HONG KONG, Dec. 2, 2025 -- 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 on December 1, 2025, Kling AI officially unveiled Kling O1, positioned as the industry's first unified multimodal creation tool. Powered by next-generation video and imaging architectures, Kling O1 integrates text, video, image, and subject inputs, consolidating all generation and editing tasks into a single, all-encompassing engine. This launch definitively resolves the "consistency challenge" regarding characters and scenes in AI video generation, providing a deeply integrated, one-stop solution tailored for film, television, social media, advertising, and e-commerce.

The Unified Model: A Paradigm Shift in Video Creation

As the pioneer of unified multimodal video models, Kling O1 is engineered on a Multimodal Visual Language (MVL) framework. It transcends the boundaries of traditional single-task video generation models by fusing a comprehensive spectrum of capabilities – including reference-based video generation, text-to-video generation, start and end frame generation, video in-painting (content insertion and removal), video modification and transformation, style re-rendering, and shot extension – into one versatile engine. This eliminates the need for creators to toggle between disparate models and tools; the entire creative lifecycle, from inception to refinement, is now a seamless, single-stream workflow.

Leveraging deep semantic reasoning, Kling O1 is able to interpret all user inputs – whether images, video clips, specific subjects, or text – as executable prompts. By removing modality constraints, Kling O1 achieves a holistic understanding of elements from multiple perspectives, generating output with pixel-perfect precision.

With its user-friendly multimodal prompt input interface, Kling O1 transforms complex post-production editing into a simple, conversational experience. Bypassing the need for manual masking or keyframing, users can simply input prompts such as "remove passersby," "transition day to dusk," or "swap the protagonist's attire." Kling O1 decodes the visual logic, executing pixel-level semantic reconstruction – ranging from targeted subject replacement to full-frame style re-rendering. In addition, Kling O1 supports a full suite of editing functions, including image/subject referencing, video content editing, shot transitions, first- and last-frame generation, and text-to-video generation.

Addressing the critical pain point of character and scene inconsistency in real-world AI video adoption, Kling O1 features enhanced foundational comprehension of images and videos. Acting with "director-like memory," the model retains the identity of main characters, props, and settings, ensuring feature stability amidst dynamic camera movements. Furthermore, the model excels in multi-subject integration. Users can mix and match multiple subjects or blend them with reference images. Even in complex group scenes or interactive scenarios, Kling O1 independently tracks and preserves the fidelity of each character and prop, delivering industrial-grade consistency across all shots.

Kling O1 enables "skill combos," transcending single-task limitations. Users can command the model to "insert a subject while simultaneously modifying the background context" or "generate from a reference image while shifting the artistic style." This capacity to execute a compound creative variation in a single pass exponentially expands creative freedom and flexibility, enabling a true alchemy of ideas.

Regarding video duration, Kling O1 restores temporal control to the creator, supporting generation lengths between 3 and 10 seconds. Whether crafting a brief visual impact or a sustained narrative arc, pacing is entirely user-defined. Notably, as part of the unified model, Kling O1's first- and last-frame capabilities will soon support the 3-10 second range, further enhancing narrative flexibility.

Kling AI also unveiled the Kling O1 image model, enabling seamless end-to-end workflows from basic image generation to advanced detail editing. Users can generate images from text alone or upload up to 10 reference images to inspire and guide new creations. The model offers four key advantages. First, it ensures high feature retention, keeping subject elements stable and consistent. Second, it offers high-precision detail editing, aligning every adjustment with user expectations. Third, it maintains accurate style control, ensuring a consistent visual tone throughout. Fourth, it delivers exceptionally rich creativity, enabling more dynamic and expressive creative outputs, truly making "what you envision is what you get" a reality.

One Model, Diverse Creative Scenarios: Empowering Film, Television, Social Media, Advertising, and E-Commerce

Combining both generation and editing into a single solution, the all-new Kling O1 is uniquely adapted for film, television, social media, advertising, and e-commerce scenarios. Whether building narratives from scratch or restructuring existing element, Kling O1 flexibly leverages its referencing and editing capabilities to streamline production.

In film and television production, utilizing robust image (subject) consistency and a dedicated subject library, Kling O1 maintains strict continuity of characters, costumes, and props across every shot, effortlessly generating coherent cinematic sequences. For video editors and social media creators, with prompts as simple as "remove passersby from the background" or "enhance sky color," Kling O1 automatically performs pixel-level intelligent repair and reconstruction.

To mitigate the high costs and logistical friction of traditional offline advertising shoots, with Kling O1, users can upload images of products, models, and scenes, add a few simple prompts, and rapidly generate multiple high-impact product showcase ads, significantly cutting production costs. To solve the hassles of scheduling models and outfit changes, Kling O1 allows for a 24/7 virtual runway. By uploading model and clothing images and inputting prompts, Kling O1 flawlessly renders fabric textures and details, producing high-quality video lookbooks at scale.

Kling O1's robust and full-featured capabilities are driven by groundbreaking innovations in its technical architecture. The brand-new Kling O1 video model dismantles traditionally fragmented video generation, editing, and comprehension features, creating a next-generation unified generative foundation. By combining the Multimodal Transformer with built-in multimodal comprehension and multimodal long-context, Kling O1 thoroughly integrates diverse tasks into a single, cohesive workflow.

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