
WebML Image Captioning is a free Chrome extension that generates descriptive captions for images using machine learning models that run entirely inside your browser. It can caption images from local files or from a browser tab, and lets you export or clear the collected results at any time.
| 维度 / 指标 | ![]() | ![]() |
|---|---|---|
| 官方域名 | tinyfish.ai | chromewebstore.google.com |
| 定价模式 | 免费增值,定价请咨询 | 免费 |
| 月访问量 | 112.5万 (1,124,952) | 0 (0) |
| 月度环比流量变化 | +74.96万 (+199.7%) | 0 (—) |
| 主要市场与份额 | 🇺🇸 美国 (27.4%) | 🌐 全球 (—) |
| 直接访问 / 月 | 40.13万 | 0 |
| 用户评分 | 4.4 | 3.8 |
| 支持的平台 | 网站 | 浏览器扩展 |

一个 API Key,提供面向智能体的网页搜索、抓取、浏览与自动化能力
真实浏览器渲染的搜索,以结构化 JSON 返回实时、非缓存的结果,且不收取搜索费用。
把任意 URL 转换为省 token 的 Markdown、JSON 或 HTML,在内容到达模型前就剔除导航栏、Cookie 弹窗与广告。
提供可保持状态的完整云浏览器会话,可用 Playwright、Puppeteer 或 Chrome DevTools 协议驱动。
用自然语言给出目标,智能体即可导航、填表并返回结构化结果;监控功能会在被跟踪的页面或主题变化时发出提醒。

WebML Image Captioning is a free Chrome extension that generates descriptive captions for images using machine learning models that run entirely inside your browser. It can caption images from local files or from a browser tab, and lets you export or clear the collected results at any time.
The captioning model is downloaded into the browser and inference happens on your own machine, so images are never transmitted to a third-party cloud service.
Caption images stored on your computer or images shown in the current browser tab, without saving them first.
After the model has been initialized the extension can keep captioning images without an active internet connection.
Save the caption output together with the related images, and clear the stored data whenever you choose.
免费 / 开源提供更干净、适合 LLM 的 Markdown 转换与爬虫功能,但缺乏 TinyFish 的交互式云端浏览器自动化能力。

提供强大的无头浏览器自动化和控制,但比起托管的 Agent API,需要更多自定义开发。
提供强大的无头浏览器自动化和控制,但比起托管的 Agent API,需要更多自定义开发。
把任意图片转成详细的 AI 生成提示词

专项更强Provides independent web search and agent grounding, but lacks content fetching and browser automation features.
用 AI 描述任意图片——详细描述、配文、提示词与文字提取集于一处
免费 / 开源Uses natural language prompts for open-source web scraping, but offers fewer managed enterprise cloud browser features.
免费 / 开源Uses natural language prompts for open-source web scraping, but offers fewer managed enterprise cloud browser features.
免费双语浏览器扩展,自选 AI 引擎翻译任意网页

Provides reliable proxy and web scraping endpoints for data extraction, but lacks advanced agentic cloud browser workflows.
Provides reliable proxy and web scraping endpoints for data extraction, but lacks advanced agentic cloud browser workflows.