Introducing our new frontier video model, Runway Gen-4.5. Previously known as Whisper Thunder (aka) David. Gen-4.5 is state-of-the-art and sets a new standard for video generation motion quality, prompt adherence and visual fidelity. Learn more below.

@nvidia We are gradually rolling out access to Runway Gen-4.5. It will be available to everyone in the coming days. Learn more: https://t.co/VMMZBF5mzz

Gen-4.5 was developed entirely on @nvidia GPUs across initial R&D, pre-training, post-training and inference. We collaborated extensively with NVIDIA to push the boundaries of what's possible in video diffusion model optimization, from training efficiency to inference speed.

Gen-4.5 achieves an unprecedented level of physical accuracy and visual precision. Objects move with realistic weight and momentum. Surfaces behave the way they would in the real world. Laws of physics can be both observed or ignored, depending on your vision. Despite the big

The model excels at understanding and executing complex, sequenced instructions. You can specify detailed camera choreography, intricate scene compositions, precise timing of events and subtle atmospheric changes all within a single prompt. We remain committed to making highly

Two years ago, we introduced Gen-1, the first publicly available video generation model. It enabled an entirely new form of creative expression and created a new product category. Over the past two years, we've led the industry in making video models more powerful and

Runway Gen-4.5 represents significant advancements in both pre-training data efficiency and post-training techniques for video models and serves as our new foundation model for world modeling. Gen-4.5 scored 1,247 Elo points in the Artificial Analysis Text to Video leaderboard,

Audio nodes, new models and more new features and improvements in Workflows, a detailed custom Workflow walkthrough and a community spotlight. Get caught up on what happened This Week with Runway.

Try it now at

Introducing Audio Nodes for Runway Workflows. Now you can add various audio generation models directly to your custom workflows for even more creative control throughout your creative pipeline. All in one place. These four new nodes include: Text to Speech, Text to SFX, Voice

What a remarkable short film. Original. Good story, great art direction. One of the best I've seen recently. Originally a Gen-48 piece. If you have 5 minutes, watch this. Made with Runway. Made by Javier De La Chica and Guillermo Miranda

Do this with as many parts of the scene as you like. And that’s it, your own reality, reimagined with Runway. Try Workflows now at https://t.co/D0gm8lPjhC (6/6)

Step Four Bring your generated video back into your original high-res footage on your timeline. Scale and position it to sit within the larger scene. (5/6)

Step Three Use Workflows to chain together multiple steps and models all in a single interface. First, turn your sketch keyframe into a high fidelity generated image using a reference image of the item you’re looking to add to that scene. Then, use a clean plate of your shot

Step Two Sketch your desired composition on top of your exported still frame. (3/6)

Step One Import your 4K footage to a timeline and export a zoomed in still frame. (2/6)

Edit your reality with Runway. Learn how with the step by step breakdown below. (1/6)

Runway is helping the world’s leading companies, brands, enterprises, agencies, studios and organizations bring AI into their creative and production pipelines. Learn more about how your team can do the same at https://t.co/N1IA5c8kMR

Bring even more control and customization to your generative pipeline with Workflows. Combine multiple models, modalities and generative steps to get everything done all in one place. Learn how with today's episode of Runway Academy.

Workflows is an insanely powerful product. This short film was made entirely using the new Workflow interface. Really captures what’s now possible end-to-end inside Runway. Made by @ j.felipe.orozco in IG.