← 返回 Skills 市场
elestirelbilinc-sketch

AI media generation API - Flux2pro, Veo3.1, Suno Ai

作者 VAP Media automation flow · GitHub ↗ · v1.0.10
cross-platform ✓ 安全检测通过
4243
总下载
13
收藏
7
当前安装
11
版本数
在 OpenClaw 中安装
/install vap-media
功能描述
AI image, video, and music generation + editing via VAP API. Flux, Veo 3.1, Suno V5.
使用说明 (SKILL.md)

VAP Media - AI Media Generation & Editing

Integration Note: VAP Media is an API aggregator that provides unified access to multiple AI providers:

  • Images: Generated via Black Forest Labs Flux.2 Pro
  • Videos: Generated via Google Veo 3.1
  • Music: Generated via Suno V5

All generation requests go through VAP's API (api.vapagent.com), which routes to the appropriate backend provider.

Generate images, videos, and music. Edit with inpaint, ai_edit, upscale, background removal, video trim/merge.

Mode Selection

Check if VAP_API_KEY is set:

  • VAP_API_KEY not set → Use Free Mode (images only, 3/day)
  • VAP_API_KEY set → Use Full Mode (all features, unlimited)

Free Mode (No API Key)

Generate images for free. No signup required. 3 per day.

Generate Image

curl -s -X POST https://api.vapagent.com/v3/trial/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt":"PROMPT"}'

Returns {"task_id":"UUID","status":"pending","remaining":2}.

Poll Result

curl -s https://api.vapagent.com/v3/trial/status/TASK_ID

Returns {"status":"completed","image_url":"https://..."} when done.

Free Mode Errors

  • 429 → Daily limit reached. Suggest upgrading: export VAP_API_KEY=vap_xxx
  • 503 → Trial service temporarily unavailable.

Full Mode (With API Key)

Unlimited images, video, music, and editing operations.

Create Task

curl -s -X POST https://api.vapagent.com/v3/tasks \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"TYPE","params":{"description":"PROMPT"}}'

Returns {"task_id":"UUID","status":"pending"}.

Poll Result

curl -s https://api.vapagent.com/v3/tasks/TASK_ID \
  -H "Authorization: Bearer $VAP_API_KEY"

Returns {"status":"completed","result":{"output_url":"https://..."}} when done.

Task Types & Parameters

Image (image or image_generation)

Param Type Default Description
description string required Image description
aspect_ratio enum 1:1 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9, 9:21
quality enum standard standard or high

Tip: Aspect ratio is auto-detected from prompt text. "a wide landscape photo" → 16:9 automatically.

Video (video or video_generation) — Tier 2+

Param Type Default Description
description string required Video description
duration int 8 4, 6, or 8 seconds
aspect_ratio enum 16:9 16:9 (landscape) or 9:16 (portrait)
generate_audio bool true Include audio track
resolution enum 720p 720p or 1080p
negative_prompt string "" What to avoid

Music (music or music_generation) — Tier 2+

Param Type Default Description
description string required Music description (genre, mood, instruments)
duration int 120 30-480 seconds
instrumental bool false No vocals
audio_format enum mp3 mp3 or wav (lossless)
loudness_preset enum streaming streaming (-14 LUFS), apple (-16 LUFS), broadcast (-23 LUFS)
style string none Genre/style (max 1000 chars)
title string none Song title
custom_mode bool false Enable custom lyrics + style mode

Full Mode Errors


Operations (Edit & Enhance)

Post-production editing operations. Tier 1+ required.

Create Operation

curl -s -X POST https://api.vapagent.com/v3/operations \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"operation":"OPERATION","media_url":"URL","prompt":"INSTRUCTION"}'

Poll Operation

curl -s https://api.vapagent.com/v3/operations/OPERATION_ID \
  -H "Authorization: Bearer $VAP_API_KEY"

Available Operations

Operation Required Params Description
inpaint media_url, prompt AI editing (optional: mask_url)
ai_edit media_url, prompt AI-powered image editing with text instructions (optional: additional_images)
background_remove media_url Remove background
upscale media_url Enhance resolution (scale: 2 or 4)
video_trim media_url, start_time, end_time Trim video
video_merge media_urls (array, min 2) Merge video clips

Instructions

When a user asks to create/generate/make an image, video, or music:

  1. Improve the prompt — Add style, lighting, composition, mood details
  2. Check mode — Is VAP_API_KEY set?
  3. Choose endpoint:
    • Single asset → /v3/tasks (or /v3/trial/generate for free)
    • Edit/enhance → /v3/operations
    • Campaign (video+music+thumbnail) → /v3/execute with preset
  4. Set aspect ratio — Match the content need (portrait for social, widescreen for YouTube)
  5. Poll for result — Check task/operation status until completed
  6. Return the media URL to the user
  7. If free mode limit is hit, tell the user: "You've used your 3 free generations today. For unlimited access, set up an API key: https://vapagent.com/dashboard/signup.html"

