发现一个好用的用于文本图片识别的 prompt，还有一个免费 AI OCR 工具

[saga]

在线免费 AI OCR 工具： https://functions-ocr.edgeone.app/

代码是开源的，核心 prompt 在这里：pages-templates/examples/functions-ocr/functions/ocr/index.js at main · TencentEdgeOne/pages-templates · GitHub

看模型用的是 hunyuan-vision，换成其他平台的大语言模板效果应该都差不多。

[yuaotian (煎饼果子卷鲨鱼辣椒)]

看看，感觉好像还不错？

[hsingjui (刘作老虎)]

还不错

[handsome (大帅哥)]

感谢你的分享

[beary]

感谢佬的分享，用起来。

[Cax (伦比亚)]

马克杯用

[PLA81]

感谢楼主分享

[fangyuan99]

省流：

Convert the provided image into Markdown format.
Ensure that all content from the page is included, such as headers, footers, subtexts, images (with alt text if possible), tables, and any other elements.
Requirements:
- Output Only Markdown: Return solely the Markdown content without any additional explanations or comments.
- No Delimiters: Do not use code fences or delimiters like \`\`\`markdown.
- Complete Content: Do not omit any part of the page, including headers, footers, and subtext.
- Return the table content in the form of a markdown table.

[I-IronMan (我钢铁侠)]

爱你摸摸哒

[Haven (黑神话·悟空)]

感谢大佬的神六

[CaptainVIX (Edward)]

感谢大佬分享，这种需求很大

[dash.z (王)]

好东西，谢谢佬

[randolph5 (泗水亭长)]

好东西。感谢大佬分享

[858146815 (深圳佬)]

感觉好像还不错

[zlex]

好东西。感谢大佬分享