agentsclimarketplace

Image local

Skill jk241282/-deepseek-skills/image-local

给 Claude Code + DeepSeek 装上眼睛和耳朵:本地多模态 Skills 套装,支持图片识别/OCR(Ollama minicpm-v)和语音转文字(faster-whisper large-v3-turbo),纯本地运行无需云服务

Install
npx -y skills add jk241282/-deepseek-skills --skill image-local

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 1 stars1 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

当用户要求生成图片、画图、创作图像时使用此 skill。使用本地 SDXL Turbo 模型进行文生图,GPU 加速 1 步出图。触发场景:用户说"生成一张图片"、"画一个"、"帮我画"、"generate an image"、"创作一张图"等任何要求用文字生成图片的场景。

SKILL.md

1.3 KB, 369 tokens by cl100k_base, as published. Nobody here has run it

本地文生图

管线

用户描述 → Claude 翻译为英文 prompt → SDXL Turbo (GPU) → PNG 图片

SDXL Turbo 需要英文提示词。将用户的中文描述翻译为英文后传入。

执行步骤

1. 理解用户需求

从用户输入中提取图片描述,翻译为英文 prompt。

2. 生成图片

py -3.12 "<skill目录>/scripts/generate.py" "<英文提示词>" "<输出路径>" <宽度> <高度>
  • 默认 512×512,可指定 768 或 1024
  • 1 步出图,约 10 秒
  • 输出默认保存到桌面

3. 呈现结果

用 Read 工具读取生成的 PNG 图片展示给用户。

模型位置

C:/Users/Dp333/Desktop/models/sdxl-turbo/

常见问题

  • 首次加载慢: 模型约 7 GB,GPU 加载约 8 秒
  • 显存: SDXL Turbo 在 RTX 4060 8GB 上流畅运行
  • 提示词: 必须使用英文,SDXL Turbo 不支持中文
  • Python 版本: 必须使用 Python 3.12(py -3.12),3.14 不支持 CUDA

What ships with it: 1 file

1.6 KB alongside SKILL.md, 1 of them executable

scripts/

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.