Search AI Products and News

Today, at the Create 2025 AI Developer Conference held in Wuhan, Baidu founder Li Yanhong delivered a nearly 60-minute keynote speech themed "The World of Models, the Realm of Applications." He officially released Ernie 4.5 Turbo and X1 Turbo, and revealed the progress and challenges of DeepSeek's implementation within the Baidu ecosystem.

Alibaba's Tongyi announced the open-sourcing of the Wan2.1 series of models, including a powerful first and last frame video generation model. This model utilizes the advanced DiT architecture, achieving several technological breakthroughs. It significantly reduces the computational cost of generating high-definition videos while ensuring high temporal and spatial consistency. This open-sourcing provides developers and creators with powerful tools, driving the advancement of video generation technology.

Bug fixing is a persistent challenge in software development. ByteDance's Doubao large model team has exciting news: they've launched Multi-SWE-bench, the first multi-lingual software engineering (SWE) dataset. This new dataset aims to evaluate and improve the ability of large models to automatically fix code errors. Multi-SWE-bench significantly expands the scope compared to previous single-language datasets. It covers not only Python, but also...

The WeChat Video Creation Safety Center recently announced that it has discovered some broadcasters improperly using AI tools during live streams, leading to risks such as misleading viewers and infringing on others' portrait rights. These actions violate the "WeChat Video Account Operation Regulations" and "WeChat Video Account Live Streaming Behavior Regulations," disrupting the platform's healthy ecosystem.

OpenAI's ChatGPT is experiencing rapid growth. According to a recent report by The Information, ChatGPT's paid user base has surpassed 20 million in just three months, a nearly 30% increase from 15.5 million at the end of last year. This surge indicates a growing willingness among users to pay for the AI's capabilities in writing code, articles, providing health advice, and financial planning. Estimates suggest ChatGPT's monthly revenue currently reaches at least $415 million.

A new study has raised concerns that OpenAI may have used copyrighted O'Reilly Media books to train its latest AI models without permission. The study was released by the AI Disclosures Project, a non-profit organization founded in 2024 by media mogul Tim O'Reilly and economist Ilan Strauss. AI models can be viewed as sophisticated prediction engines that...

Recently, ChatGPT has experienced an unprecedented surge in users thanks to its new image generation capabilities, becoming a hot topic on the internet. According to SensorTower data, the app's active users, in-app subscription revenue, and downloads all hit record highs last week, signifying its strong market performance. Since the launch of GPT-4, ChatGPT has attracted a large number of users employing its image generation tools to transform everyday photos and memorable moments into the style of Japan's Studio Ghibli animation.

Spain is considering legislation aimed at combating the proliferation of AI-generated pornography and safeguarding the privacy of minors.

The Spanish government has recently passed a new law imposing substantial fines on companies that fail to properly label AI-generated content, aiming to combat the spread of deepfakes. Digital Transformation Minister Oscar Lopez announced that the law, inspired by the EU's AI Act, mandates strict transparency requirements for AI systems deemed high-risk. Image caption: Image generated by AI, image licensing provider Midjourney. Lopez noted...

VideoPainter is a deep learning-based editing tool that allows for automated video content modification using simple prompts. It's particularly well-suited for long-form video editing. Imagine watching a great video, only to find a detail you'd like to change. Previously, you might have had to painstakingly adjust each frame or even reshoot the entire segment. Now, with VideoPainter, you simply input a short prompt, and the system...

Recently, developer scraed released LanPaint on GitHub, a zero-shot image inpainting tool. This tool aims to help users achieve high-quality image inpainting results on any Stable Diffusion (SD) model, including custom-trained models. LanPaint achieves this by iteratively prompting the model to 'think' before denoising, resulting in more seamless and accurate inpainting. A key feature of LanPaint is its zero-shot capability; users can start using it immediately without any training.