Today's featured cutting-edge AI information, welcome to read 👇
🔄 ChatGPT reintroduces web browsing feature, displaying source links, and launches Chrome extension for search engine conversion.
🔍 Google AI Studio's Gemini integrates Google Search capabilities, offering free real-time information retrieval.
🎨 New image model In-Context LoRA, built on Flux, generates series of images with consistent style and portrait features.
📚 GitHub releases comprehensive Web3 learning resource collection, including fundamentals, project cases, and development resources.
🤖 Open-source automation crawler tool Maxun released, building bots through visual interface, supporting various data collection and export functions.
Latest News
1. Major comeback! ChatGPT finally restores web browsing functionality!
Better than the previous web browsing feature, it provides quick, timely answers and displays source links to relevant web resources.
Official announcement: https://openai.com/index/introducing-chatgpt-search/
Additionally, it offers a Chrome browser extension that can directly change the search engine to point to ChatGPT.
2. Gemini supports Google Search.
Using Gemini in Google AI Studio can combine Google Search to generate real-time information responses, reducing hallucinations and increasing credibility.
Experience it at: https://aistudio.google.com
Currently free to use, though when it will be supported on Gemini remains unknown.
AI Art
1. An image model capable of generating consistent portraits and styles: In-Context LoRA.
Built on Flux, it can generate multiple images with consistent style and portrait features in one go. The demo images look amazing!
Detailed introduction: https://ali-vilab.github.io/In-Context-LoRA-Page/
It can be used to generate a series of coherent images or AI portrait photos with consistent style. It has many application scenarios and strong potential for monetization and experimentation.
However, the code is not yet open-sourced, worth keeping an eye on.
Open Source Projects
1. A comprehensive Web3 learning resource collection: web3.0.
Covers Web3 basics, applications and projects, related content creators, video tutorials, related books, development resources, and tools.
GitHub: https://github.com/wangschang/web3.0
Additionally, it includes some Web3-related job opportunities. The project is continuously updating, interested parties can take a look.
2. An open-source automated web data crawling tool: Maxun.
Build custom bots through a visual interface without coding, enabling automated web data crawling, supporting operations like capturing lists, text, or screenshots.
GitHub: https://github.com/getmaxun/maxun
Furthermore, it supports data extraction, handling pagination and scrolling, specifying bot runtime, converting web data to API or exporting to Excel spreadsheets, and more.
Currently, the tool is being rapidly iterated and updated. Interested users can follow and try it out.
