Search AI Products and News

Scientists at Alibaba Group have introduced VACE, a universal AI model designed to unify a wide range of video generation and editing tasks. At the heart of VACE is an enhanced Diffusion Transformer architecture, innovating with a novel input format called "Video Conditional Unit" (VCU). VCU distills diverse modalities such as text prompts, reference images or video sequences, and spatial masks into a unified representation, and through a specialized mechanism coordinates different inputs to avoid conflicts. Concept decoupling enables fine-grained control.

Recently, the "Top 20 AI Video Generation Companies of 2025" list, jointly released by DBC, CIW, and CIS, has been officially announced. Keling AI (Kuaishou), PixVerse AI (Aishi Technology), and Jimeng AI (Douyin) occupy the top three positions. In addition, many other companies, including Alibaba (Tongyi Wanxiang, Huiwa AI Video), Tencent (Zhiying), iFlytek (Xunfei Huijing), and MiniMax (Haier AI), are also on the list.

In April 2025, Moonvalley, a video generation technology company, announced the successful completion of a $43 million Series B funding round. The round involved 11 unnamed investors, bringing the company's total funding to $113 million. This investment will further fuel Moonvalley's technological innovation and market expansion in the AI video generation field. Just ten days prior to the funding announcement, Moonvalley launched its first video generation model, Marey.

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.

Artificial intelligence video generation technology is changing the landscape of content creation at an unprecedented rate. AIbase learned from social media that Google Veo 2 has officially launched on Google AI Studio, offering users free trial access. This news has generated considerable enthusiasm among developers and creators, marking not only a key step in Veo 2's popularization but also providing a low-threshold testing environment for AI video generation. Below is AIbase's in-depth report on this development, analyzing Veo 2's free trial mechanism and...

A new milestone has been reached in the field of AI video generation. AIbase learned from social media that ByteDance recently released a paper and demo of its new video generation model, Seaweed-7B, showcasing groundbreaking capabilities including synchronized audio and video generation, long-shot storytelling, and real-time high-resolution generation. This release signifies ByteDance's accelerated deployment in AI video technology. Below is AIbase's in-depth report on Seaweed-7B, analyzing its technological highlights and industry impact. Seaweed-7B is groundbreaking.

Alibaba's Tongyi Lab recently released a new digital human video generation model called "OmniTalker." This innovative model allows for precise imitation of a person's expressions, voice, and speaking style by simply uploading a reference video. Compared to traditional digital human production workflows, OmniTalker significantly reduces production costs while enhancing the realism and interactive experience of the generated content, meeting a wide range of application needs. OmniTalker is easy to use; users only need to...

Higgsfield, an innovative AI video generation company, recently unveiled Higgsfield Mix, a groundbreaking technology that completely overturns the physical limitations of traditional cameras. According to AIbase, this technology allows users to combine multiple motion controls in a single shot, creating dynamic effects impossible with real cameras. Higgsfield also introduced 10 new motion control modes specifically designed to enhance speed, tension, and cinematic impact, empowering film creation and numerous other applications.

AI video generation platform Pika recently unveiled a revolutionary new technology enabling users to manipulate any character or object within a video in hyperrealistic ways. This groundbreaking feature has quickly garnered enthusiastic responses from creators worldwide. According to AIbase, Pika's technology achieves remarkably realistic video editing effects. Showreel examples from its creator community are breathtaking, showcasing the limitless potential of AI in video content creation. Hyperrealistic control: A new video editing experience. Pika's new technology leverages advanced A...

UK-based startup Synthesia, which uses AI to generate realistic avatars, has signed a licensing agreement with US stock video company Shutterstock to leverage Shutterstock's extensive video library to enhance the realism of its technology. While the financial terms of the deal remain undisclosed, Synthesia stated that this will help their latest AI model better capture human expressions, vocal tones, and body language. Synthesia creates digital...

Google's AI team recently announced the launch of Veo 2, its highly anticipated video generation model, via the Gemini API. This news has generated significant excitement in the tech world, marking a new era for AI video generation. Starting today, developers with billing enabled and Tier 1 access or higher can utilize the API to access Veo 2 and experience its powerful Text-to-Video and Image-to-Video capabilities.

Skywork AI's research team recently unveiled SkyReels-A2, a groundbreaking video generation framework pushing the boundaries of controllable video synthesis. This Element-to-Video (E2V) framework generates natural videos from text prompts by composing diverse visual elements (characters, objects, backgrounds), maintaining high fidelity to reference images. SkyReels-A2's core lies in its sophisticated data processing pipeline. The research team designed a comprehensive data construction pipeline.

ByteDance recently launched its new AI project, DreamActor-M1. This project aims to replicate the functionality of Runway Act-One, utilizing advanced generative AI technology to transform character performances in videos into virtual animations with improved accuracy and expressiveness. This news has quickly garnered widespread attention from the industry and netizens, seen as another significant step forward for ByteDance in the AI video generation field. Technological Breakthrough: Ambition to Surpass Runway Act-One. According to publicly available information, Drea...

With the rapid development of artificial intelligence technology, iPIKA, an AI video generation platform, recently launched a striking new feature—allowing you to meet your younger self. This feature has quickly sparked heated discussions since its launch, becoming another innovative case combining technology and emotion. iPIKA's new feature allows users to generate a virtual video interacting with their younger selves by uploading a childhood photo and a selfie video. The specific operation process is: Users shoot a selfie video, ensuring that half of the screen is left empty (themselves located on the left or right).

Diffusion models have garnered significant attention in the field of AI video generation due to their superior performance. However, their inherent iterative denoising nature leads to a time-consuming and computationally expensive generation process, significantly hindering their widespread adoption. Recently, a research team from Beihang University, the University of Hong Kong, and the Shanghai AI Laboratory jointly released AccVideo, an innovative technology. This method, employing a novel and efficient distillation approach combined with a synthetic dataset, successfully boosts the generation speed of video diffusion models by an impressive 8.5 times.

In the field of artificial intelligence, Kuaishou's Keling AI is gradually emerging as a dark horse in video generation applications. According to the latest earnings call, Cheng Yixiao, founder and CEO of Kuaishou, revealed that since its launch in June last year, Keling AI's revenue has exceeded 100 million yuan, making it the largest commercially successful video generation AI application in China. Keling AI's strong functionality and early market entry have secured its position in the fiercely competitive AI market. Cheng Yixiao emphasized that with the continued development of AI...

On March 25th, Kuaishou released its full-year 2024 financial results, reporting a year-on-year revenue growth of 11.8% to 126.9 billion yuan, and adjusted net profit reached 17.7 billion yuan, a significant year-on-year increase of 72.5%. A highlight of the report is the rapid commercial progress of Keling AI, its video generation large language model launched in June last year. By February this year, it had accumulated over 100 million yuan in revenue. Keling AI adopts a membership fee model for C-end users and has established API subscription partnerships with thousands of B-end enterprises. Kuaishou CEO Cheng Yixiao revealed in the earnings conference call that Keling AI is already serving...

LiblibAI has integrated Alibaba's Tongyi large language model to launch a new feature enabling users to generate 10-second AI videos quickly and easily.