
Security News
PHP Foundation Says Chainguard Broke Security Embargo Ahead of Emergency Patches
The PHP Foundation says Chainguard broke a security embargo ahead of critical RCE patches, as leaks disrupted the coordinated release.
picturereader-zcode
Advanced tools
ZCode plugin: pixel-to-text image reading for text-only models. Downscales and color-quantizes PNG/JPEG/GIF/BMP and feeds the coarse pixel grid to the model so it can 'see' layout, colors and rough shapes without a vision model. Ported from the picturerea
给纯文本模型(如 deepseek-v4-flash)的"读图"能力——双版本发布:
- DSH 版:DeepSeek Harness 插件(
dsh-plugin,含 DSH EAC 桌面端)- ZCode 版:ZCode 桌面端插件(
zcode-plugin,经 MCP 暴露工具)
把图片 降分辨率 + 降色深 + 结构/色彩指纹提取,渲染成文本网格喂回对话, 让模型像多模态模型一样"看"图:描述场景、主体、环境、光线与语义内容。 纯本地、零外部模型依赖、零 API key、零 Python(PaddleOCR 为可选增强)。
| 版本 | 平台 | 形态 | 源码 | 安装 |
|---|---|---|---|---|
| DSH 版 | DeepSeek Harness(含 EAC 桌面端) | npm 插件(dsh.bundle) | 仓库根目录 | dsh plugin --profile web add picturereader |
| ZCode 版 | ZCode 桌面端 | 本地 marketplace 插件(MCP server + skill) | jing-hy/picturereader-zcode(独立仓库) | 见其 README |
两个版本共用同一套业务核心(src/core.js)与读图方法论 skill(image-reading),
三个工具行为完全一致:image_scan / image_ocr / image_sample。
ZCode 版性能说明:ZCode 版通过 MCP(stdio 子进程)暴露工具,每次调用都要 经历进程通信与序列化开销,速度明显慢于 DSH 版(DSH 版为插件内直接调用)。 高频看图、批量看图任务请优先使用 DSH 版;ZCode 版适合轻量、偶发看图。
DeepSeek 等纯文本模型没有视觉编码器,无法直接看图。picturereader 把"看图"翻译成模型能理解的结构化文本证据,并提供一套经过大量真实图片迭代验证的读图方法论 skill(image-reading),让模型像人一样分步看图:
| 工具 | 作用 |
|---|---|
image_scan | 全局/区域扫描:亮度/颜色网格 + regions 色块 + shade diversity + texture mix + structure(条纹/对称) + 像素级 colors + hue families 纯色指纹;支持 focus/region 局部放大、px_per_cell 像素密度定向放大 |
image_ocr | 文字识别双引擎:windows(内置,默认)/ paddle(选装,发光/弯曲/游戏字更强),失败自动降级不崩溃 |
image_sample | 8×8 精确像素取样,判断材质/纹理(金属/木纹/织物/皮肤/噪点) |
skills/image-reading.md(DSH 版)/ skills/image-reading/SKILL.md(ZCode 版)是一套经大量真实图片场景迭代验证的读图方法论
(按 experience / skill / principle / insight 分层,教训有据可依、找得到主模型模式),
安装后模型自动掌握:
# 1. 插件
dsh plugin --profile web add picturereader # 或从源码: dsh plugin --profile web add .
dsh plugin --profile headless add picturereader
# 2. 读图方法论 skill(推荐)
copy skills\image-reading.md %USERPROFILE%\.dsh\skills\ # Windows
# macOS/Linux: cp skills/image-reading.md ~/.dsh/skills/
# 3.(可选)PaddleOCR 增强引擎:node scripts/setup-ocr.mjs
重启 DSH Desktop 后,模型工具列表出现 image_scan / image_ocr / image_sample,
技能目录出现 image-reading。
ZCode 版是独立仓库:jing-hy/picturereader-zcode。
ZCode 版通过 MCP server(mcp/server.js,stdio)把三个工具暴露给 ZCode,
读图方法论作为 skill(skills/image-reading/)随插件分发,业务逻辑 src/core.js
与本仓库完全一致。安装与使用请见其 README。
直接对模型说:
用 image_scan 看一下 <路径> 这张图,细看感兴趣的部分
模型会加载 image-reading 方法论自动执行完整流程(定调 → 找主体 → 验证 → 描述)。
image: chart.png (600x400 -> 32x21 cells, ~18.8x19px per cell, region=full, palette=full, mode=color)
shade diversity: 10 distinct shades | texture: smooth 24.2%, medium 19.3%, rough 56.5%
structure: 6 vertical stripes (4 alternating colors) at cols 4..7; left-right symmetry 45%
hue families: cyan 88.2%, green 4.5%, yellow 1% ← 真实主调(colors 灰白占比是假象)
regions: ...(色块结构)
colors by area: ...(像素级真实占比)
luminance grid / color grid
| 变量 | 默认值 | 作用 |
|---|---|---|
DSH_PADDLE_PYTHON | C:\Users\Administrator\paddle_venv\Scripts\python.exe | PaddleOCR 解释器路径(与原插件同名,便于直接迁移) |
DSH_PADDLE_CACHE | <插件目录>\.paddlex-cache | PaddleX 模型缓存目录 |
# DSH 版(本仓库)
npm install
npm test # node:test,76 个测试全绿
node scripts/setup-ocr.mjs # 可选:装 PaddleOCR
node scripts/preview.mjs # 生成 fixtures 并预览渲染
# ZCode 版(独立仓库 jing-hy/picturereader-zcode)
git clone https://github.com/jing-hy/picturereader-zcode.git
cd picturereader-zcode
npm install
npm test # node:test
node scripts/setup-ocr.mjs # 可选
热插拔(DSH 版):DSH 本身不支持代码热重载,但本插件自带执行层热加载——业务逻辑全在
src/core.js 单文件,工具每次执行按 mtime 动态加载(cache-bust),改 core.js
下次调用即生效;工具定义(schema/描述)改动需重启桌面端。
热插拔(ZCode 版):MCP server 从所选目录运行,改 src/core.js 下次调用即生效
(详见 picturereader-zcode 仓库 README)。
scripts/setup-ocr.mjs),缺失自动降级不崩溃MIT
FAQs
ZCode plugin: unified image understanding for text-only models. Fuses frame-free pseudo-multimodal reading (pixel scan + OCR×3 engines + sample + crop/palette/compare + batch + document-to-image) with an optional external vision API bridge (LM Studio / ll
The npm package picturereader-zcode receives a total of 0 weekly downloads. As such, picturereader-zcode popularity was classified as not popular.
We found that picturereader-zcode demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.

Security News
The PHP Foundation says Chainguard broke a security embargo ahead of critical RCE patches, as leaks disrupted the coordinated release.

Security News
PHP releases emergency patches for two critical RCE vulnerabilities as agencies urge organizations to take unpatched sites offline.

Threat Research
/Security News
A supply chain attack compromised LiteLLM 1.107.0 on PyPI and Docker, spreading malware that steals cloud credentials, developer secrets, and AI provider keys.