We are also bringing Gen-4 Image Turbo to all web users allowing you to generate with reference images in 10 seconds or less. Gen-4 Image Turbo costs 2.5-4x less than non-turbo and achieves a 93.3% quality Dreambench++ Score compared to standard Gen-4 Image generations. Turbo is

Runway Aleph can accurately remove subjects from your scene. Even with complex motion, lighting conditions and passing foreground occlusions. All you need to do is tell Aleph what you want.

Runway Aleph can seamlessly add new objects and effects to existing footage. Matching lighting, color temperature and motion. All you need to do is tell Aleph what you want.

Nico has access to the same models that I do. His videos are orders of magnitude better. There’s a lesson here.

The normalization of magic. The fact that you can do all of this in a few minutes inside Runway is still pretty wild to me.

Imagine a world where anyone can create any world they want. This world is coming, very soon.

This is exactly what is needed. To stop. Take a step back. Break the flow of the news cycle and speak the truth: that Islamophobia is socially accepted in the West. That these people are racist. And deserve to be treated as such. That this racism needs to end. Now.

Justine Moore Feels a bit underwhelming? Not sure but a lot of hype for something that has existed for months and with better results. Nano Banana for video is Aleph: runwayml.com/research/intro…

From being one of a kind to being the best of a kind.

Tune in to see what we've been building! Runway youtube.com/live/OnXu-6xec… via YouTube

Today we shared five exciting announcements across both product and research that outline our future vision for how AI will change how stories are told, scientific progress is made and how the next frontiers of humanity are reached. Learn more below about how we’re building AI

Our third announcement is GWM Worlds. A world model for real-time environment simulation. You give the model a static scene, and it generates an immersive, infinite, explorable space as you move through it, with geometry, lighting and physics. All in real-time. You can travel

Gen-4.5 is now live, and we have many incredible updates to follow! Excited to share our team's work with the world and can't wait to see everyone's creations!

So, you’re into AI? Name every token

A short statement on our mission ahead: to train generalist models directly on observations from the universe, in what we believe will be the most important (and fun) technological quest of our time.

It's been an incredible joy to work on this. So proud of the team and excited to share Gen-4.5 I2V with everyone.

claude --dangerously-skip-permissions

I've been obsessing over Runway Gen-4.5 this past week. I tested it quite extensively, and I noticed a few things that should be fundamental to any video model: 1. Amazing spatial awareness. It just knows what comes next in the scene and renders it perfectly, with the correct

Gen-4.5 has a very specific and special way of making things move naturally, realistically, and surprisingly.