GitHub · 多媒体与视觉
picturereader
给纯文本模型的"读图"能力：图片降分辨率+降色深+结构/色彩指纹渲染成文本网格喂回对话，模型像多模态一样自主缩放、取样、OCR 读图；纯本地零外部模型依赖，附读图方法论 skill 与可选 PaddleOCR。
SOURCE-DECLARED INSTALL
dsh plugin --profile web add github:jing-hy/picturereaderSource-declared command. Review the package and Registry Listing before running it.
MEDIA REFERENCES
Captured in public view
No public media reference was captured for this record.
REGISTRY LISTINGS
Source-attributed install evidence
| Registry source | Install spec | Version | Verification claim | Observed | Raw snapshot |
|---|---|---|---|---|---|
| zoahdev/dsh-subscribe · registry.json | github:jing-hy/picturereadergit | — | source does not claim verified | 2026-08-16 → 2026-08-16 | 962 |
| awesome-dsh-plugin/awesome-dsh-plugin · https://awesome-dsh-plugin.com/plugins.json | github:jing-hy/picturereadergit | — | unreported | 2026-08-16 → 2026-08-16 | 1093 |
| Zhiyuan-Fan/Awesome-DeepSeek-Harness-Plugins · README.md | — | — | unreported | 2026-08-16 → 2026-08-16 | 1093 |
Verification is a claim made by the named Registry Source; it is not a security, compatibility, quality, or official-endorsement claim by this site.
CONTEXT
Why it is here
给纯文本模型的"读图"能力：图片降分辨率+降色深+结构/色彩指纹渲染成文本网格喂回对话，模型像多模态一样自主缩放、取样、OCR 读图；纯本地零外部模型依赖，附读图方法论 skill 与可选 PaddleOCR。
Evidence updated 2026-08-16T13:41:06Z. Interaction numbers are platform-native snapshots; the evidence panel records the metric source and observation time. NULL means the public page did not expose a number at collection time.