share_log

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

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

快手推出自有視頻生成模型“Kling”; 現已可供測試
PR Newswire ·  06/11 08:10

BEIJING, June 10, 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.

2024年6月10日,北京 / PRNewswire / - 快手科技(HKD Counter:01024 / RMB Counter:81024)(與其子公司及合併附屬實體共同稱爲“快手”),一家領先的內容社區和社交平台,最近推出了自主開發的視頻生成模型可靈(Kling)。Kling 能夠生成複雜的時空運動並模擬物理世界的特性。藉助這些能力,Kling 可將文本提示轉化爲高質量的 AI 視頻,其運動模式和物理特徵與真實世界的複雜運動模式和物理特徵密切相似。Kling 還具有強大的概念組合和想象能力。Kling 可以生成長達兩分鐘、幀率爲30fps、視頻分辨率最高可達1080p,並支持各種縱橫比的視頻。

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 採用擴散式轉換器結構(DiT),並通過快手對該模型的潛在空間編碼 / 解碼和時間建模模塊的升級進行了優化。在潛在空間編碼 / 解碼方面,快手自主開發了一個3D VAE網絡,實現了同步時空壓縮並獲得了高重建質量,在培訓性能和效果之間取得了良好平衡。在時間建模方面,快手設計了一種計算效率高、完全注意力機制的時空建模模塊。該方法整合了時間和空間信息,從而實現對視頻數據的全面分析和處理。它可以準確捕捉視頻幀內部的局部空間特徵以及跨幀的時間動態特徵,以更全面地理解和重現視頻中的運動信息。因此,Kling 能夠準確捕捉快速移動物體、劇烈場景變化、複雜人類動作等細節,從而實現動態、高度逼真的視頻內容生成。

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

Kling 目前可供中國用戶在快手的視頻編輯應用程序 KuaiYing 中進行測試。用戶可以在 KuaiYing 中註冊並申請 Kling 試用。有關更多信息和視頻演示,請訪問 Kling 的官方網站。

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.

作爲短視頻行業的全球領導者,快手製定了全面的人工智能戰略,迎接大型人工智能模型時代的到來。大型人工智能模型爲快手提供了豐富的應用場景,與快手的內容和商業生態系統完美融合。快手已經發布了擁有1750億參數的通用大語言模型 KwaiYii,以及文本到圖像生成的大型模型產品 KeTu,這兩個產品都引起了廣泛關注。Kling 的推出展示了快手加速大型模型的研究、開發和應用的承諾,旨在爲創作者和用戶提供更多樣化的基於人工智能的創作和交互體驗。

About Kuaishou

關於快手

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.

快手是一家以服務客戶爲使命的領先內容社區和社交平台,致力於通過不斷創新和優化產品和服務,爲用戶創造價值。在快手,任何用戶都可以通過短視頻和直播來記錄和分享他們的生活經歷,並展示他們的天賦。與內容創作者和企業緊密合作,快手提供了可滿足各種自然產生的用戶需求的產品和服務,包括娛樂、營銷服務、電子商務、網絡遊戲、在線知識共享等。

Forward-Looking Statements

前瞻性聲明

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.

除了歷史事實之外,本新聞稿中包含的某些描述均屬於前瞻性陳述。前瞻性陳述通常可通過採用前瞻性術語來識別,如“可能”、“會”、“可以”、“能”、“將”、“將會”、“預計”、“相信”、“持續”、“估計”、“期望”、“預測”、“打算”、“尋求”或“時間表”,等等。這些前瞻性陳述,受到風險、不確定性和假設影響,可能包括公司概述、財務表現估計、經營計劃預測、增長策略以及預期行業趨勢的投影。這些前瞻性陳述基於集團當前的資訊,在本新聞發佈時的展望,根據某些期望、假設和前提陳述。這些前瞻性陳述可能被證明是不正確的,並且未來可能不會被實現。在這些前瞻性陳述的背後,存在着大量的風險和不確定性。鑑於風險和不確定性,本新聞稿中包含的前瞻性陳述不應被視爲董事會或公司計劃和目標的表述,投資者不應過於依賴此類陳述。除非依據法律規定,否則我們沒有義務,也沒有義務公開發布任何關於這些前瞻性陳述的修訂版本,儘管這些版本可能反映了新聞發佈日期或未預料到事件的發生。

For investor and media inquiries, please contact:
Kuaishou Technology
Investor Relations
Email: [email protected]

投資者和媒體諮詢,請聯繫:
快手科技
投資者關係
電子郵件:[email protected]

SOURCE Kuaishou Technology

資料來源:快手科技

譯文內容由第三人軟體翻譯。


以上內容僅用作資訊或教育之目的,不構成與富途相關的任何投資建議。富途竭力但無法保證上述全部內容的真實性、準確性和原創性。
    搶先評論