Gen-3 Alpha Text to Video is now available to everyone. A new frontier for high-fidelity, fast and controllable video generation. Try it now at

Today we are releasing Frames. Our most advanced base model for image generation, offering unprecedented stylistic control and visual fidelity. Learn more below. (1/10)

Runway meetups around the world continue. Next stop is Seoul. Join us on Jan 20th

As AI reshapes creative work, many worry it will diminish the artist's role. I think pretty much the opposite. The artist's purpose becomes more vital. As new tools unleash boundless streams of imagery, scripts, sounds, and concepts, the critical human skill shifts from the craft of making each element by hand to the art of selection and refinement: curation. What matters most is taste, judgment, and a guiding vision. The artist's craft is to select what resonates, refine what inspires, and discard what feels hollow. Like a gardener tending a sprawling garden, the human hand chooses which saplings to nurture and which to prune. Far from making the artist obsolete, this shift places a premium on something distinctly human—taste, perspective, sensitivity. It's the rise of the creative director-producer hybrid: part auteur, part curator, part cultural filter. Creativity is shifting from production to taste-making at scale.

Today we’re sharing an early video keyframing prototype that treats creative exploration like a search process of all latent artistic possibilities. One which allows you to simultaneously navigate this vast space with both precise control as well as serendipitous nonlinear discovery. (1/8)

Introducing Frames: An image generation model offering unprecedented stylistic control. Frames is our newest foundation model for image generation, marking a big step forward in stylistic control and visual fidelity. With Frames, you can begin to architect worlds that represent very specific points of view and aesthetic characteristics. See below for examples. World 1089: Mise-en-scène (1/11)