← 返回 Skills 市场
onlyloveher

AI Video Gen CN

作者 onlyloveher · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
126
总下载
0
收藏
1
当前安装
1
版本数
在 OpenClaw 中安装
/install ai-video-gen-cn
功能描述
End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Re...
使用说明 (SKILL.md)

AI Video Generation Skill

Generate complete videos from text descriptions using AI.

Capabilities

  1. Image Generation - DALL-E 3, Stable Diffusion, Flux
  2. Video Generation - LumaAI, Runway, Replicate models
  3. Voice-over - OpenAI TTS, ElevenLabs
  4. Video Editing - FFmpeg assembly, transitions, overlays

Quick Start

# Generate a complete video
python skills/ai-video-gen/generate_video.py --prompt "A sunset over mountains" --output sunset.mp4

# Just images to video
python skills/ai-video-gen/images_to_video.py --images img1.png img2.png --output result.mp4

# Add voiceover
python skills/ai-video-gen/add_voiceover.py --video input.mp4 --text "Your narration" --output final.mp4

Setup

Required API Keys

Add to your environment or .env file:

# Image Generation (pick one)
OPENAI_API_KEY=sk-...              # DALL-E 3
REPLICATE_API_TOKEN=r8_...         # Stable Diffusion, Flux

# Video Generation (pick one)
LUMAAI_API_KEY=luma_...           # LumaAI Dream Machine
RUNWAY_API_KEY=...                # Runway ML
REPLICATE_API_TOKEN=r8_...        # Multiple models

# Voice (optional)
OPENAI_API_KEY=sk-...             # OpenAI TTS
ELEVENLABS_API_KEY=...            # ElevenLabs

# Or use FREE local options (no API needed)

Install Dependencies

pip install openai requests pillow replicate python-dotenv

FFmpeg

Already installed via winget.

Usage Examples

1. Text to Video (Full Pipeline)

python skills/ai-video-gen/generate_video.py \
  --prompt "A futuristic city at night with flying cars" \
  --duration 5 \
  --voiceover "Welcome to the future" \
  --output future_city.mp4

2. Multiple Scenes

python skills/ai-video-gen/multi_scene.py \
  --scenes "Morning sunrise" "Busy city street" "Peaceful night" \
  --duration 3 \
  --output day_in_life.mp4

3. Image Sequence to Video

python skills/ai-video-gen/images_to_video.py \
  --images frame1.png frame2.png frame3.png \
  --fps 24 \
  --output animation.mp4

Workflow Options

Budget Mode (FREE)

  • Image: Stable Diffusion (local or free API)
  • Video: Open source models
  • Voice: OpenAI TTS (cheap) or free TTS
  • Edit: FFmpeg

Quality Mode (Paid)

  • Image: DALL-E 3 or Midjourney
  • Video: Runway Gen-3 or LumaAI
  • Voice: ElevenLabs
  • Edit: FFmpeg + effects

Scripts Reference

  • generate_video.py - Main end-to-end generator
  • images_to_video.py - Convert image sequence to video
  • add_voiceover.py - Add narration to existing video
  • multi_scene.py - Create multi-scene videos
  • edit_video.py - Apply effects, transitions, overlays

API Cost Estimates

  • DALL-E 3: ~$0.04-0.08 per image
  • Replicate: ~$0.01-0.10 per generation
  • LumaAI: $0-0.50 per 5sec (free tier available)
  • Runway: ~$0.05 per second
  • OpenAI TTS: ~$0.015 per 1K characters
  • ElevenLabs: ~$0.30 per 1K characters (better quality)

Examples

See examples/ folder for sample outputs and prompts.

