Everlyn
Everlyn is the first open-source foundational video model and super-agent multimodal ecosystem, aiming to provide the world with an open dream machine. Everlyn’s flagship open-source model Everlyn-1 is redefining the capabilities of video AI in terms of output duration, interactivity, generation latency, and hyper-realistic visual quality. Everlyn’s video creation engine and platform, “Eternal World,” are revolutionizing how humans interact with their own photorealistic virtual avatars, which are personalized, interactive video agents capable of performing any task.Everlyn-1 and Eternal World will fundamentally transform what humans can accomplish online, taking over tasks and activities that individuals are unwilling or unable to perform alone. Everlyn was founded by a team of leading experts in generative AI AI, including professors from Cornell University, the University of Oxford, Stanford University, the University of Central Florida (UCF), the Hong Kong University of Science and Technology (HKUST), Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), and Peking University (PKU), as well as former leaders from Meta, DeepMind, Microsoft, Google, and Tencent, and current PhD students in generative AI AI. The Everlyn team consists of prominent figures in the AI research field who have played key roles in some of the industry’s most important innovations, including Google’s foundational video model VideoPoet, Facebook’s foundational video model Make-A-Video, Tencent’s foundational video model, Meta’s Movie Gen, the most-cited benchmark model in video generation, Seeing and Hearing, the industry-leading open-source video model Open-Sora Plan, and OpenAI’s first real-time end-to-end humanoid agent video model Her Body.
Overview
Everlyn is the first open-source foundational video model and super-agent multimodal ecosystem, aiming to provide the world with an open dream machine. Everlyn’s flagship open-source model Everlyn-1 is redefining the capabilities of video AI in terms of output duration, interactivity, generation latency, and hyper-realistic visual quality. Everlyn’s video creation engine and platform, “Eternal World,” are revolutionizing how humans interact with their own photorealistic virtual avatars, which are personalized, interactive video agents capable of performing any task.Everlyn-1 and Eternal World will fundamentally transform what humans can accomplish online, taking over tasks and activities that individuals are unwilling or unable to perform alone. Everlyn was founded by a team of leading experts in generative AI AI, including professors from Cornell University, the University of Oxford, Stanford University, the University of Central Florida (UCF), the Hong Kong University of Science and Technology (HKUST), Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), and Peking University (PKU), as well as former leaders from Meta, DeepMind, Microsoft, Google, and Tencent, and current PhD students in generative AI AI. The Everlyn team consists of prominent figures in the AI research field who have played key roles in some of the industry’s most important innovations, including Google’s foundational video model VideoPoet, Facebook’s foundational video model Make-A-Video, Tencent’s foundational video model, Meta’s Movie Gen, the most-cited benchmark model in video generation, Seeing and Hearing, the industry-leading open-source video model Open-Sora Plan, and OpenAI’s first real-time end-to-end humanoid agent video model Her Body.