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...

Heygem is an open-source alternative to HeyGen, offering precise cloning of appearance and voice, and supporting lip-sync for realistic video generation.

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.

OpenAI's leadership team announced during a Discord office hours session on Friday that the company plans to eventually integrate its AI video generation tool, Sora, directly into the popular ChatGPT application, further expanding its AI creative ecosystem. Currently, Sora is only available through a dedicated web application launched by OpenAI in December, allowing users to access the AI video model to generate movie clips up to 20 seconds long. Rohan Sahai, OpenAI's product lead for Sora, stated that...

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.

Recently, Tencent's Hunyuan Video Model has officially begun recruiting testing partners on Platform X, marking a critical testing stage for this cutting-edge AI video generation technology. According to official sources, there is a high probability that the model will be open-sourced after the testing concludes, contributing its technological achievements to the global AI community. The Hunyuan Video Model is an important innovation by Tencent in the field of AI video generation, boasting over 13B parameters, making it one of the largest video generation models among open-source models.

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.