安全使用建议
This package implements the advertised video, image, and TTS flows and will call external services (OpenAI, Replicate, LumaAI, etc.). Before installing or providing API keys: 1) Confirm which API keys you must supply — the bundle is inconsistent (SKILL.md, README, and skill.yaml disagree). Provide only the minimum keys you trust. 2) Inspect the code locally (generate_video.py, add_voiceover.py) to verify endpoints and behavior; these scripts perform network calls and write files. 3) Run first in an isolated environment (VM or container) and with test/limited API keys to avoid unexpected charges or data exposure. 4) Note missing referenced files (multi_scene.py, edit_video.py, examples/) and placeholder LumaAI request logic — the Luma call may not be a correct/complete integration. 5) Ensure FFmpeg on your system is a trusted binary because the scripts invoke it. If you are not comfortable auditing the code or if the source is unknown/untrusted, avoid supplying production API keys.
功能分析
Type: OpenClaw Skill Name: ai-video-gen-cn Version: 1.0.0 The skill bundle provides a legitimate end-to-end AI video generation pipeline using OpenAI, Replicate, LumaAI, and FFmpeg. The Python scripts (generate_video.py, add_voiceover.py, images_to_video.py) use standard libraries and subprocess calls to handle media processing as described in the documentation, with no evidence of data exfiltration, malicious execution, or prompt injection.
能力评估
ℹ Purpose & Capability
Name/description, SKILL.md, and the Python scripts align: the code implements image generation, video synthesis (via LumaAI placeholder), TTS (OpenAI), and FFmpeg editing. However, registry metadata earlier claimed 'Required env vars: none' while the SKILL.md, README.md, and scripts rely on multiple API keys. Also skill.yaml only declares OPENAI_API_KEY and REPLICATE_API_KEY but the runtime uses LUMAAI_API_KEY, RUNWAY_API_KEY, and ELEVENLABS_API_KEY as well. These mismatches between declared requirements and actual code are concerning because they obscure what sensitive data the skill will require.
ℹ Instruction Scope
SKILL.md instructions remain within the stated purpose: they show how to run scripts, set API keys, install dependencies, and use FFmpeg. The code reads .env, invokes network APIs (OpenAI, Replicate, LumaAI endpoints), writes image/audio/video files to disk, and calls ffmpeg via subprocess. Nothing in the instructions asks the agent to read unrelated system files or exfiltrate arbitrary data. Concerns: SKILL.md and README reference additional scripts (multi_scene.py, edit_video.py, examples/ folder) that are not present in the package — this inconsistency could confuse users or hide intended flows. The LumaAI call in generate_video.py is implemented as a placeholder that uploads a local path as JSON; if left unmodified it may not work as intended.
✓ Install Mechanism
No binary download/install spec is embedded in the skill bundle. It's instruction-only for installation (pip install -r requirements.txt) and includes requirements.txt. No remote, arbitrary archive downloads or obscure install URLs are used. The only potentially risky external dependency is the requirement to have FFmpeg available (invoked via subprocess), but this is expected for video tooling.
⚠ Credentials
The environment variables the code uses (OPENAI_API_KEY, REPLICATE_API_TOKEN, LUMAAI_API_KEY, RUNWAY_API_KEY, ELEVENLABS_API_KEY) are appropriate for video/image/voice generation, so their presence is proportionate to the feature set. The concern is inconsistency in where those variables are declared: registry metadata lists none, skill.yaml only declares two, SKILL.md lists several. This mismatch makes it unclear which secrets the skill will actually read and whether the platform will surface prompts to provide them. Before providing keys, users should confirm which keys are actually required and whether keys will be persisted anywhere.
✓ Persistence & Privilege
The skill does not request elevated or persistent platform privileges (always: false). It does not modify other skills' configuration nor request system-wide changes. It runs as ordinary user code, writing generated media files to the current working directory.
如何使用
  1. 确保已安装 OpenClaw（本地或 Docker 部署）
  2. 在对话框中输入安装命令：/install ai-video-gen-cn
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /ai-video-gen-cn 触发
  4. 根据 Skill 的参数说明提供必要输入，即可获得结构化输出
版本历史
v1.0.0
Initial release with CN suffix
元数据
Slug ai-video-gen-cn
版本 1.0.0
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 1
常见问题

AI Video Gen CN 是什么？

End-to-end AI video generation - create videos from text prompts using image generation, video synthesis, voice-over, and editing. Supports OpenAI DALL-E, Re... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 126 次。

如何安装 AI Video Gen CN？

在 OpenClaw 或 Claude Code 对话框中运行命令「/install ai-video-gen-cn」即可一键安装，无需额外配置。

AI Video Gen CN 是免费的吗？

是的，AI Video Gen CN 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。

AI Video Gen CN 支持哪些平台？

AI Video Gen CN 跨平台运行，可在任意部署了 OpenClaw / Claude Code 的环境中使用（cross-platform）。

谁开发了 AI Video Gen CN？

由 onlyloveher（@onlyloveher）开发并维护，当前版本 v1.0.0。

推荐 Skills
self-improving agent
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Clau...
⬇ 463815 · by pskoett
Skill Vetter
Security-first skill vetting for AI agents. Use before installing any skill from ClawdHub, GitHub, or other sources. Checks for red flags, permission scope, and suspicious patterns.
⬇ 259802 · by spclaudehome
Polymarket
Query Polymarket prediction markets. Check odds, find trending markets, search events, track price movements.
⬇ 232503 · by joelchance
Self-Improving + Proactive Agent
Self-reflection + Self-criticism + Self-learning + Self-organizing memory. Agent evaluates its own work, catches mistakes, and improves permanently. Use when...
⬇ 200680 · by ivangdavila
Github
Interact with GitHub using the `gh` CLI. Use `gh issue`, `gh pr`, `gh run`, and `gh api` for issues, PRs, CI runs, and advanced queries.
⬇ 191345 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190333 · by oswalpalash

💬 留言讨论