Search AI Products and News

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.

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...

Heard of OpenAI's extravagant Sora? With training costs easily exceeding millions of dollars, it's like the Rolls-Royce of video generation. Now, LuChern Technology announces the open-sourcing of its video generation model, Open-Sora 2.0! For a mere $200,000 (equivalent to 224 GPUs), they successfully trained a commercial-grade video generation model with 11 billion parameters. Performance rivals OpenAI Sora. Don't let the low cost of Open-Sora 2.0 fool you...

Still lamenting the high barrier to entry for video production and the complexities of post-editing? Fear not! Alibaba's Tongyi Wan team has launched their latest heavyweight model: the All-in-One video generation and editing model—VACE. One of VACE's most striking capabilities is its powerful conditional video generation function. This means you only need to describe your desired scene in text, and VACE will quickly transform your imagination into reality. It's like having a dream film crew at your command, with astonishing efficiency!

Recently, the Modelers community officially launched Step-Video and Step-Audio, two open-source multimodal large models developed by Step-Star. These models are designed for video generation and voice interaction, respectively, aiming to provide developers and enterprise users with more powerful AI tools. Step-Video, formally known as Step-Video-T2V, is a 30-billion parameter model, making it the world's largest open-source video generation model. This model can directly generate 20...

The DeepBeepMeep team recently released Wan2.1GP on GitHub, a video generation model optimized for users with low-end GPUs. Based on Alibaba's Wan2.1, this model aims to provide powerful video generation capabilities to those lacking access to high-performance GPU resources. The launch of Wan2.1GP marks a significant advancement in video generation technology, particularly within the open-source community. Image source note: Image generated by AI, licensed from Midjourney.

Alibaba today announced the full open-sourcing of its video generation model, Wanxiang 2.1, releasing both a 14B and a 1.3B parameter version. The professional 14B parameter version offers top-tier performance, suitable for scenarios demanding high video quality. The 1.3B parameter version, optimized for consumer-grade GPUs, requires only 8.2GB of VRAM to generate high-quality 480P videos and is ideal for secondary model development and academic research. According to Alibaba, Wanxiang 2.1 excels in handling complex movements, accurately representing real-world physics, and enhancing the cinematic quality of generated videos.

Recently, Tongyi announced the open-sourcing of its latest Tongyi Wanxiang large model, Wan2.1. Wan2.1 is an AI model focused on high-quality video generation. With its excellent performance in handling complex movements, reproducing realistic physics, enhancing cinematic quality, and improving instruction following, it has become the preferred tool for creators, developers, and businesses embracing the AI era.

On February 18, Kunlun Wanwei announced the open source of China's first AI short drama creation video generation model SkyReels-V1 and China's first SOTA-level expression action controllable algorithm based on video base model SkyReels-A1. This initiative aims to address current issues such as the lack of open-source AI video generation models, high costs, and usability challenges, promoting innovation and development in the AI short drama industry. SkyReels-V1 is China's first open-source video generation model for AI short drama creation. The model combines lip-sync generation.

Today, Step-Chronicles and Geely Automobile Group announced the joint open-source of two models from the Step series of multimodal large models: the Step-Video-T2V video generation model and the Step-Audio voice model. Among them, the Step-Video-T2V video generation model is globally ahead in both parameter count and performance. This model has 30 billion parameters and can directly generate high-quality videos at 540P resolution with 204 frames, ensuring high information density and strong consistency in the generated content. Evaluation results show that