Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

上海的陆家嘴
0

近日,国际知名人工智能研究团队Colossal-AI再度发力,宣布全面开源其研发的全球首个类Sora架构视频生成模型——「Open-Sora 1.0」。这一开创性举措,旨在推动视频生成技术的普及和进步,为全球AI爱好者提供一个全新的创新平台。

在两周前,Colossal-AI团队已经成功推出了成本降低46%的Sora训练推理复现流程,为业界带来了显著的成本效益提升。如今,他们更进一步,将「Open-Sora 1.0」的完整训练流程公之于众,包括数据处理的详细步骤、所有训练的精细参数以及模型权重,这无疑将极大地促进视频生成技术的研发和应用。

「Open-Sora 1.0」的开源,标志着视频创作领域进入了一个新的纪元。它不仅为开发者和研究人员提供了宝贵的参考资料,也将激发更多创新思维,推动AI在视频生成领域的边界不断拓展。Colossal-AI团队的这一举动,无疑将助力全球AI社区共同探索和进步,加速视频生成技术的革新步伐。

来源:机器之心

英语如下:

**News Title:** “Colossal-AI Launches ‘Open-Sora 1.0’, the World’s First Sora-like Video Generation Model, Pioneering a New Era in Video Creation”

**Keywords:** Open-Sora 1.0, Video Generation, AI Open-Source

**News Content:**

Title: Colossal-AI Team Open-Sources ‘Open-Sora 1.0’, the Global First Sora-inspired Video Generation Model,开创 Video Creation’s New Chapter

Recently, the renowned international AI research team, Colossal-AI, made headlines as it announced the full open-source release of its groundbreaking Sora-architecture-inspired video generation model, ‘Open-Sora 1.0’. This initiative aims to promote the普及 and advancement of video generation technology, offering a fresh innovation platform for AI enthusiasts worldwide.

Just two weeks ago, the Colossal-AI team successfully introduced a Sora training inference reproduction process that reduced costs by 46%, delivering substantial cost-effectiveness improvements to the industry. Now, they are taking it a step further by making ‘Open-Sora 1.0’s complete training process available, including detailed data preprocessing steps, all fine-tuned training parameters, and model weights. This is set to significantly facilitate the development and application of video generation technology.

The open-source release of ‘Open-Sora 1.0’ signifies a new epoch in the realm of video creation. It not only provides invaluable resources for developers and researchers but also fosters innovative thinking, pushing the boundaries of AI in video generation. Colossal-AI’s move is poised to empower the global AI community in collective exploration and progress, accelerating the pace of innovation in video generation technology.

**Source:** Jingji Xinxi Xinwen (translated as ‘Machine Heart’)

【来源】https://www.jiqizhixin.com/articles/2024-03-18-12

Views: 1

0

发表回复

您的邮箱地址不会被公开。 必填项已用 * 标注