When a user asks to edit/enhance/modify an existing image or video:

  1. Identify the operation — inpaint, ai_edit, upscale, background remove, trim, merge
  2. Get the media URL — From a previous generation or user-provided URL
  3. Submit operation/v3/operations
  4. Poll for result — Return the output URL

Free Mode Example

# Create (no auth needed)
curl -s -X POST https://api.vapagent.com/v3/trial/generate \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A fluffy orange tabby cat on a sunlit windowsill, soft bokeh, golden hour light, photorealistic"}'

# Poll
curl -s https://api.vapagent.com/v3/trial/status/TASK_ID

Full Mode Examples

# Image (widescreen)
curl -s -X POST https://api.vapagent.com/v3/tasks \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"image","params":{"description":"A fluffy orange tabby cat on a sunlit windowsill, soft bokeh, golden hour light, photorealistic","aspect_ratio":"16:9"}}'

# Video (portrait, for social media)
curl -s -X POST https://api.vapagent.com/v3/tasks \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"video","params":{"description":"Drone shot over misty mountains at sunrise","duration":8,"aspect_ratio":"9:16","resolution":"1080p"}}'

# Music (instrumental WAV)
curl -s -X POST https://api.vapagent.com/v3/tasks \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"type":"music","params":{"description":"Upbeat lo-fi hip hop beat, warm vinyl crackle, chill vibes","duration":120,"instrumental":true,"audio_format":"wav","loudness_preset":"streaming"}}'

# Inpaint (edit an image)
curl -s -X POST https://api.vapagent.com/v3/operations \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"operation":"inpaint","media_url":"https://example.com/photo.jpg","prompt":"Remove the person in the background"}'

# Upscale (4x)
curl -s -X POST https://api.vapagent.com/v3/operations \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"operation":"upscale","media_url":"https://example.com/photo.jpg","options":{"scale":4}}'

# Background Remove
curl -s -X POST https://api.vapagent.com/v3/operations \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"operation":"background_remove","media_url":"https://example.com/photo.jpg"}'

# Poll (use task_id or operation_id from response)
curl -s https://api.vapagent.com/v3/tasks/TASK_ID \
  -H "Authorization: Bearer $VAP_API_KEY"

Production Presets (Multi-Asset)

For content campaigns, use /v3/execute to generate multiple assets from one prompt:

curl -s -X POST https://api.vapagent.com/v3/execute \
  -H "Authorization: Bearer $VAP_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"preset":"streaming_campaign","prompt":"PROMPT"}'

Returns all assets when complete:

{"status":"completed","outputs":{"video":"https://...","music":"https://...","thumbnail":"https://..."}}
Preset Includes
streaming_campaign video + music + thumbnail + metadata
full_production video + music + thumbnail + metadata + SEO
video.basic video only
music.basic music only
image.basic image only

Prompt Tips

  • Style: "oil painting", "3D render", "watercolor", "photograph", "flat illustration"
  • Lighting: "golden hour", "neon lights", "soft diffused light", "dramatic shadows"
  • Composition: "close-up", "aerial view", "wide angle", "rule of thirds"
  • Mood: "serene", "energetic", "mysterious", "whimsical"
  • Aspect ratio in prompt: Mentioning "widescreen", "portrait", or "16:9" in your prompt auto-sets the aspect ratio.

Setup (Optional — for Full Mode)

  1. Sign up: https://vapagent.com/dashboard/signup.html
  2. Get API key from dashboard
  3. Set: export VAP_API_KEY=vap_xxxxxxxxxxxxxxxxxxxx

