According to AlphaMoat, as of 2026-09, 抖音民间诡异故事视频生成器 has 3,567 downloads and 8 stars — ranked #3,066 of 5,078 AI skills overall, and #282 of 512 in Design & Media.

Installs

935

Downloads

3.6K

Stars

Overall Rank

#3,066

Top 61% overall · Top 56% in Design & Media

Platform	Installs	Downloads	Stars	Comments
ClawHub ↗	40	1.6K	1	-
SkillHub ↗	935	3.6K	8	—

Platforms count differently and update at different times.

What this skill does

From a script the user supplies it generates voiceover, images, and video clips, composites them into a final video, and can upload the result to Douyin. It triggers on requests to generate Douyin videos, folk story videos, horror story videos, or AI video production. Before publishing or sending content, show the final content and target to the user and obtain explicit confirmation. Treat credentials and private source data as sensitive.

Profile published 2026-10-27

What you can do with it

Turn a folk story script into a vertical video with voiceover.
Generate images for an existing horror story draft and composite the final cut.

When to use it

When you have the script and need a video quickly.
When producing folk story short videos in batches.

Example prompts

Generated from the skill’s documentation as examples; not results of actual runs.

Generate a Douyin video with voiceover and images from this folk story script.

Turn this story into a horror-style final cut and show me the shot list first.

Monthly Trend

Downloads3.6K

Stars8

The counting method changed in 2026-09: skills with the same name are now counted separately by author, and the full catalog is covered. Dashed lines show months before the change; they are not compared with later months, and no growth is computed across the change.

Month	Downloads	MoM	Stars
2026-09	3.6K	—	8
2026-08	3.1K	+7.0%	8
2026-07	2.9K	+13.5%	8
2026-06	2.5K	+11.1%	8
2026-05	2.3K	—	6
2026-03	1.4K	—	1

SKILL.md (original)

The author’s original file, shown as plain text without edits or review by AlphaMoat. Links are not clickable; check commands before running them. Fetched 2026-10-23.

2.9 KB · ClawHub v1.0.0

---
name: douyin-folklore-video
description: 抖音民间诡异故事视频生成器。根据用户提供的文案自动生成配音、图片、视频并合成最终视频，支持上传到抖音。触发词：生成抖音视频、民间故事视频、诡异故事视频、AI视频制作。
---

# 抖音民间诡异故事视频生成器

根据用户提供的文案，全自动生成抖音风格的民间诡异故事视频。

## 完整流程

Show all (117 lines)


### 1. 获取故事文案
- 必须使用用户提供的文案
- 保存到 `story.txt`

### 2. 生成配音
调用 `scripts/generate_voice.py`：
```bash
python scripts/generate_voice.py <故事文案> <输出目录>
```
- 输出：`voice.wav`
- 返回：配音时长（秒）

### 3. 生成图片
调用 `scripts/generate_images.py`：
```bash
python scripts/generate_images.py <故事文案> <输出目录>
```
- 根据故事生成 5-6 张图片
- 尺寸：720×1280
- 风格：dark horror comic style
- 保存：`img1.png` ~ `imgN.png`

### 4. 生成视频段
调用 `scripts/generate_videos.py`：
```bash
python scripts/generate_videos.py <图片URL列表> <输出目录>
```
- 每段 5 秒
- 按顺序推进（不回退）
- 保存：`v1.mp4` ~ `vN.mp4`

### 5. 视频拼接
```bash
ffmpeg -f concat -safe 0 -i list.txt -c copy video_raw.mp4
```

### 6. 生成同步字幕
调用 `scripts/generate_subtitle.py`：
```bash
python scripts/generate_subtitle.py <配音时长> <故事文案> <输出目录>
```
- 根据配音时长精确计算每句字幕时间
- 输出：`subtitle.srt`

### 7. 视频合成
```bash
# 加字幕
ffmpeg -i video_raw.mp4 -vf "scale=540:960,subtitles=subtitle.srt" -c:v libx264 -crf 23 -an video_sub.mp4

# 加音频
ffmpeg -i video_sub.mp4 -i voice.wav -c:v copy -c:a aac -map 0:v -map 1:a final_video.mp4
```

### 8. 发送给用户审核
用 message 工具发送 `final_video.mp4` 给用户。

### 9. 用户确认"发布"后上传抖音
使用 browser 工具：
- profile: openclaw
- 上传文件到 `C:\Users\SS\AppData\Local\Temp\openclaw\uploads\`
- 找到 `input[type=file]` 元素上传
- 填写标题、描述、话题
- 添加 AI 声明
- 点击发布

## 关键参数

| 参数 | 值 |
|------|-----|
| 配音模型 | qwen3-tts-flash |
| 图片模型 | wan2.6-t2i |
| 视频模型 | wan2.2-kf2v-flash |
| 图片尺寸 | 720×1280 |
| 视频分辨率 | 540×960 |
| 字幕字号 | 12 |
| 视频编码 | H264 |

## 配置信息

见 `references/config.md`：
- API Key
- FTP 服务器信息
- 浏览器配置

## 视频结构规则

**按顺序推进，不回退：**
```
v1: img1 → img2
v2: img2 → img3
v3: img3 → img4
v4: img4 → img5
...
```

**视频时长规则：**
- 配音时长 + 1~2秒 = 视频时长
- 每段视频固定 5 秒
- 根据配音时长计算需要多少段视频

## 注意事项

1. 字幕必须根据配音时长精确计算，确保同步
2. 视频要比配音长 1-2 秒
3. 上传抖音时必须添加 AI 声明
4. 用户确认"发布"后才能点发布按钮