Video Generation Model

At the 2024 Ali Yunqi Conference, Ali Cloud CTO Zhou Jingren announced that its latest research and development of AI video generation big model - Tongyi Wanxiang AI raw video, has been officially online, the official website and App can be immediately tried. AI video domestic battlefield, Ali also down. Alibaba's Tongyi launched the Tongyi Wanxiang AI raw video model is officially online, with a powerful picture visual dynamic generation capability, supporting a variety of artistic styles and film and television level texture video content generation. The model optimizes the performance of Chinese elements, supports multi-language input and variable resolution generation, has a wide range of application scenarios, and provides free service...

Byte Jump Volcano Engine announced that the beanbag big model will be released on September 24th video generation model, and will bring more model family ability upgrade. It is understood that the Beanbag Big Model was officially released on May 15, 2024 at the Volcano Engine Original Power Conference. Beanbag Big Model offers multiple versions, including professional and lightweight versions, to suit the needs of different scenarios. The professional version supports 128K long text processing with powerful comprehension, generation and logic synthesis capabilities for scenarios such as Q&A, summarization, creation and classification. While the lightweight version provides lower token cost and latency, providing enterprises with flexible...

Adobe has announced that it will launch video generation capabilities powered by the Adobe Firefly Video model by the end of this year, which will be available in the Premiere Pro beta app and on a standalone Web site. Adobe says it is currently testing three features internally: Generative Extend, Text to Video, and Image to Video, and will be opening them up for public testing in the near future. Generative Extend...

Zhipu AI recently released its latest large-scale model GLM-4-Plus, which demonstrates powerful visual capabilities comparable to OpenAI GPT-4, and announced that it will be open for use on August 30. Major update highlights: Language base model GLM-4-Plus: A qualitative leap in language parsing, instruction execution, and long text processing capabilities, continuing to maintain a leading position in international competition. CogView-3-Plus: The performance of the text model is comparable to the industry's top MJ-V6 and FLUX models. Image/video understanding model GLM-4V-Plus...

On August 28, Zhipu AI open-sourced the CogVideoX-5B video generation model. Compared with the previously open-sourced CogVideoX-2B, the official said that its video generation quality is higher and the visual effect is better. The official said that the inference performance of the model has been greatly optimized, and the inference threshold has been greatly reduced. CogVideoX-2B can be run on early graphics cards such as GTX 1080Ti, and CogVideoX-5B models can be run on desktop "dessert cards" such as RTX 3060. CogVideoX is a big...

Zhipu AI announced today that it will open source CogVideoX, a video generation model with the same origin as "Qingying". According to reports, the CogVideoX open source model includes multiple models of different sizes. Currently, CogVideoX-2B will be open source. It requires 18GB of video memory for inference at FP-16 precision and 40GB of video memory for fine-tuning. This means that a single 4090 graphics card can perform inference, and a single A6000 graphics card can complete fine-tuning. The upper limit of the prompt word of CogVideoX-2B is 226...

Runway, a company that builds generative AI tools for film and image content creators, has released its Gen-3 Alpha video generation model. With the official Gen-3 Alpha website: https://runwayml.com/blog/introducing-gen-3-alpha/ Runway says that compared to its previous flagship video model, Gen-2, the model delivers "major "and fidelity, as well as providing structure, style, and motion to the generated video...

Earlier in the day, OpenAI released its latest video generation model, Sora, which generates a video based on a text description entered by the user. At the same time, OpenAI also released several demo videos, such as a modern woman walking through the streets of Tokyo and a woolly mammoth walking in the snow, which 1ai has reported on in detail. Elon Musk has since commented on OpenAI's new model several times. Musk tweeted a video of Sora's demonstration to Twitter user "Bev Jassos" with the caption "gg Pixar," which Musk then tweeted this afternoon...

Recently, AI startup Runway announced that its video generation model Gen-2 has launched an amazing "motion brush" feature. The launch of this feature represents an important milestone in the controllability of the model. Users only need to paint an area or subject in the image, select a direction and add motion intensity for it, and the motion brush can add controlled motion to the user's generation. This feature is currently available for free trial, usually for 125 seconds of free credits, and consumes about 4 seconds at a time. Users can provide their own pictures, or directly use pictures generated by Runway. The launch of this feature is for users...

Stability AI recently launched a video generation model called Stable Video Diffusion, which is based on the company's existing Stable Diffusion text-to-image model and is capable of generating videos by animating existing images. Unlike other AI companies, Stable Video Diffusion offers one of the few video generation models in the open source space. However, it should be noted that the model is currently in a "research preview" phase, and users must agree to specific terms of use that specify...