← Back to Skills Marketplace
mendynew

lovart skill

by mendynew · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ⚠ suspicious
213
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install lovart
Description
与 Lovart.ai API 集成,生成 AI 设计、图片和视频。支持图像生成、图像编辑、视频创建和模板工作流。
README (SKILL.md)

Lovart AI Design Skill

该 Skill 与 Lovart.ai API 集成,提供强大的 AI 设计能力,包括图像生成、图像编辑、视频创建等功能。

功能特性

  • AI 图像生成:从文本描述生成高质量视觉内容
  • 图像增强:使用 AI 进行图像放大和优化
  • 视频生成:从图像或文本提示创建短视频
  • 模板库:访问平台提供的设计模板库
  • 多模型支持:支持 Flux、Stable Diffusion 等多种 AI 模型

触发词

当用户提到以下内容时,应触发此 Skill:

  • "使用 Lovart 生成设计"
  • "用 Lovart AI 创建图片"
  • "Lovart 设计"
  • "AI 设计生成"
  • "生成产品图片"
  • "创建营销素材"
  • "AI 视频生成"

API 配置

获取 API Key

  1. 访问 Lovart.ai
  2. 创建账户并登录
  3. 在账户设置中生成 API Key
  4. 将 API Key 保存到环境变量:LOVART_API_KEY

认证方式

所有 API 请求需要在 Authorization header 中包含 API Key:

Authorization: Bearer YOUR_API_KEY

API 端点

1. 生成设计

端点: POST /v1/design/generate

描述: 基于文本提示和参数生成 AI 驱动的设计

请求参数:

  • prompt (string): 设计描述文本
  • model (string, 可选): 使用的 AI 模型 (如 "flux", "stable-diffusion")
  • width (integer, 可选): 图像宽度
  • height (integer, 可选): 图像高度
  • style (string, 可选): 设计风格
  • template_id (string, 可选): 使用的模板 ID

响应:

  • id (string): 设计任务 ID
  • status (string): 任务状态 (pending/processing/completed)
  • result_url (string): 完成后的图像下载链接

2. 获取设计状态

端点: GET /v1/design/{id}

描述: 检查设计生成请求的状态

响应:

  • id (string): 设计任务 ID
  • status (string): 当前状态
  • progress (integer): 处理进度 (0-100)
  • result_url (string): 结果 URL(如果完成)

使用示例

示例 1: 生成产品图片

curl -X POST https://api.lovart.ai/v1/design/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A modern running shoe on a white background, professional product photography",
    "width": 1920,
    "height": 1080,
    "model": "flux"
  }'

示例 2: 创建营销海报

curl -X POST https://api.lovart.ai/v1/design/generate \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Summer sale promotional poster with vibrant colors and modern typography",
    "style": "marketing",
    "template_id": "template_123"
  }'

示例 3: 检查生成状态

curl -X GET https://api.lovart.ai/v1/design/{id} \
  -H "Authorization: Bearer YOUR_API_KEY"

最佳实践

提示词编写

  • 具体明确: 描述要详细,包括主体、风格、构图、光线等
  • 风格参考: 提及具体的设计风格或艺术家
  • 技术规格: 指定尺寸、格式等技术要求

好的提示词示例:

"A premium coffee product shot, top-down view, natural lighting,
wooden surface background, minimalist composition,
4K resolution, professional commercial photography"

错误处理

  • 检查 API Key 是否有效
  • 验证请求参数格式
  • 处理网络超时和重试逻辑
  • 监控配额使用情况

性能优化

  • 使用异步任务处理
  • 实现结果缓存
  • 批量请求合并处理

定价信息

  • 免费版: 有限配额,探索平台功能
  • Starter: $9/月,1200 快速积分
  • Basic: $29/月,更多积分和标准处理
  • Pro: $49/月,优先处理
  • Ultimate: $99/月,最高优先级

所有付费计划包含完整的商业使用权限。

支持与资源

常见问题

Q: 生成的图片可以商用吗? A: 是的,所有付费计划都包含完整的商业使用权限。

Q: 支持哪些文件格式? A: 支持 PNG、JPG 等常见图像格式,具体取决于生成参数。

Q: 可以批量生成吗? A: 是的,可以通过多个 API 调用实现批量生成。

Q: 如何处理长时间运行的任务? A: 使用异步任务模式,通过 /v1/design/{id} 端点轮询状态。

注意事项

⚠️ 安全提醒:

