GEN-2 Now Available!

“Deep neural networks for image and video synthesis are becoming increasingly precise, realistic, and controllable. In a couple of years, we have gone from blurry low-resolution images to both highly realistic and aesthetic imagery allowing for the rise of synthetic media.” - Runway AI

Runway, a leading AI software company, has unveiled the highly anticipated second generation of its groundbreaking AI software, aptly named Runway AI Gen-2. This new release marks a significant leap forward from its predecessor, offering unprecedented capabilities in text-to-video synthesis. Unlike its older version, which relied solely on existing video data, Runway AI Gen-2 can now generate complete videos based solely on textual descriptions.

Over the past year, Runway has dedicated extensive efforts to developing this innovative model, and they are proud to announce that it is the first text-to-video AI model available to the general public. The company asserts that their novel approach empowers users to create realistic and consistent synthesized videos through two different methods. Firstly, users can leverage the composition and style of an image or text prompt, applying them to the structure of a source video—a feature inherited from Gen-1. Alternatively, users can now generate entirely new videos using only text prompts, a remarkable advancement.

While Gen-1 primarily focused on modifying existing videos by allowing users to enhance shaky smartphone clips or crude 3D animations with AI-generated overlays, Runway AI Gen-2 is a remarkable improvement. It combines the best qualities of both generations, enabling the application of composition and style from image or text prompts to create entirely new videos. The outcome of this innovation is truly astonishing—Runway AI Gen-2 can now generate fresh video content based solely on textual descriptions.

Accessible through a user-friendly web-based platform, Runway AI Gen-2 produces videos with a commendable level of resolution. Although not yet reaching photorealistic quality, these videos showcase the immense potential of the technology. In comparison to existing offerings in the market, the videos produced by Gen-2 Runway AI are exceptional, pushing the boundaries of what is currently available.

With Runway AI Gen-2, the possibilities for video creation have expanded exponentially. This significant advancement in text-to-video synthesis technology not only offers users greater creative freedom but also sets a new standard for AI-driven video generation. As Runway continues to push the boundaries of AI innovation, we eagerly anticipate the future developments and applications this remarkable platform will bring.

Learn more about this new generation of Runway tools, here: https://runwayml.com/ai-magic-tools/gen-2/

Richard Cawood

Richard is an award winning portrait photographer, creative media professional and educator currently based in Dubai, UAE.

http://www.2ndLightPhotography.com
Previous
Previous

SUMMER ON THE HORIZON

Next
Next

AI REFLECTIONS NOW ON YOUTUBE