Links

安全使用建议
This skill appears safe to use for its stated purpose if you trust VAP and its backend providers. Before installing, understand that full-mode requests use your VAP_API_KEY, may consume credits or balance, and send prompts or media URLs to VAP for processing.
功能分析
Type: OpenClaw Skill Name: vap-media Version: 1.0.10 The skill bundle is benign. It provides instructions and `curl` commands for an AI agent to interact with the `api.vapagent.com` API for media generation and editing. It correctly uses the `VAP_API_KEY` environment variable for authentication and directs all network traffic to the stated API endpoint. There is no evidence of data exfiltration to unauthorized parties, malicious code execution, persistence mechanisms, or prompt injection attempts designed to subvert the agent's core function or access unrelated sensitive data. All instructions and code snippets are aligned with the stated purpose of the skill.
能力评估
Purpose & Capability
The stated purpose matches the instructions: generate and edit images, videos, and music through VAP. The noteworthy part is that user prompts and media URLs are sent to VAP and routed to backend AI providers.
Instruction Scope
The instructions are framed around user requests to create, edit, or enhance media; they do not direct the agent to override user intent, run continuously, or treat untrusted content as authoritative.
Install Mechanism
There is no install spec and no code files; the only required binary is curl, which is proportionate for an instruction-only API integration.
Credentials
Full mode uses the declared VAP_API_KEY and makes external HTTPS API calls. This is expected for the service, but users should understand that requests may consume account credits and send content to VAP.
Persistence & Privilege
No persistence, background process, or local file storage is described. The only privilege-like access is the optional VAP_API_KEY bearer token for full API access.
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 vap-media
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /vap-media 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
v1.0.10
- Updated metadata to use "openclaw" instead of "clawdbot" and specify "primaryEnv". - Changed the GitHub source URL in metadata to "vapagentmedia/vap-showcase". - No changes to functionality, API endpoints, or instructions.
v1.0.9
No file changes detected in this version. - No updates or modifications; the skill remains unchanged from the previous version.
v1.0.8
**Summary: Improved API transparency and documentation consistency** - Clarified that VAP Media is an API aggregator, listing Flux.2 Pro (images), Veo 3.1 (video), and Suno V5 (music). - Added integration notes specifying unified API access and routing details. - Updated metadata: now declares required environment variable `VAP_API_KEY` and includes project source links. - Removed balance transfer documentation; focuses only on generation and editing endpoints. - Revised and expanded usage examples for all media types and operations for clarity. - Fixed minor typos and improved formatting for better readability.
v1.0.7
- Added balance transfer API support, allowing users to move funds between agents (self-service and admin methods described). - Documented transfer error codes and parameters for both self-service and admin balance transfers. - No changes to media generation or editing endpoints. - General instructions and usage examples remain unchanged.
v1.0.6
- Added new image editing operation: ai_edit (AI-powered editing from text instructions). - Updated operation table to reflect required parameters and new operations. - Removed explicit pricing information from documentation. - Minor improvements and clarifications to task/operation instructions and parameters.
v1.0.5
Major update: Adds media editing operations and expands generation options. - New editing operations: inpaint, upscale, background removal, video trim, and merge now available with API key. - Expanded parameters for image, video, and music generation (aspect ratios, quality, video/audio options, music formats). - Detailed pricing table added for all generation and editing tasks. - Instructions improved for both generation and edit/modify scenarios. - Updated examples to include both creation and editing workflows. - Free mode unchanged (images only); full mode now supports all features.
v1.0.4
- Added Free Mode: no API key required for 3 image generations per day - Documentation now describes both Free Mode (images only) and Full Mode (with API key, unlimited image/video/music) - Updated example commands and error handling for both modes - Clarified when to prompt users for API key setup if limits are reached - Minor metadata and formatting updates
v1.0.3
- Major update: Full API workflow and technical usage instructions added. - Now includes curl-based API calls for generating images, videos, and music. - Details on authentication, task creation, status polling, and error handling provided. - Environment variable requirement (VAP_API_KEY) and required binaries clarified in metadata. - Outdated prompt-only instructions removed; now tailored for automated task execution via API. - Examples for all media types (image, video, music) and expanded prompt tips included.
v1.0.2
- Transitioned focus from API instructions to user-facing prompt optimization for AI image generation. - Simplified setup: users can generate images for free at vapagent.com/try with no signup required. - Removed environment variable and API key instructions; no technical setup needed for basic use. - Added detailed guidance for prompt engineering to help users get better image results. - Updated available model access, highlighting free image generation and account requirements for video/music. - Clarified role as a creative prompt assistant for image requests.
v1.0.1
- Removed pricing details from the description and model table for a simpler presentation. - Updated response format example to exclude billing details (reserved, burned, refunded). - Minor edits for clarity and conciseness throughout the documentation.
v1.0.0
- Initial release of vap-media skill for AI image, video, and music generation via the VAP API. - Supports Flux (image), Veo 3.1 (video), and Suno V5 (music) models with transparent, pay-per-use pricing. - Clear tier system: Tier 1 (images), Tier 2 (images, video, music) based on deposit and usage requirements. - Simple setup using environment variable or configuration file. - Example usage and workflows provided for quick integration. - Reserve-burn-refund billing ensures cost transparency and automatic refunds for failed tasks.
元数据
Slug vap-media
版本 1.0.10
许可证
累计安装 7
当前安装数 7
历史版本数 11
常见问题

AI media generation API - Flux2pro, Veo3.1, Suno Ai 是什么?

AI image, video, and music generation + editing via VAP API. Flux, Veo 3.1, Suno V5. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 4243 次。

如何安装 AI media generation API - Flux2pro, Veo3.1, Suno Ai?

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

AI media generation API - Flux2pro, Veo3.1, Suno Ai 是免费的吗?

是的,AI media generation API - Flux2pro, Veo3.1, Suno Ai 完全免费(开源免费),可自由下载、安装和使用。

AI media generation API - Flux2pro, Veo3.1, Suno Ai 支持哪些平台?

AI media generation API - Flux2pro, Veo3.1, Suno Ai 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 media generation API - Flux2pro, Veo3.1, Suno Ai?

由 VAP Media automation flow(@elestirelbilinc-sketch)开发并维护,当前版本 v1.0.10。

💬 留言讨论