Kling AI Launches 3.0 Model Series with Multimodal Video and Image Generation

The AI-powered creative platform Kling AI has launched its Kling 3.0 model series, announced in a press release. The lineup includes Video 3.0, Video 3.0 Omni, Image 3.0, and Image 3.0 Omni, designed to provide greater narrative control and improved consistency in AI-generated videos and images.

The Video 3.0 model supports video generation up to 15 seconds with enhanced shot consistency, photorealistic output, and native audio generation in multiple languages and accents. It also enables creators to produce multi-character dialogue scenes and manage complex multi-shot storytelling with dynamic camera control.

Video 3.0 Omni adds advanced reference-based generation and a new multi-shot storyboard feature, allowing users to specify parameters such as shot duration, perspective, and camera movements. For still visuals, Image 3.0 and Image 3.0 Omni deliver ultra-high-resolution output up to 4K with accurate texture and lighting preservation.

All models are built on Kling AI’s unified multimodal framework, integrating text, image, audio, and video inputs for seamless creation and editing. The Kling 3.0 models are available for early access to Ultra subscribers, with wider availability expected soon.