After teasing its debut a few weeks ago, Runway, the artificial intelligence-powered video maker, has officially launched its new Gen-3 Alpha model. The Gen-3 Alpha video creator has been significantly upgraded in its ability to create ultra-realistic videos based on user instructions, which is a huge step forward from the Gen-2 model released early last year.
Runway's Gen-3 Alpha is targeted at a variety of content creators, including marketing and ad groups. The startup claims it's better than any of its competitors when it comes to handling complex transitions, keyframes, and expressive people. The model is trained on a large dataset of descriptively captioned videos and images, allowing it to generate highly realistic video clips. As of this writing, the company has not revealed the source of its video and image datasets.
The new model is available to all users who sign up to the RunwayML platform, but unlike Gen-1 and Gen-2, Gen-3 Alpha is not free. Users will need to upgrade to a paid plan, with pricing starting at $12 per editor per month. This move suggests that Runway is ready to professionalize the product after having a chance to refine it thanks to all the users playing with the free model.
Initially, Gen-3 Alpha will be featured in 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. Additionally, Gen-3 Alpha will be integrated with Runway's control features, including motion brushes, advanced camera controls, and director mode.
Runway says Gen-3 Alpha is just the first in a new series of models built for large-scale, multi-modal training, with the end goal being what the company calls “general-world models” that will be able to represent and simulate a wide range of real-world situations and interactions.
View
AI Video Race
The immediate question is whether Runway's progress can match or surpass OpenAI's much-talked-about Sora model. While Sora promises one-minute videos, Runway's Gen-3 Alpha currently only supports video clips up to 10 seconds long. Despite this limitation, Runway hopes to differentiate itself from Sora with the speed and quality of its Gen-3 Alpha, at least until it can expand its model to produce longer videos as planned.
The competition isn't just Sora's problem, with other companies like Stability AI, Pika, and Luma Labs all vying to claim the title of best AI video creator. As the competition heats up, Runway's release of Gen-3 Alpha is a strategic move to establish a leading position in the market.
