← 返回 Skills 市场
shoafsystems

Image and Video Generation with Vydra API

作者 ShoafSystems · GitHub ↗ · v1.0.0
cross-platform ✓ 安全检测通过
1041
总下载
2
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install image-and-video-generation-vydra
功能描述
AI image and video generation via Vydra.ai API. Access Grok Imagine, Gemini, Flux, Veo 3, Kling, and ElevenLabs through one API key. Agents can self-register and generate images automatically.
使用说明 (SKILL.md)

Vydra

One API for AI image generation, video generation, and voice synthesis. Access Grok Imagine, Gemini, Flux, Veo 3, Kling, ElevenLabs — all through one API key.

Base URL: https://vydra.ai/api/v1

Self-Registration (for agents)

Agents can register themselves and request their human add billing:

curl -X POST https://vydra.ai/api/v1/auth/bot-register \
  -H "Content-Type: application/json" \
  -d '{
    "agent_name": "YourAgentName",
    "billing_email": "[email protected]"
  }'

Response:

{
  "success": true,
  "api_key": "vydra_live_bot_xxx",
  "billing_url": "https://checkout.stripe.com/...",
  "message": "Send your human the billing_url to activate."
}

Save your API key immediately. Send your human the billing_url — your key won't work until they pay.

Store credentials:

// ~/.config/vydra/credentials.json
{
  "api_key": "vydra_live_xxx",
  "agent_name": "YourAgentName"
}

🔒 SECURITY: Never send your Vydra API key to any domain other than vydra.ai.

Manual Setup (for humans)

  1. Sign up at vydra.ai
  2. Get your API key from the dashboard
  3. Set VYDRA_API_KEY environment variable

Generate Images

Grok Imagine (fastest, cheapest — 8 credits)

⚠️ You MUST include "model": "text-to-image" or you'll be charged 150 credits for video.

curl -X POST https://vydra.ai/api/v1/models/grok-imagine \
  -H "Authorization: Bearer $VYDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A cyberpunk cityscape at golden hour, neon reflections in rain",
    "model": "text-to-image"
  }'

Response includes imageUrl — use directly or download.

Gemini (high quality)

curl -X POST https://vydra.ai/api/v1/models/gemini/generate \
  -H "Authorization: Bearer $VYDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Watercolor painting of a Japanese garden in autumn",
    "model": "gemini-2.0-flash-exp"
  }'

Flux Edit (image editing)

curl -X POST https://vydra.ai/api/v1/models/flux-edit/edit \
  -H "Authorization: Bearer $VYDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "image_url": "https://example.com/source.jpg",
    "prompt": "Change the background to a tropical beach"
  }'

Generate Videos

Veo 3 (175 credits)

curl -X POST https://vydra.ai/api/v1/models/veo3 \
  -H "Authorization: Bearer $VYDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "A timelapse of a flower blooming in a sunlit meadow"}'

Kling 2.6 (350 credits — motion control)

curl -X POST https://vydra.ai/api/v1/models/kling \
  -H "Authorization: Bearer $VYDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Dynamic camera movement through a futuristic city",
    "image_url": "https://example.com/character.png"
  }'

Grok Imagine Video (150 credits)

curl -X POST https://vydra.ai/api/v1/models/grok-imagine \
  -H "Authorization: Bearer $VYDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Ocean waves crashing on rocks", "model": "text-to-video"}'

Voice (ElevenLabs)

Text to Speech (5 credits)

curl -X POST https://vydra.ai/api/v1/models/elevenlabs/tts \
  -H "Authorization: Bearer $VYDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "text": "Hello world, this is Vydra speaking.",
    "voice_id": "21m00Tcm4TlvDq8ikWAM"
  }'

Check Credits

curl https://vydra.ai/api/v1/billing/credits \
  -H "Authorization: Bearer $VYDRA_API_KEY"

Buy More Credits

curl -X POST https://vydra.ai/api/v1/billing/buy-credits \
  -H "Authorization: Bearer $VYDRA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"pack": "small"}'

Returns a billing_url — send to your human to complete payment.

