HONG KONG, April 15, 2025 (GLOBE NEWSWIRE) -- Kuaishou Technology (“Kuaishou” or the “Company”; HKD Counter Stock Code: 01024 / RMB Counter Stock Code: 81024), a leading content community and social platform, announced that Kling AI hosted the “From Vision to Screen” launch event for its Kling AI 2.0 Model in Beijing. The event marked a new round of upgrades to Kling’s foundation models, highlighted by the official global debut of Kling AI 2.0 Video Generation Model and Kling AI 2.0 Image Generation Model.
As the world’s first user-accessible DiT video generation model, in the 10 months since its initial launch in June of last year, its global user base has surpassed 22 million. On March 27, Artificial Analysis, a globally renowned AI benchmarking organization, released the latest global rankings for video generation large models. Kuaishou Kling 1.6 Pro (high-quality mode) topped the Image to Video category with an Arena ELO benchmark score of 1,000, while Google Veo 2 and Pika Art ranked second and third, respectively.
Since its launch in June of last year, Kling AI has undergone over 20 iterations focused on enhancing the fundamental quality of its models, improving image clarity, and introducing more innovative features to meet diverse user needs. Mr. Gai Kun, Senior Vice President of Kuaishou Technology and Head of the Community Science Department, emphasized that Kling AI’s mission is to empower everyone to tell great stories with AI, enabling more precise and complex creative expression.
Kling AI Advances to the 2.0 Era, Redefining Human-AI Interaction Kling AI 2.0 leads the global industry in areas such as motion quality, semantic responsiveness, and visual aesthetics. Meanwhile, the Kolors 2.0 Model has made significant advancements in prompt adherence, cinematic quality, and artistic style expression. Mr. Gai Kun highlighted that in the team’s internal multi-metric tests and evaluations with GSB (Good-Same-Bad) methodology, both models have consistently ranked No.1 in the industry. For instance, in the image-to-video category, Kling AI 2.0 has a win-loss ratio of 182% against Google Veo2 and 178% against Runway Gen-4, significantly outperforming its rivals in dimensions such as semantic responsiveness, visual quality, and dynamic quality.
Mr. Gai Kun, Senior Vice President of Kuaishou Technology and Head of the Community Science Department
(Mr. Gai Kun, Senior Vice President of Kuaishou Technology and Head of the Community Science Department)
Mr. Gai Kun believes that AI holds immense potential for assisting creative expression, but current industry conditions fall short of meeting user needs. There are still “numerous challenges” regarding the stability of AI-generated content and the precise expression of users’ complex creative ideas. Therefore, to truly realize the vision of “telling great stories with AI,” it is essential to comprehensively enhance foundation models’ capabilities and define a “new language” for human-AI interaction.
In this 2.0 model iteration, Kling AI officially introduces multi-modal visual language (MVL), a new interactive concept for AI video generation. This feature allows users to integrate multimodal inputs, such as image references and video clips, enabling them to convey complex creative ideas effectively and directly to AI, covering aspects such as identity, appearance, style, scenarios, actions, expressions, camera movements, and other elements.
"It's clear that text alone is insufficient for conveying visual information. We need a new approach that allows people to accurately express their thoughts," Mr. Gai Kun pointed out. He explained that MVL consists of TXT (Pure Text) and MMW (Multi-modal-document as a Word), which facilitate precise creative expression for AI-empowered creators through two key aspects: setting foundational direction for video generation and enabling fine-tuned control.
Based on the MVL concept, Kling AI has officially introduced its multimodal editing feature. "Starting today, our multimodal editing capabilities are available on the Kling AI platform. Users can directly input their ideas through images and other formats, generating creative videos that align with their concepts," explained Mr. Gai Kun. He further highlighted that MMW will extend beyond images and videos, incorporating other forms of information such as voice and motion trajectories, allowing users to express themselves in more diverse ways.
"From Vision to Screen" Kling AI 2.0 Launch Event
("From Vision to Screen" Kling AI 2.0 Launch Event)
Kling AI 2.0 Master Edition Officially Launched, Unveiling the All-New Multimodal Video Editing Feature Leveraging the innovative MVL interaction approach,Mr. Zhang Di, Vice President of Kuaishou Technology and Head of Kling AI, officially unveiled the all-new Kling AI 2.0 Master Edition at the launch event. This new version significantly enhances content generation performance in areas such as semantic responsiveness, motion quality, and visual aesthetics. These upgrades include significant improvements in following instructions, enhanced movie aesthetic expression, and support for over 60 types of stylized effect transcription, achieving a significant leap in creativity and imagination for image generation.
Mr. Zhang Di, Vice President of Kuaishou Technology and Head of Kling AI
(Mr. Zhang Di, Vice President of Kuaishou Technology and Head of Kling AI)
Notably, the Kling AI 2.0 Master Edition features a comprehensive upgrade in controllable video and image generation and editing capabilities. The newly-introduced multimodal video editing function efficiently captures user intent. With a video clip, users can add, remove, or replace content elements generated in the video by inputting images or text, empowering creators with greater flexibility in editing and processing.
