Runway’s AI video creation and editing service has added a promised video-to-video revamp feature to its Gen-3 Alpha model platform. The video-to-video tool lets you submit a video and a text prompt for modification. The changes can change the setting, artists or other elements of the video to match the text prompt or one of a handful of preset style suggestions.
Video-to-video is the latest major addition to Runway’s video creation capabilities. Runway already allows users to start with text or images to define the look and motion of the video. Now, starting with a real video, users can pre-define the motion and then use AI to modify the design and aesthetic. Runway trained the feature on a large set of videos and images with subtitles, with details to teach the AI model how to understand uploaded movies and the prompts to modify them. It’s like seeing a new video from a completely different universe. You can see how it works below.
“Video to Video represents a new control mechanism for precise movement, expressiveness and intent across generations,” Runway explained on social media. “To use Video to Video, simply upload your input video, prompt in any aesthetic direction you desire, or choose from a collection of preset styles.”
Film Multiverse
Combined with Gen-3 Alpha’s existing ability to handle complex transitions and expressive human faces and emotions, the results can be quite spectacular. Runway has been quick to expand Gen-3 Alpha with new options. The company recently showed off the Gen-3 Alpha Turbo version of its model, which sacrifices some functionality for speed. In addition to the video-to-video makeover option, the tool also works with Motion Brush, Advanced Camera Controls, Director Mode, and other, more detailed video editing features.
Gen-3 Alpha comes across as much more versatile and user-friendly than the Gen-2 model. That said, it does have limitations despite its impressive output. Currently, it can generate video clips of up to 10 seconds long, barely a feature film. Speed and quality can compensate for that until it can do longer. However, there is increasing competition for Runway to outdo.
The most famous is OpenAI’s Sora model, but it’s far from the only one. Stability AI, Pika, Luma Labs’ Dream Machine and more are all working to bring AI video models to the public. Even TikTok’s parent company, Bytedance, has an AI video maker named Jimeng.
If you’d like to try out Runway’s video to video tool, Gen-3 Alpha is available to users with paid plans starting at $12 per month.