Gen-3 Alpha

Gen-3 Alpha is the pioneering model in Runway's next generation of foundation models, designed to revolutionize AI-driven video creation. Launched in June 2024, it represents a substantial advancement over its predecessor, Gen-2, with enhanced fidelity, consistency, and motion capabilities. Built on a new large-scale multimodal training infrastructure, Gen-3 Alpha powers Runway's Text to Video, Image to Video, and Text to Image tools, as well as advanced control modes such as Motion Brush and Camera Controls. This model is aimed at expanding the creative horizons in video generation and editing, making it a powerful tool for professionals in film, advertising, social media, and beyond.

Gen-3 Alpha's key features include high-fidelity video generation, advanced control features for detailed prompt specification, multimodal capabilities supporting text-to-video, image-to-video, and text-to-image creation, temporally dense captions for precise scene manipulation, and integrated safeguards for responsible AI use. These features make it a versatile and robust solution for various creative and professional needs.