Runway Aleph
Runway Aleph is a state‑of‑the‑art in‑context video model that redefines multi‑task visual generation and editing by enabling a vast array of transformations on any input clip. It can seamlessly add, remove, or transform objects within a scene, generate new camera angles, and adjust style and lighting, all guided by natural‑language instructions or visual prompts. Built on cutting‑edge deep‑learning architectures and trained on diverse video datasets, Aleph operates entirely in context, understanding spatial and temporal relationships to maintain realism across edits. Users can apply complex effects, such as object insertion, background replacement, dynamic relighting, and style transfers, without needing separate tools for each task. The model’s intuitive interface integrates directly into Runway’s existing Gen‑4 ecosystem, offering an API for developers and a visual workspace for creators.
Learn more
Gen-3
Gen-3 Alpha is the first of an upcoming series of models trained by Runway on a new infrastructure built for large-scale multimodal training. It is a major improvement in fidelity, consistency, and motion over Gen-2, and a step towards building General World Models.
Trained jointly on videos and images, Gen-3 Alpha will power Runway's Text to Video, Image to Video and Text to Image tools, existing control modes such as Motion Brush, Advanced Camera Controls, Director Mode as well as upcoming tools for more fine-grained control over structure, style, and motion.
Learn more
Runway
Runway is an AI research and product company focused on building systems that simulate the world through generative models. The platform develops advanced video, world, and robotics models that can understand, generate, and interact with reality. Runway’s technology powers state-of-the-art generative video models like Gen-4.5 with cinematic motion and visual fidelity. It also pioneers General World Models (GWM) capable of simulating environments, agents, and physical interactions. Runway bridges art and science to transform media, entertainment, robotics, and real-time interaction. Its models enable creators, researchers, and organizations to explore new forms of storytelling and simulation. Runway is used by leading enterprises, studios, and academic institutions worldwide.
Learn more
Gen-4.5
Runway Gen-4.5 is a cutting-edge text-to-video AI model from Runway that delivers cinematic, highly realistic video outputs with unmatched control and fidelity. It represents a major advance in AI video generation, combining efficient pre-training data usage and refined post-training techniques to push the boundaries of what’s possible. Gen-4.5 excels at dynamic, controllable action generation, maintaining temporal consistency and allowing precise command over camera choreography, scene composition, timing, and atmosphere, all from a single prompt. According to independent benchmarks, it currently holds the highest rating on the “Artificial Analysis Text-to-Video” leaderboard with 1,247 Elo points, outperforming competing models from larger labs. It enables creators to produce professional-grade video content, from concept to execution, without needing traditional film equipment or expertise.
Learn more
