AI-powered video creator Runway has officially launched its new Gen-3 Alpha model, after teasing its debut a few weeks ago. The Gen-3 Alpha video creator brings major upgrades to creating hyper-realistic videos based on user prompts, and is a significant step up from the Gen-2 model released early last year.
Runway’s Gen-3 Alpha is aimed at a range of content creators, including marketing and advertising groups. The startup claims to outperform all competitors when it comes to handling complex transitions, as well as key-framing and human characters with expressive faces. The model was trained on a large video and image dataset with descriptive captions, allowing it to generate highly realistic video clips. At the time of writing, the company is not disclosing the sources of its video and image datasets.
The new model is accessible to all users who have signed up on the RunwayML platform, but unlike Gen-1 and Gen-2, Gen-3 Alpha is not free. Users will have to upgrade to a paid subscription, with prices starting at $12 per month per editor. This move suggests that Runway is ready to professionalize its products after having a chance to refine them, thanks to all the people playing with the free models.
Initially, Gen-3 Alpha will power Runway’s text-to-video mode, allowing users to create videos using natural language prompts. In the coming days, the model’s capabilities will be expanded to include image-to-video and video-to-video modes. In addition, Gen-3 Alpha will be integrated with Runway’s control features, such as Motion Brush, Advanced Camera Controls, and Director Mode.
Runway said that Gen-3 Alpha is just the first in a new series of models built for large-scale multimodal training. The end goal is what the company calls “General World Models,” which will be able to represent and simulate a wide range of real-world situations and interactions.
AI video race
The immediate question is whether Runway’s advancements can match or surpass what OpenAI is doing with its attention-grabbing Sora model. While Sora promises one-minute videos, Runway’s Gen-3 Alpha currently supports video clips that are only 10 seconds long. Despite this limitation, Runway is betting on the speed and quality of Gen-3 Alpha to differentiate it from Sora, at least until it can scale up the model as it has planned, allowing it to produce longer videos.
The race isn’t all about Sora. Stability AI, Pika, Luma Labs and others are all vying for the title of best AI creator. With the competition heating up, Runway’s release of Gen-3 Alpha is a strategic move to take a leading position in the market.