognize_image`.

Each button is an object with `text` and `action` (not bare strings):

- **`send_message`**: `content` is the full sentence sent when tapped.
- **`fill_input`**: `content` is starter text the user can edit.

Offer **2–4** options. Localize `text` and `content` to the user's language. No channel or tool names on buttons.

Before every pause turn, `read_skill_file` → `references/guidance-buttons.md`.

| Pause | When | Example intents (localize) |
|---|---|---|
| P-empty | No upload, no group brief, no direct-generate tap, no last clip to refine | Direct generate four-person video · Upload group photo · Describe the group |
| P-brief | Wants the video but no group cues and no upload | Direct generate default group · fill_input custom group · Upload photo instead |
| P-refuse | Real-person face as subject without consent, gore, hate, NSFW | Direct generate fictional group · Upload a different photo |
| P-fail | Generation or `video_agent` `success=false` after retry | Direct generate again · Regenerate from last still · Softer motion, same framing |
| P-done | Final four-person cinematic video ready | Direct generate new group · Upload my photo · Faster motion · Slower cinematic drift |

## When to use

- User wants **Four-Person Pose Cinematic Video** / **4-person pose video** / **group photo to video** with **delicate pose transitions** and **identity lock**.
- User uploads a **photo of four people** and wants a **cinematic short video** preserving **each person's identity, outfits, and group framing**.
- User has **no photo** or taps **direct generate** — run **T2I four-person still + i2v** using defaults in `references/guidance-buttons.md` (default invented group, not real celebrities).
- User asks to **retry**, **regenerate from last still**,