Halloween Magical Forest Person Video · Open Skill 公開技能

Halloween Magical Forest Person Video

Halloween Magical Forest Person Video 是 Digen 上的公開 Open Skill。開啟後即可了解此工作流能製作什麼。

@hiaosbd

Custom

0 0 1

https://d7qlwi7tl2u27.cloudfront.net/skill-covers/prod/4284861/2026-10-15/exaft8ks.gif

# Halloween Magical Forest Person Video

Deliver one **short vertical (9:16) Halloween fantasy walk clip** (default **12 seconds** unless the user asked for another length). The person **walks forward following will-o'-the-wisp lights** through an **enchanted foggy forest**. **Facial identity lock:** keep the reference person's **exact facial features and recognizability**; **clothing, background, props, and lighting** may shift to Halloween magical-forest styling.

**Upload path:** optional hero still polish, then **`ref2v`** with the locked forest-walk prompt and embedded ambient audio when the model supports it. **Direct generate:** text-to-image **three-quarter or full-body keyframe** of an original adult, then the same pipeline—**upload is never required**.

Prompt templates and camera 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`, `generate_video`, and `video_agent` `instruction` 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 portrait**, **describe the walker**, 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 **magical forest walk clip** 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`, `video_agent`, 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 walker brief, no direct-generate tap, no last clip to refine | Direct generate forest walk · Upload my photo · Describe my walker |
| P-brief | Wants the forest clip but no mood or wardrobe cues and no upload | Direct generate default · fill_input custom walker · Upload photo instead |
| P-refuse | Minor in sexualized context, non-consensual deepfake, hate, graphic gore, NSFW staging | Direct generate fictional adult · Upload a different photo |
| P-fail | Generation or `video_agent` `success=false` after retry | Direct generate again · Regenerate video from last still · More eerie fog |
| P-done | Final forest walk clip ready | Direct generate new character · Upload my photo · More eerie · Softer dreamy mood |

## When to use

- User wants a **Halloween magical forest** video with **will-o'-the-wisp** lights and **identity-locked face** from a photo or invented character.
- User uploads a **portrait** and wants a **dreamy, subtly eerie** walk with **low-to-rising camera** tracking.
- User has **no photo** or taps **direct generate**—run **T2I keyframe + ref2v** using defaults in `references/guidance-buttons.md` (default **original adult in subtle Halloween forest attire**,