Runway’s new Gen-4.5 Image to Video Tool is claimed to allow users to transform any static image, regardless of whether it’s real, generated, sketched, or illustrated, into a dynamic video.
Key features
- Generate photorealistic and consistent characters
- Create epic establishing shots and dynamic chase sequences
- Produce big-budget visual effects
- Develop product shots and advertisements
Two years ago, Runway released Gen-1, the first publicly available video generation model. Since that time, Runway has been one of the leaders in the industry in making video models more powerful and controllable.
Runway Gen-4.5 pushes the technology of video generation even further. It is claimed to represent significant advances in both pre-training data efficiency and post-training techniques. The goal of Gen-4.5 is to set new standards for dynamic, controllable action generation, temporal consistency and precise controllability across diverse generation modes. With 1,247 Elo points, Gen-4.5 is said to currently hold the top position in the Artificial Analysis Text to Video benchmark, surpassing all other models.
Gen-4.5 was developed entirely on NVIDIA GPUs across initial R&D, pre-training, post-training, and inference. Inference runs on NVIDIA Hopper and Blackwell series GPUs.
According to Runway, despite the leap in capabilities, the model exhibits several limitations common to video generation models:
- Causal reasoning: effects sometimes precede causes (e.g., a door opening before the handle is pressed).
- Object permanence: objects may disappear or appear unexpectedly across frames (e.g., a cup vanishing after being occluded).
- Success bias: actions disproportionately succeed (e.g., a poorly aimed kick still scoring a goal).
