Gen-4.5:全球最强视频模型

Runway Gen-4.5: Best-in-class AI video generation model

State-of-the-art motion quality, prompt adherence and visual fidelity built on NVIDIA Hopper and Blackwell GPUs.

December 1, 2025

by Runway

Introduction

Runway Gen-4.5 is the world's top-rated video model, offering unprecedented visual fidelity and creative control. It produces cinematic and highly realistic outputs while providing limitless creative freedom and precise control over every aspect of generation.

Runway Gen-4.5: State-of-the-Art AI Video Generation

Two years ago, we released Gen-1, the first publicly available video generation model. It enabled an entirely new form of creative expression and a new product category. Since then, we've led the industry in making video models more powerful and controllable, from significant base model improvements to new controls and general in-context capabilities. Runway Gen-4.5 pushes the frontier of video generation even further. It represents significant advances in both pre-training data efficiency and post-training techniques. Gen-4.5 sets new standards for dynamic, controllable action generation, temporal consistency and precise controllability across diverse generation modes. With 1,247 Elo points, Gen-4.5 currently holds the top position in the Artificial Analysis Text to Video benchmark, surpassing all other models.

Gen-4.5 maintains the speed and efficiency of Gen-4, delivering breakthrough quality without compromising performance. Available at comparable pricing across all subscription plans, Gen-4.5 makes world-leading video generation accessible to creators and organizations at every scale. We’ll also be bringing all existing control modes (Image to Video, Keyframes, Video to Video and more) to Gen-4.5.

Evolution of Video Generation

Gen-4.5 achieves unprecedented physical accuracy and visual precision. Objects move with realistic weight, momentum and force. Liquids flow with proper dynamics. Surface details render at great fidelity. And fine details like hair strands and material weave remain coherent across motion and time.

Complex Scenes

Intricate, multi-element scenes rendered with precision.

1 / 3

Detailed Compositions

Precise placement and fluid motion for both objects and characters.

1 / 3

Physical Accuracy

Realistic physics with believable collisions and natural movement.

1 / 3

Expressive Characters

Nuanced emotions, natural gestures and lifelike facial detail.

1 / 3

Gen-4.5 can handle a wide range of aesthetics, from photorealistic and cinematic to stylized animation, while maintaining a coherent visual language.

Photorealistic

Visuals indistinguishable from real-world footage with lifelike detail and accuracy.

1 / 3

Non-photorealistic

Stylized, expressive motion with artistic freedom unconstrained by realism.

1 / 3

Slice of Life

Everyday scenes and environments with authentic, true-to-life detail.

1 / 3

Cinematic

Emotionally powerful visuals with striking depth and cinematic polish.

1 / 3

High-performance

Built on NVIDIA

Gen-4.5 was developed entirely on NVIDIA GPUs across initial R&D, pre-training, post-training and inference. We collaborated extensively with NVIDIA to push the boundaries of what's possible in video diffusion model optimization, from training efficiency to inference speed. Inference runs on NVIDIA Hopper and Blackwell series GPUs, delivering optimized performance without compromising quality.

“

This is an incredibly exciting time for video and world models.

We’re proud that Runway built their groundbreaking video and world model on NVIDIA GPUs, and are thrilled to see Runway revolutionize the video generation industry.

Together, we are partnering to advance the entire lifecycle of AI from pretraining, to post-training and inference.”

Jensen Huang

President and CEO of NVIDIA

Select Early Access Enterprise Partners

Marketing & Advertising

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).

These limitations are particularly important in our work on world models, which need to accurately represent the outcomes of actions taken in the environment. We are actively researching ways to address them.

Generated with Runway Gen-4.5

Gen-4.5 is available across all paid Runway plans.

Try now