Runway’s Gen-3 Alpha is available now for everyone and it’s wild. What’s the whole fuss about? Well, it’s been a few weeks since Gen-3 Alpha was announced, offering users the ability to create hyper-realistic AI videos from text, image, or video prompts. As of today, widespread access is rolling out, allowing anyone signed up on the RunwayML platform to leverage the model’s high fidelity and controllable outputs for various creative applications. This includes advertising! Something has changed though, and we’re not talking specs. Unlike the Gen-1 and Gen-2 models, Gen-3 Alpha is not available for free. Users will need to upgrade to a paid plan from the company, with prices starting at $12 per month per editor, billed annually. Since the last Runway’s update much have changed in the world of text to video AI models, with Pika, Stability AI, OpenAI, and most recently Luma Labs releasing their offerings.

Gen-3 Alpha is the first of an upcoming series of models trained by Runway on a new infrastructure built for large-scale multimodal training. It is a major improvement in fidelity, consistency, and motion over Gen-2, and a step towards building General World Models, systems that will understand the visual world and its dynamics. We’re talking real DYNAMICS. Just check out the examples we have managed to scout from the X. Put your seatbelts on.

Key Highlights include:

Visual Excellence: GEN-3 delivers exceptional visual fidelity, consistency, and fluid motion, purpose-built for creative applications.

Expressive Characters: Capable of generating realistic human emotions, actions, and gestures.

Versatile Shots: Excels in POV and drone footage, ensuring smooth transitions between locations.

Industry Customization: Developed in collaboration with entertainment and media organizations to provide tailored solutions.

Learn more about the release on the RunwayML official site here. Definitely worth the time.