zh-cn
关于问题反馈与寻求帮助
如果在使用过程中遇到任何问题，或者有新功能的需求，欢迎随时在 Issues 中提出。我会尽量在看到后予以修复、解答或评估。对于单纯求助或提问的帖子，建议大家在发布时主动打上 help wanted 标签，以便于分类和跟进。
目前本项目暂无专属的交流群，出于个人隐私考量，我也不会公开 QQ 或微信等联系方式。如需交流或有要事联系，请通过邮件 (me@ifoxhui.com) 或 Telegram (@ifoxhui) 找到我。
关于作者与免责声明
我目前还是一名在校学生，技术能力与日常维护时间都相对有限，很多时候也是边学边做、“摸着石头过河”。因此，我无法保证项目随时处于完美无缺的状态（例如可能会遇到不可控的反人机检测等问题）。
本项目遵循开源协议。如果您打算将其用于商业用途（如包装后售卖接口等），作为开源作者我不会干涉。但请务必明确：本项目及作者本人不承担任何因使用本项目而导致的直接或间接后果。 这包括但不限于：因项目 Bug 或漏洞造成的经济损失、相关网站账号被封禁，以及任何可能衍生的法律问题。请大家合理、合规地评估风险后使用。
项目的诞生与发展历程
这个项目最初其实只是一个单文件的 NodeJS 脚本。当时 Gemini 的 Nano Banana (Pro) 模型非常火爆，许多机器人爱好者希望将其接入自己的群聊机器人，用于给群成员发送的图片进行“手办化”或“CosPlay 化”等二次创作。由于直接使用该模型的官方接口成本比较昂贵，我便想到通过浏览器自动化操作 LMArena 网页来实现免费图片生成的想法。
换句话说，它起初只是我随手写的一个“玩具”。（现在您依然可以在 puppeteer-edition 分支中去考古本项目早期的“圣遗物” ）
后来，随着相关爱好者的不断反馈，以及为了解决实际使用中出现的痛点，项目经历了多次迭代。代码变得越来越庞大，实现方式也逐渐褪去初期的简陋走向专业，慢慢成长为了一个相对合格的成品。在这个过程中，我也收获了非常多宝贵的经验。
直到最近，随着 OpenClaw 系列工具火爆全网，我这个小小的项目似乎也有幸蹭到了一波 AI 时代的红利，迎来了用户量的激增（甚至还在邮箱里收到了各种推广合作与求助的邮件）。
在此，由衷地感谢大家对本项目的关注、包容与支持！
en-us
About Feedback and Seeking Help
If you encounter any problems or have new feature requests while using this project, please feel free to open an Issue. I will do my best to fix, answer, or evaluate them once I see them. For general help or questions, it is highly recommended to actively add the help wanted label when creating your issue to help with categorization and follow-ups.
Currently, there is no dedicated discussion group for this project. For personal privacy reasons, I will not be sharing my QQ or WeChat contact information. If you need to reach out or have urgent matters, please contact me via email (me@ifoxhui.com) or Telegram (@ifoxhui).
About the Author and Disclaimer
I am currently a student, which means my technical skills and the time I can dedicate to maintenance are limited. A lot of the time, I am learning as I go. Therefore, I cannot guarantee that the project will always be in a flawless state (for instance, it may encounter uncontrollable anti-bot detection issues).
This project is open-source. If you plan to use it for commercial purposes (such as packaging and selling APIs), I, as the author, will not interfere. However, please be explicitly aware: This project and the author assumes no responsibility for any direct or indirect consequences arising from its use. This includes, but is not limited to, financial losses caused by project bugs or vulnerabilities, account bans on related websites, and any potential legal issues. Please evaluate the risks thoroughly and ensure compliance before using.
The Origin and Development of This Project
Initially, this project was nothing more than a single-file NodeJS script. Back then, Gemini's Nano Banana (Pro) model was incredibly popular, and many bot enthusiasts wanted to integrate it into their group chat bots to apply effects like "figure-style" or "Cosplay-style" transformations to images sent by users. Since the official API costs for that model were quite high, I came up with the idea of using browser automation to interact with the LMArena webpage for free image generation.
In other words, it started out simply as a fun little "toy." (You can still dig up the early "relics" of this project in the puppeteer-edition branch if you want to take a trip down memory lane!)
Over time, fueled by continuous feedback from fellow enthusiasts and the need to resolve practical pain points, the project underwent multiple iterations. The codebase expanded, and the implementation transitioned from its initial simplicity to a more professional architecture, gradually maturing into a reasonably solid project. Along the way, I've gained a tremendous amount of valuable experience.
Recently, with the explosive popularity of the OpenClaw series of tools across the internet, my small project seems to have luckily caught the tailwind of the AI era, experiencing a massive surge in users (I've even started receiving various collaboration requests and help emails).
