← 返回 Skills 市场
jiangyukunok

SGLang-Diffusion Image Generation

作者 jiangyukunok · GitHub ↗ · v1.0.1 · MIT-0
cross-platform ✓ 安全检测通过
496
总下载
0
收藏
1
当前安装
2
版本数
在 OpenClaw 中安装
/install sglang-diffusion
功能描述
Generate images using a local SGLang-Diffusion server (FLUX, Stable Diffusion, Qwen-Image, etc.). Use when: user asks to generate, create, draw, or render an...
安全使用建议
This skill is a small, coherent helper for a local SGLang-Diffusion server. Before installing or using it, ensure you trust the server you point it at (default is localhost). Only set SGLANG_DIFFUSION_API_KEY if the server requires it and you trust the host; do not provide secrets for unrelated services. Be aware the script will write images to /tmp by default or to any --out path you provide.
功能分析
Type: OpenClaw Skill Name: sglang-diffusion Version: 1.0.1 The sglang-diffusion skill is a straightforward implementation for generating images via a local SGLang-Diffusion server. The Python script (generate.py) uses standard libraries to send POST requests to an OpenAI-compatible API endpoint and saves the base64-encoded response as a PNG file. No evidence of data exfiltration, malicious execution, or prompt injection was found.
能力评估
Purpose & Capability
Name/description match the included script and required binary (python3). The script only implements OpenAI-compatible image generation calls to a SGLang-Diffusion server; no unrelated services, credentials, or binaries are requested.
Instruction Scope
SKILL.md instructs the agent to run the bundled Python script and optionally set SGLANG_DIFFUSION_API_KEY. The script only posts prompts to the configured /v1/images/generations endpoint and writes the returned image to disk. Note: the server URL is user-controllable (defaults to localhost) so prompts and optional API key may be sent to any server the user specifies.
Install Mechanism
No install spec is provided (instruction-only plus a small included script). No remote downloads or package installs are performed by the skill itself.
Credentials
The skill declares no required env vars but supports an optional SGLANG_DIFFUSION_API_KEY (documented in SKILL.md and read by the script). This is proportionate to the purpose; users should only provide an API key for servers they trust.
Persistence & Privilege
The skill does not request permanent inclusion (always:false), does not modify other skills or system-wide settings, and only writes image files to a user-specified path or /tmp by default.
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 sglang-diffusion
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /sglang-diffusion 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
- Added new script: scripts/generate.py for image generation via the SGLang-Diffusion server. - Updated documentation to use the new generate.py script instead of curl commands. - Clarified usage instructions, prerequisites, and API key handling. - Provided example command-line usages with common parameters. - Noted OpenClaw integration features and output file handling.
v1.0.0
Initial release of sglang-diffusion skill. - Enables image generation via a local SGLang-Diffusion server (supports FLUX, Qwen-Image, etc.) - Requires the SGLang-Diffusion server and API key to be set up locally. - Provides command instructions for generating and saving images. - Supports optional generation parameters: negative prompt, inference steps, guidance scale, and seed.
元数据
Slug sglang-diffusion
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

SGLang-Diffusion Image Generation 是什么?

Generate images using a local SGLang-Diffusion server (FLUX, Stable Diffusion, Qwen-Image, etc.). Use when: user asks to generate, create, draw, or render an... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 496 次。

如何安装 SGLang-Diffusion Image Generation?

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

SGLang-Diffusion Image Generation 是免费的吗?

是的,SGLang-Diffusion Image Generation 完全免费,采用 MIT-0 许可证,可自由下载、安装和使用。

SGLang-Diffusion Image Generation 支持哪些平台?

SGLang-Diffusion Image Generation 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 SGLang-Diffusion Image Generation?

由 jiangyukunok(@jiangyukunok)开发并维护,当前版本 v1.0.1。

💬 留言讨论