← 返回 Skills 市场
mmyg11

Ai Video Gen Temp

作者 mmyg11 · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ⚠ suspicious
208
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install ai-video-gen-temp
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 contains working scripts for generating videos with third‑party APIs, but there are several inconsistencies and missing files that reduce confidence in the bundle's provenance. Before installing or running: 1) do not paste production API keys — create a throwaway key or isolated billing account for testing and rotate it afterwards; 2) inspect the code yourself (or have someone you trust do so), especially the API calls that send data to remote endpoints; 3) note SKILL.md and README reference files that are not included (.env.example, multi_scene.py, edit_video.py, examples/) and the metadata owner mismatch — treat the source as unverified; 4) be aware of cost/billing for calls to OpenAI/Runway/LumaAI/Replicate/ElevenLabs; 5) test in an isolated environment (container or VM), and if you decide to use it long-term, only enable the minimum required keys and monitor usage. If you want, I can list the exact places in code that send data to remote services and suggest minimal tests to validate behavior safely.
功能分析
Type: OpenClaw Skill Name: ai-video-gen-temp Version: 1.0.1 The skill bundle provides a legitimate set of tools for AI video generation using OpenAI, Replicate, and LumaAI APIs. The Python scripts (generate_video.py, add_voiceover.py, images_to_video.py) use standard libraries and safely invoke FFmpeg via subprocess lists to avoid shell injection. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
⚠ Purpose & Capability
The scripts implement an image→video→voice pipeline and legitimately need API keys for OpenAI, Replicate, LumaAI, Runway, and ElevenLabs. However, the registry metadata claims no required environment variables or credentials, which is inconsistent with the code and SKILL.md. The _meta.json owner also differs from the registry owner id, and SKILL.md/README reference files (e.g., .env.example, multi_scene.py, edit_video.py, examples/) that are not present in the bundle — these mismatches reduce trust in the package provenance.
⚠ Instruction Scope
SKILL.md instructs the agent to use external services (OpenAI, LumaAI, Replicate, ElevenLabs) and to read environment keys from a .env file — behavior consistent with the stated purpose. But SKILL.md references scripts that are missing from the repo (multi_scene.py, edit_video.py, examples/), and the LumaAI call in generate_video.py sends a local file path string in JSON ("image": image_path) rather than uploading file contents or a public URL, which looks buggy and could leak local path information to the remote API. The runtime instructions are otherwise focused on the task and do not instruct reading unrelated system files.
ℹ Install Mechanism
There is no install spec in the registry (instruction-only), but the bundle includes a requirements.txt listing common packages (openai, replicate, requests, pillow, python-dotenv). This is proportionate to the functionality and lower risk than arbitrary binary downloads, but you must pip install dependencies before running. No external download URLs or extract/install steps are present.
⚠ Credentials
The code expects multiple API credentials (OPENAI_API_KEY, REPLICATE_API_TOKEN, LUMAAI_API_KEY, RUNWAY_API_KEY, ELEVENLABS_API_KEY). Those credentials are proportionate to a multi-provider video tool, but the registry metadata declared 'no required env vars' which is inaccurate. Because the skill will call external services, providing keys grants networked access to those services (and billing), so keys should be limited and rotated if used for testing.
✓ Persistence & Privilege
The skill does not request persistent system privileges, does not set always:true, and does not attempt to modify other skills or global agent configs. It runs as command-line scripts and uses ordinary filesystem operations (temporary filelist.txt), which is expected for its purpose.
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-temp
  3. 安装完成后，直接呼叫该 Skill 的名称或使用 /ai-video-gen-temp 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
v1.0.1
- Skill name changed to "ai-video-gen-local" in documentation. - No changes to functionality or usage instructions. - Updated SKILL.md to reflect the new name; other content unchanged.
v1.0.0
- Initial release of AI Video Generation skill. - Generate complete videos from text prompts using image generation, video synthesis, voice-over, and editing. - Supports multiple models and APIs: DALL-E, Stable Diffusion, LumaAI, Runway, ElevenLabs, and Replicate. - Includes scripts for end-to-end video creation, image-to-video conversion, voiceover addition, and multi-scene assembly. - Provides setup instructions, API key requirements, and usage examples for various workflows.
元数据
Slug ai-video-gen-temp
版本 1.0.1
许可证 MIT-0
累计安装 1
当前安装数 1
历史版本数 2
常见问题

Ai Video Gen Temp 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 208 次。

如何安装 Ai Video Gen Temp？

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

Ai Video Gen Temp 是免费的吗？

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

Ai Video Gen Temp 支持哪些平台？

Ai Video Gen Temp 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 Temp？

由 mmyg11（@mmyg11）开发并维护，当前版本 v1.0.1。

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...
⬇ 463368 · 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.
⬇ 259467 · 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...
⬇ 200457 · 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.
⬇ 191163 · by steipete
ontology
Typed knowledge graph for structured agent memory and composable skills. Use when creating/querying entities (Person, Project, Task, Event, Document), linkin...
⬇ 190189 · by oswalpalash

💬 留言讨论