At the same time, Kolors 2.0 has also launched practical image controllable editing functions, including partial redrawing and expanding, and supporting image addition, modification and repair. For multimodal controllable image generation, Kolors 2.0 has also launched a brand-new stylized transcription function, which allows users to switch an image’s artistic style in one click by simply uploading the image with a style description, while precisely retaining the semantic content of the original image.
Kling AI 2.0 Master Edition Operation Interface
(Kling AI 2.0 Master Edition Operation Interface)
Mr. Zhang Di stated that currently, image-generated video accounts for about 85% of Kling AI video creation, with image quality playing a crucial role in video generation effects. In the realm of large image generation models, Kuaishou Kolors leads the industry with several core advantages, such as powerful complex semantic understanding, movie-level visual quality, and controllable stylized generation under multiple conditions. In a number of internal team win-loss reviews, it maintains a significant advantage over industry-leading image models such as Midjourney V7, FLUX 1.1 Pro, and Reve.
"Kling AI 2.0 Master Edition is not just a technical upgrade, but a full-spectrum leap in user experience," Mr. Zhang Di noted. The Kling AI 2.0 Master Edition achieves breakthroughs in technology, user experience, and aesthetics.
The Rapid Development of AIGC Technology Has Injected New Vitality into Industry Development In addition to a subscription service for individual users, Kling AI also offers API interface solutions and other services to businesses. Currently, Kling AI has partnered with thousands of domestic and overseas enterprises, including Xiaomi, Amazon Web Service, Alibaba Cloud, Freepik, and BlueFocus.
Mr. Gai Kun noted that over 15,000 developers and business clients worldwide have applied Kling API in various industry scenarios, cumulatively generating about 12 million images and over 40 million videos. Today, Kling AI is becoming the new infrastructure for video creation in the AI era, and the rapid development of AIGC technology is reshaping many industries, such as advertising and marketing, professional creation, film and television, and entertainment and creativity.
Mr. Chen Xiangyu, one of the Kling AI super creators, general director of New World Is Loading, and founder of the media company named Outliers, shared that Kling AI can be fully integrated into the episode creation process. AIGC not only improves efficiency but also revolutionizes the trial-and-error space compared to live shooting and animation. From scriptwriting to content distribution, the Outliers team has completed a comprehensive image industrialization creation process, covering everything from aesthetic expression to lens structure to the intricate presentation of complex action scenes and details. “Through practice, we found that Kling AI is a generative collaborative large model that can be stably and massively embedded into the episode creation process,” Mr. Chen Xiangyu commented. With AI’s assistance, the director and scriptwriting team have brought more of their ideas to life with greater imagination. “AIGC may be the prototype of the next generation of content structure,” said Mr. Chen Xiangyu.
Mr. Chen Xiangyu Keling AI Super Creator, General Director of New World Is Loading, Founder of the media company named Outliers
(Mr. Chen Xiangyu Keling AI Super Creator, General Director of New World Is Loading, Founder of the media company named Outliers)
To further inspire the creative passion of AI enthusiasts, Mr. Zhang Di, Vice President of Kuaishou Technology and Head of Kling AI, also officially launched the “Kling AI NextGen New Image Venture Capital Program” at the event. This program aims to increase support for AIGC creators through millions of RMB in capital investment, global publicity and distribution, and IP creation and protection, facilitating the global dissemination of compelling AI stories through various flexible collaborations such as wholly-owned production, co-production and technical support, among other means. Meanwhile, Kling AI has extended invitations to global creators to jointly create the world’s first user-co-created AIGC creative short film, showcasing creators’ inspiration and creativity on advertising screens in cities like Shanghai, Hong Kong, Tokyo, Paris, and Toronto.
Looking to the future, Mr. Gai Kun stated that Kling AI will continue to vigorously promote technological innovation and help users realize the precise expression of complex creative ideas through a new language for human-AI interaction. “Our goal is to empower everyone to tell a good story through AI, and we’re striving to make that a reality sooner,” concluded Mr. Gai Kun.
About Kuaishou
Kuaishou is a leading content community and social platform in China and globally, committed to becoming the most customer-obsessed company in the world. Kuaishou uses its technological backbone, powered by cutting-edge AI technology, to continuously drive innovation and product enhancements that enrich its service offerings and application scenarios, creating exceptional customer value. Through short videos and live streams on Kuaishou's platform, users can share their lives, discover goods and services they need and showcase their talent. By partnering closely with content creators and businesses, Kuaishou provides technologies, products, and services that cater to diverse user needs across a broad spectrum of entertainment, online marketing services, e-commerce, local services, gaming, and much 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
