image-studio图片处理：本地批量抠图、换背景与水印
image-studio图片处理是 SkillHub 社区 Skill（@user_3b76b7e2/image-studio-pro，v1.0.0，design-media），通过 SKILL.md 指导 Agent 调用本地 Python CLI image_studio.py，在 rembg 与 Pillow 上完成抠图、换背景、水印和尺寸裁剪，支持单张或目录批量，格式含 PNG/JPG/WEBP 等。依赖安装后无需 API Key。文章说明 SkillHub 安装命令、各客户端 skills 目录、依赖安装与典型命令行流水线。
Read Moredsh-rembg: Local Image Background Removal Plugin
`dsh-rembg` is a local image background removal plugin for DeepSeek Harness (DSH), enabling agents to process images without cloud APIs. Installation requires DSH version 0.1.7-rc.1 or later; after installing it from the command line, initial configuration must be completed in the Web GUI, including selecting the runtime mode (CPU or GPU) and installing the model. The plugin provides the `rembg` tool function, which supports removing backgrounds by specifying a model and an image path, making it suitable for local agent development scenarios without public API access.
Read Moredsh-pro-vision-std: Portable DeepSeek V4-Pro Image Processing ModelProvider
`dsh-pro-vision-std` is a plugin for DeepSeek Harness (DSH) designed to add image processing capabilities to models. It is rewritten based on the `dsh-std` specification and supports image attachments by first invoking a vision model to generate a description, then using V4-Pro to perform text generation. As a standalone ModelProvider, it is compatible with DSH core logic and supports in-process caching and contract integration. Installation requires the `@dsh-std/adapter-dsh` dependency and provides the route `dsh-pro-vision / deepseek-v4-pro` to enable image-and-text capabilities, without affecting official plugins.
Read Moredsh-imagedit: DeepSeek Harness Local Image Processing and Smooth Image Generation Plugin
The `dsh-imagedit` plugin for DeepSeek Harness (DSH) aims to address imperfections in generated images by providing a local, deterministic image editing pipeline. Core features include quick/AI cutout, cropping, color adjustment, filters, rounded corners, and batch processing (with support for Sprite Sheet generation). The plugin supports Agent tool calls and CLI command-line operations, can generate shapes through automatic suffix correction, and supports PNG/JPEG/WebP export and compression. It is recommended to use it together with `dsh-draw` to post-process generated images and obtain high-quality asset images.
Read MoreLearn Python OpenCV Easily: Drawing Basic Geometric Shapes
This article introduces methods to draw basic geometric shapes using OpenCV. The steps are as follows: First, install the opencv-python and numpy libraries. After importing these libraries, create a 500x500 black canvas. For drawing shapes: Lines are drawn using cv2.line, e.g., an anti-aliased red line from (50,50) to (450,450); Rectangles are drawn using cv2.rectangle, supporting both outlines (line width 3) and fill (line width -1), such as a green outlined rectangle and a blue filled rectangle; Circles are drawn using cv2.circle, supporting both outlines (line width 5) and fill (line width -1), such as a yellow outlined circle and a red filled circle; Polygons are drawn using cv2.polylines (for outlines) and cv2.fillPoly (for filling), with an example being a cyan triangular outline and a light red quadrilateral fill. Finally, display the image with cv2.imshow and wait for user input to close using cv2.waitKey. Key notes: Colors are in BGR format (e.g., red is (0,0,255)), line width -1 indicates filling, and the coordinate origin is at the top-left corner of the image.
Read More