  • 永远不要在客户端代码中暴露 API Key
  • 始终通过后端服务器代理 API 请求
  • 定期轮换 API Key
  • 监控 API 使用情况以防止滥用

📋 使用限制:

  • 遵守 Lovart 服务条款
  • 尊重知识产权和版权
  • 不得生成非法或有害内容
Usage Guidance
This skill appears to do what it claims (calls Lovart.ai), but the package metadata is inconsistent. Before installing or using it: 1) Verify the source/owner (unknown origin). 2) Confirm you have and will supply LOVART_API_KEY as an environment variable — the skill and examples require it though the registry metadata omitted it. 3) Ensure the runtime environment includes curl and jq (examples.sh uses jq) or adjust examples accordingly. 4) Manually inspect SKILL.md and prompt.md for any hidden/strange unicode/control characters (the scanner flagged them). 5) Do not put your API key in client-side code; prefer a backend proxy as the skill itself recommends. If the owner/source cannot be validated or the metadata is not corrected, treat the skill with caution and avoid giving it sensitive, high-privilege credentials.
Capability Analysis
Type: OpenClaw Skill Name: lovart Version: 1.0.0 The skill bundle provides a legitimate integration with the Lovart.ai API for AI-driven image and video generation. It includes clear documentation, technical configuration, and example scripts (examples.sh, skill.md, prompt.md) that follow standard practices for API interaction, such as using environment variables for authentication. No evidence of malicious intent, data exfiltration, or suspicious execution was found.
Capability Assessment
Purpose & Capability
The skill's name/description, SKILL.md, prompt.md, config.json and examples.sh consistently describe a Lovart.ai image/video generation integration — that matches the stated purpose. However, the registry metadata claims no required environment variables or primary credential while the SKILL.md/config/examples clearly require LOVART_API_KEY. This metadata omission is incoherent and could lead to silent failures or misconfiguration.
Instruction Scope
Runtime instructions are scoped to calling Lovart API endpoints (POST /v1/design/generate, GET /v1/design/{id}) and handling task polling; they explicitly instruct using an API key in Authorization header and recommend backend proxying. There is nothing in the instructions that reads unrelated system files or exfiltrates data. However, a prompt-injection detection (unicode-control-chars) was found in SKILL.md/prompt.md — worth manual review to ensure no hidden control characters alter model behavior.
Install Mechanism
No install spec (instruction-only plus example script) — low installation risk. The skill does not download or extract external archives.
Credentials
Functionally the skill only needs a single service credential (LOVART_API_KEY), which is proportionate. But the top-level registry metadata lists no required env vars/primary credential while config.json, SKILL.md, prompt.md and examples.sh require LOVART_API_KEY. Also examples.sh calls jq (and curl), but the manifest's required binaries list is empty — undeclared runtime dependency. These inconsistencies reduce trust and need correction before use.
Persistence & Privilege
The skill does not request always:true or any elevated persistent privileges. It is user-invocable and allows normal autonomous invocation; nothing in the files attempts to modify other skills or system-wide settings.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install lovart
  3. After installation, invoke the skill by name or use /lovart
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
lovart 1.0.0 首次发布,集成 Lovart.ai API,实现强大 AI 设计生成能力。 - 支持 AI 图像生成、图像编辑、视频创作与模板工作流 - 多模型支持,包括 Flux 和 Stable Diffusion - 提供详细 API 文档与调用示例,方便开发集成 - 覆盖商业使用、定价与安全合规说明 - 包含实用提示词建议和错误处理最佳实践
Metadata
Slug lovart
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is lovart skill?

与 Lovart.ai API 集成,生成 AI 设计、图片和视频。支持图像生成、图像编辑、视频创建和模板工作流。 It is an AI Agent Skill for Claude Code / OpenClaw, with 213 downloads so far.

How do I install lovart skill?

Run "/install lovart" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is lovart skill free?

Yes, lovart skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does lovart skill support?

lovart skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created lovart skill?

It is built and maintained by mendynew (@mendynew); the current version is v1.0.0.

💬 Comments