← Back to Skills Marketplace
yuanweiphone

Spark Image

by yuanweiphone · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
53
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install spark-image
Description
提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。
README (SKILL.md)

Spark Image Skill 图片生成技能

文本生成图片服务,基于火山引擎图片生成 API。Base URL: https://image.open-idea.net/api/v1Authorization: Bearer \x3CKey>

Install

openclaw skills install spark-image

Setup

Privacy

图片生成时,提示词文本将发送至第三方服务 image.open-idea.net(火山引擎 API)。请勿上传敏感或保密内容。

Output

成功响应后对用户展示:业务正文(图片或生成结果)+ 计费行。

图片以 \x3Cimg src="data:image/png;base64,..."> 渲染给用户,或提供下载链接。若返回多张图,则逐张渲染。贴长 base64 原文。

计费行:

本次扣费: {charged} CNY, 余额: {balance} CNY

HTTP 头字段:X-Mengguyu-Billing-Charged · X-Mengguyu-Billing-Balance · X-Mengguyu-Billing-Currency

禁止对用户输出:完整 JSON、路由说明、模型名、token、Key 等内部信息。

Usage

生成图片

POST /image
Body: { "prompt": "描述文字", "width": 2048, "height": 2048, "style": "油画风格,厚涂笔触", "image_count": 1 }

响应:data.images[](1-4 张 base64 PNG)+ data.points_used

说明:

  • 当前公开接口仅支持 2K 及以上推荐尺寸组合。
  • image_count 支持 1-4
  • 多图请求会逐张生成并聚合返回,通常比单图耗时更长。

可用尺寸与点数

尺寸 点数
2048x2048 56
2304x1728 54
1728x2304 54
2848x1600 61
1600x2848 61
2496x1664 56
1664x2496 56
3136x1344 57

详见 IMAGE-GENERATION.mdHTTP-REQUESTS.md

references/

文件 用途
HTTP-REQUESTS.md 全接口 curl、计费头
IMAGE-GENERATION.md 图片生成详细说明
BEHAVIOR-RULES.md 行为规范、重试、确认
API-KEY.md Key 配置
Usage Guidance
Install only if you are comfortable sending image prompts to image.open-idea.net and paying for generated images. Keep IMAGE_GATEWAY_API_KEY out of chat logs, screenshots, shell history, and version control, and confirm the estimated cost before generation.
Capability Tags
requires-oauth-tokenrequires-sensitive-credentials
Capability Assessment
Purpose & Capability
The artifact consistently describes text-to-image generation through image.open-idea.net, including prompt submission, supported image counts and sizes, billing, and returned image handling.
Instruction Scope
Triggers include broad image and style phrases, but the runtime instructions require user confirmation and estimated cost disclosure before any billed API request.
Install Mechanism
Installation is a normal OpenClaw skill install and the artifact contains only markdown documentation, with no executable scripts or package dependencies.
Credentials
The required IMAGE_GATEWAY_API_KEY environment variable is proportionate for a third-party image API that uses bearer-token authentication.
Persistence & Privilege
No persistence, background execution, local indexing, destructive behavior, or privilege escalation is shown; the credential guidance is basic and users should store the key carefully.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install spark-image
  3. After installation, invoke the skill by name or use /spark-image
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial ClawHub publish.
Metadata
Slug spark-image
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is Spark Image?

提供图片生成能力:输入文本描述生成图片,可附加风格提示词。支持 1-4 张图片生成,按图片尺寸对应点数计费。Authorization 使用本系统发放的 Bearer Token。 It is an AI Agent Skill for Claude Code / OpenClaw, with 53 downloads so far.

How do I install Spark Image?

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

Is Spark Image free?

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

Which platforms does Spark Image support?

Spark Image is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Spark Image?

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

💬 Comments