I want to express my sincere gratitude to everyone for your attention, patience, and support for this project!
zh-cn
关于问题反馈与寻求帮助
如果在使用过程中遇到任何问题，或者有新功能的需求，欢迎随时在 Issues 中提出。我会尽量在看到后予以修复、解答或评估。对于单纯求助或提问的帖子，建议大家在发布时主动打上
help wanted标签，以便于分类和跟进。目前本项目暂无专属的交流群，出于个人隐私考量，我也不会公开 QQ 或微信等联系方式。如需交流或有要事联系，请通过邮件 (me@ifoxhui.com) 或 Telegram (@ifoxhui) 找到我。
关于作者与免责声明
我目前还是一名在校学生，技术能力与日常维护时间都相对有限，很多时候也是边学边做、“摸着石头过河”。因此，我无法保证项目随时处于完美无缺的状态（例如可能会遇到不可控的反人机检测等问题）。
本项目遵循开源协议。如果您打算将其用于商业用途（如包装后售卖接口等），作为开源作者我不会干涉。但请务必明确：本项目及作者本人不承担任何因使用本项目而导致的直接或间接后果。 这包括但不限于：因项目 Bug 或漏洞造成的经济损失、相关网站账号被封禁，以及任何可能衍生的法律问题。请大家合理、合规地评估风险后使用。
项目的诞生与发展历程
这个项目最初其实只是一个单文件的 NodeJS 脚本。当时 Gemini 的 Nano Banana (Pro) 模型非常火爆，许多机器人爱好者希望将其接入自己的群聊机器人，用于给群成员发送的图片进行“手办化”或“CosPlay 化”等二次创作。由于直接使用该模型的官方接口成本比较昂贵，我便想到通过浏览器自动化操作 LMArena 网页来实现免费图片生成的想法。
换句话说，它起初只是我随手写的一个“玩具”。（现在您依然可以在 puppeteer-edition 分支中去考古本项目早期的“圣遗物” ）
后来，随着相关爱好者的不断反馈，以及为了解决实际使用中出现的痛点，项目经历了多次迭代。代码变得越来越庞大，实现方式也逐渐褪去初期的简陋走向专业，慢慢成长为了一个相对合格的成品。在这个过程中，我也收获了非常多宝贵的经验。
直到最近，随着 OpenClaw 系列工具火爆全网，我这个小小的项目似乎也有幸蹭到了一波 AI 时代的红利，迎来了用户量的激增（甚至还在邮箱里收到了各种推广合作与求助的邮件）。
在此，由衷地感谢大家对本项目的关注、包容与支持！
en-us
About Feedback and Seeking Help
If you encounter any problems or have new feature requests while using this project, please feel free to open an Issue. I will do my best to fix, answer, or evaluate them once I see them. For general help or questions, it is highly recommended to actively add the help wanted label when creating your issue to help with categorization and follow-ups.
Currently, there is no dedicated discussion group for this project. For personal privacy reasons, I will not be sharing my QQ or WeChat contact information. If you need to reach out or have urgent matters, please contact me via email (me@ifoxhui.com) or Telegram (@ifoxhui).
About the Author and Disclaimer
I am currently a student, which means my technical skills and the time I can dedicate to maintenance are limited. A lot of the time, I am learning as I go. Therefore, I cannot guarantee that the project will always be in a flawless state (for instance, it may encounter uncontrollable anti-bot detection issues).
This project is open-source. If you plan to use it for commercial purposes (such as packaging and selling APIs), I, as the author, will not interfere. However, please be explicitly aware: This project and the author assumes no responsibility for any direct or indirect consequences arising from its use. This includes, but is not limited to, financial losses caused by project bugs or vulnerabilities, account bans on related websites, and any potential legal issues. Please evaluate the risks thoroughly and ensure compliance before using.
The Origin and Development of This Project
Initially, this project was nothing more than a single-file NodeJS script. Back then, Gemini's Nano Banana (Pro) model was incredibly popular, and many bot enthusiasts wanted to integrate it into their group chat bots to apply effects like "figure-style" or "Cosplay-style" transformations to images sent by users. Since the official API costs for that model were quite high, I came up with the idea of using browser automation to interact with the LMArena webpage for free image generation.
In other words, it started out simply as a fun little "toy." (You can still dig up the early "relics" of this project in the puppeteer-edition branch if you want to take a trip down memory lane!)
Over time, fueled by continuous feedback from fellow enthusiasts and the need to resolve practical pain points, the project underwent multiple iterations. The codebase expanded, and the implementation transitioned from its initial simplicity to a more professional architecture, gradually maturing into a reasonably solid project. Along the way, I've gained a tremendous amount of valuable experience.
Recently, with the explosive popularity of the OpenClaw series of tools across the internet, my small project seems to have luckily caught the tailwind of the AI era, experiencing a massive surge in users (I've even started receiving various collaboration requests and help emails).
I want to express my sincere gratitude to everyone for your attention, patience, and support for this project!