美通社

2024-06-11 08:21

Kuaishou Unveils Proprietary Video Generation Model 'Kling;' Testing Now Available

BEIJING, June 11, 2024 /PRNewswire/ -- Kuaishou Technology (HKD Counter: 01024 / RMB Counter: 81024)(together with its subsidiaries and consolidated affiliated entities, hereinafter referred to as "Kuaishou"), a leading content community and social platform, recently launched its self-developed video generation model, the Kling Large Model (hereinafter referred to as "Kling" (可灵)). Kling is capable of generating complex spatiotemporal motions and simulating the characteristics of the physical world. Leveraging these capabilities, Kling transforms text prompts into high-quality AI videos that closely mimic the real world's complex motion patterns and physical characteristics. Kling also possesses powerful conceptual combination and imagination abilities. Kling can generate videos up to two minutes long with a frame rate of 30fps and video resolution up to 1080p while supporting a variety of aspect ratios. 

Kling utilizes diffusion-based transformer architecture (DiT), enhanced with Kuaishou's upgrades to the model's latent space encoding/decoding and temporal modeling modules. In terms of latent space encoding/decoding, Kuaishou has self-developed a 3D VAE network, achieving synchronous spatiotemporal compression and obtaining a high reconstruction quality, striking an excellent balance between training performance and effectiveness. In terms of temporal modeling, Kuaishou designed a computationally efficient, full-attention mechanism as a spatiotemporal modeling module. This method integrates temporal and spatial information, enabling comprehensive analysis and processing of video data. It can accurately capture local spatial features within video frames and temporal dynamic features across frames for a more comprehensive understanding and reproduction of motion information in videos. As a result, Kling can accurately capture details from rapidly moving objects, drastic scene changes, complex human movements and more, empowering dynamic, highly realistic video content generation. 

Kling is currently available for beta testing within "KuaiYing" (快影), Kuaishou's video editing application for users in China. Users may register and apply for a Kling trial through KuaiYing. For more information and a video demo, please visit Kling's official website at http://kling.kuaishou.com/

As a global leader in the short video industry, Kuaishou has developed a comprehensive AI strategy to usher in the large AI model era.  Large AI models offer a rich array of application scenarios for Kuaishou, seamlessly integrating with Kuaishou's content and commercial ecosystems. Kuaishou has already released "KwaiYii" (快意), a general large language model with 175 billion parameters, and "KeTu" (可图), a large model product for text-to-image generation, both of which have attracted widespread attention. Kling's launch demonstrates Kuaishou's commitment to accelerating the research, development and application of large models, aiming to provide creators and users with more diverse AI-powered creation and interactive experiences.

About Kuaishou

Kuaishou is a leading content community and social platform with its mission to be the most customer-obsessed company in the world. Kuaishou has relentlessly been focusing on serving its customers and creating value for them through the continual innovation and optimization of its products and services. At Kuaishou, any user can chronicle and share their life experiences through short videos and live streams and showcase their talents. Working closely with content creators and businesses together, Kuaishou provides product and service offerings that address various user needs that arise naturally, including entertainment, online marketing services, e-commerce, online games, online knowledge-sharing, and more.

Forward-Looking Statements

Certain statements included in this press release, other than statements of historical fact, are forward-looking statements. Forward-looking statements generally can be identified by the use of forward-looking terminology such as "may", "might", "can", "could", "will", "would", "anticipate", "believe", "continue", "estimate", "expect", "forecast", "intend", "plan", "seek", or "timetable". These forward-looking statements, which are subject to risks, uncertainties, and assumptions, may include our business outlook, estimates of financial performance, forecast business plans, growth strategies and projections of anticipated trends in our industry. These forward-looking statements are based on information currently available to the Group and are stated herein on the basis of the outlook at the time of this press release. They are based on certain expectations, assumptions and premises, many of which are subjective or beyond our control. These forward-looking statements may prove to be incorrect and may not be realized in the future. Underlying these forward-looking statements are a large number of risks and uncertainties. In light of the risks and uncertainties, the inclusion of forward-looking statements in this press release should not be regarded as representations by the Board or the Company that the plans and objectives will be achieved, and investors should not place undue reliance on such statements. Except as required by law, we are not obligated, and we undertake no obligation, to release publicly any revisions to these forward-looking statements that might reflect events or circumstances occurring after the date of this press release or those that might reflect the occurrence of unanticipated events.

For investor and media inquiries, please contact:
Kuaishou Technology
Investor Relations
Email: ir@kuaishou.com 

source: Kuaishou Technology

《說說心理話》 消費能獲取快樂?買不起,不如花光錢錢$$?「習得性無助」有何影響?一起看看正確理財觀念。► 即睇

人氣文章
財經新聞
評論
專題
專業版
HV2
精裝版
SV2
串流版
IQ 登入
強化版
TQ
強化版
MQ

【etnet 30周年】多重慶祝活動一浪接一浪,好禮連環賞!

【etnet30周年連環賞】睇住賞HIZERO F100 仿生潔地機(價值HK$3,980)

etnet榮獲HKEX Awards 2023 「最佳證券數據供應商」大獎

大國博弈

貨幣攻略

傾力救市

說說心理話

Watche Trends 2024

北上食買玩

Art Month 2024

理財秘笈

秋天養生食療

消委會報告

山今養生智慧

輕鬆護老