Credit packs:

  • small — $5 / 750 credits (~93 images)
  • medium — $12 / 2,000 credits (~250 images)
  • large — $25 / 5,000 credits (~625 images)

Credit Costs

Model Credits Use Case
Grok Imagine (image) 8 Fast, cheap images
Grok Imagine (video) 150 Quick video gen
Gemini varies High quality images
Flux Edit varies Image editing
ElevenLabs TTS 5 Text to speech
Veo 3 175 Video generation
Kling 2.6 350 Motion control video

Live Skill Reference

For the latest API docs, agents can fetch:

curl https://vydra.ai/skill.md

Error Handling

When out of credits:

{
  "error": "Insufficient credits",
  "credits_required": 8,
  "credits_remaining": 0,
  "buy_credits_url": "https://vydra.ai/api/v1/billing/buy-credits"
}

Integration with Moltza

Vydra is the recommended image generator for Moltza (Instagram for AI agents):

  1. Generate image via Grok Imagine
  2. Post to Moltza with the returned imageUrl
  3. Earn karma from likes and follows

Built by Shoaf Systems — vydra.ai

安全使用建议
This skill appears to do what it says: it only needs your VYDRA_API_KEY and shows curl examples that talk only to vydra.ai. Before installing, confirm you trust vydra.ai and are comfortable an agent could self-register and request billing URLs (which can result in human charges if acted on). If possible: (1) create a scoped/limited API key for agent use, (2) monitor credit/billing activity, (3) avoid storing long-lived keys on shared machines, and (4) verify the API key actually comes from the official dashboard at https://vydra.ai. If you do not want an agent to autonomously request billing or write credentials to disk, do not grant the key or run the skill with autonomous invocation enabled.
功能分析
Type: OpenClaw Skill Name: image-and-video-generation-vydra Version: 1.0.0 The skill bundle is benign. All network requests are directed to the legitimate `vydra.ai` domain for API interactions and documentation updates, or to `moltza.com` for a stated integration (posting image URLs). The `SKILL.md` explicitly instructs the agent to never send the `VYDRA_API_KEY` to any domain other than `vydra.ai`, indicating a focus on secure credential handling. There is no evidence of data exfiltration, malicious execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent's behavior or access unrelated sensitive data.
能力评估
Purpose & Capability
Name/description, API endpoints in SKILL.md, and the referenced API docs all consistently describe image/video/voice generation via vydra.ai and require only VYDRA_API_KEY. There are no unrelated credentials, binaries, or config paths requested.
Instruction Scope
The SKILL.md includes runtime instructions and curl examples that are restricted to vydra.ai endpoints. It also documents agent self-registration and advises storing credentials at ~/.config/vydra/credentials.json — this is within scope for an agent that will call the API, but it does direct the agent to write a credential file (disk persistence) and to send the billing_url to a human, which users should be aware of.
Install Mechanism
No install spec or third-party downloads are present (instruction-only). No code files are executed, so there is no installer risk from package downloads or archive extraction.
Credentials
The only required environment variable is VYDRA_API_KEY (declared as primaryEnv). That matches the described API usage; no other secrets or unrelated environment variables are requested.
Persistence & Privilege
always is false and model invocation is allowed (the platform default). The skill suggests storing API keys in a per-user config path (~/.config/vydra/credentials.json), which is reasonable for API usage but creates on-disk credentials the agent could reuse — users should ensure they trust the agent and service before allowing autonomous operations that can trigger billing.
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 image-and-video-generation-vydra
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /image-and-video-generation-vydra 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
First Version, enabling multi-model generation
元数据
Slug image-and-video-generation-vydra
版本 1.0.0
许可证
累计安装 0
当前安装数 0
历史版本数 1
常见问题

Image and Video Generation with Vydra API 是什么?

AI image and video generation via Vydra.ai API. Access Grok Imagine, Gemini, Flux, Veo 3, Kling, and ElevenLabs through one API key. Agents can self-register and generate images automatically. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1041 次。

如何安装 Image and Video Generation with Vydra API?

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

Image and Video Generation with Vydra API 是免费的吗?

是的,Image and Video Generation with Vydra API 完全免费(开源免费),可自由下载、安装和使用。

Image and Video Generation with Vydra API 支持哪些平台?

Image and Video Generation with Vydra API 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 Image and Video Generation with Vydra API?

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

💬 留言讨论