Token导航 LogoToken导航TokenDH.com
开发敏感数据clawhub未标认证来源可访问clear审计提醒

auto-video-creator自动视频创建者

Agent Skill

用于辅助视频生成、动画合成、脚本化剪辑或 Remotion 等视频项目开发。它适合让 Agent 组织镜头、生成素材说明、维护合成代码或排查渲染问题。使用时需要确认分辨率、时长、素材路径和导出格式;涉及外部素材、人物肖像或商业发布时,应先核对版权授权和内容审核要求。

总安装

9,267

周安装

394

GitHub Stars

公开资料未说明

下载量

3,247
OpenClaw

安装说明

本站只整理中文说明和来源信息,不托管安装包,也不代用户安装。

GitHub

来源数

2

许可证

MIT-0

最后核验

2026-05-01

来源状态

来源可访问

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:auto-video-creator(自动视频创建者)
来源仓库:https://github.com/yefl2064/auto-video-creator
安装命令:
openclaw skills install auto-video-creator
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install auto-video-creator

简介

使用 XLXAI Sora2 API 的人工智能视频生成器。在几秒钟内根据文本提示或图像创建专业视频。

SKILL.md

name
auto-video-creator
description
AI-powered video generator using XLXAI Sora2 API. Create professional videos from text prompts or images in seconds.

Auto Video Creator - XLXAI Video Generation Skill

Generate professional videos from text prompts or images using the XLXAI Sora2 API.

Scope

This skill focuses exclusively on video generation:

  • ✅ Calls XLXAI Sora2 API to generate videos
  • ✅ Returns task/result JSON with video URL upon completion
  • ✅ Supports text-to-video and image-to-video generation
  • ❌ Does NOT upload, post, or proxy videos to TikTok or other platforms
  • ❌ Does NOT handle social media publishing

For upload/post functionality, use a separate skill (e.g., post-to-tiktok-getlate) or downstream workflow.

Quick Start

1. Setup Environment

cp skills/xlxai-video/.env.example skills/xlxai-video/.env
# Edit skills/xlxai-video/.env and set XLXAI_API_KEY
export XLXAI_API_KEY="$YOUR_KEY"

2. Generate Video

python3 skills/xlxai-video/scripts/generate_video.py "Your video prompt here" --model sora2-portrait-4s

The script loads the API key from the XLXAI_API_KEY environment variable, handles task creation and polling, and returns JSON with the video URL when complete.

API Response Examples

Task Creation Response (no-wait)

{
  "task_id": "task_Ue8FsGswnj3fCaY91yAj84m8AA8lLVpm",
  "status": "pending",
  "model": "sora2-portrait-4s",
  "created_at": "2026-03-03T18:19:30Z"
}

Completed Task Response

{
  "task_id": "task_Ue8FsGswnj3fCaY91yAj84m8AA8lLVpm",
  "status": "completed",
  "video_url": "https://api.xlxai.store/video2-proxy/base/video/79193b56b4792daec07c5564bff412f193a6c20e5ee7ca0a323ab753da2420a9.mp4",
  "progress": 100,
  "duration": 38,
  "message": "Generation complete",
  "created_at": "2026-03-03T18:19:30Z",
  "completed_at": "2026-03-03T18:20:08Z"
}

Notes:

  • Field names depend on XLXAI API version; inspect raw JSON for actual fields
  • video_url may point to third-party CDN; download and self-host if needed

Video Models

Choose based on your needs:

Portrait Models (Vertical Videos)

  • sora2-portrait-4s — 4-second vertical video (default)
  • sora2-portrait-8s — 8-second vertical video
  • sora2-portrait-12s — 12-second vertical video

Landscape Models (Horizontal Videos)

  • sora2-landscape-4s — 4-second horizontal video
  • sora2-landscape-8s — 8-second horizontal video
  • sora2-landscape-12s — 12-second horizontal video

Default: sora2-portrait-4s

Usage Patterns

Text-to-Video Generation

Generate videos from text descriptions:

python3 scripts/generate_video.py "A 30-year-old American man in a suit presenting to camera" \
  --model sora2-landscape-8s

Image-to-Video Generation

Create videos from images with motion (local images auto-converted to data URI):

python3 scripts/generate_video.py "Man showcasing the suit, saying it's well-made and affordable" \
  --model sora2-portrait-4s \
  --image "/path/to/local/image.jpg"

Or use image URLs directly:

python3 scripts/generate_video.py "Man showcasing the suit, saying it's well-made and affordable" \
  --model sora2-portrait-4s \
  --image "http://example.com/image.jpg"

Non-blocking Task Creation

Get task ID immediately without waiting for completion:

python3 scripts/generate_video.py "Your prompt" --no-wait

Check status later:

python3 scripts/generate_video.py --check-status task_abc123

Script Options

OptionDescriptionDefault
--modelVideo model (portrait/landscape, 4s/8s/12s)sora2-portrait-4s
--imageImage URL or local file path
--no-waitReturn task ID immediatelyfalse
--poll-intervalSeconds between status checks10
--timeoutMax seconds to wait for completion600
--check-statusCheck status of existing task

Output Format

On success, the script returns JSON with:

  • status: "completed"
  • video_url: Download link for the generated video
  • progress: 100
  • duration: Generation time in seconds
  • task_id: Unique task identifier
  • created_at: Task creation timestamp
  • completed_at: Task completion timestamp

Error Handling

The script handles:

  • ✅ API request failures with retry logic
  • ✅ Timeout after 600 seconds (configurable)
  • ✅ Progress reporting during generation
  • ✅ Clear error messages for failed tasks
  • ✅ HTTP status code validation

Important Notes

  • Copyright & Rights: Verify copyright and portrait rights before publishing generated content
  • API Key Security: Keep your API key secret; use environment variables in production
  • Video URL: May point to third-party CDN; download and self-host if needed
  • Rate Limits: Check XLXAI API documentation for rate limiting

日本語ガイド

セットアップ

cp skills/xlxai-video/.env.example skills/xlxai-video/.env
export XLXAI_API_KEY="$YOUR_KEY"

ビデオ生成

python3 skills/xlxai-video/scripts/generate_video.py "あなたのプロンプト" --model sora2-portrait-4s

画像からビデオを生成

python3 skills/xlxai-video/scripts/generate_video.py "シーンの説明" --image "/path/to/image.jpg"

한국어 가이드

설정

cp skills/xlxai-video/.env.example skills/xlxai-video/.env
export XLXAI_API_KEY="$YOUR_KEY"

비디오 생성

python3 skills/xlxai-video/scripts/generate_video.py "당신의 프롬프트" --model sora2-portrait-4s

이미지에서 비디오 생성

python3 skills/xlxai-video/scripts/generate_video.py "장면 설명" --image "/path/to/image.jpg"

Contact / 連絡先 / 연락처

适合场景

01

OpenClaw 用户查找和安装 Skill 时

02

用户想查找某类 Agent Skill 时

03

需要根据任务场景推荐可安装能力包时

04

需要对比不同来源的安装命令和来源信息时

能力概览

能力 1

按任务关键词查找相关 Skills

能力 2

展示可复制的安装命令

能力 3

保留来源站点、仓库和原始说明,方便继续核验

能力 4

补充不同宿主或平台的使用分布数据

能力 5

展示第三方安全扫描或审计结果

安装后应在对应宿主中按原始 README 的触发条件使用;具体调用方式请以来源页面和 README 为准。

平台分布

OpenClaw

70.47%
按下载量换算2,288

安全审计

VirusTotal

通过

ClawScan

可疑

Static analysis

通过

权限和风险

敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在 warning/failed 结果,不能写成本站确认安全。当前只有一个来源,正式发布前建议补源仓库或其他目录站核验。

来源信息

继续浏览同类 Skills