Introducing Runway Aleph, a new way to edit, transform and generate video. Aleph is a state-of-the-art in-context video model, setting a new frontier for multi-task visual generation, with the ability to perform a wide range of edits on an input video such as adding, removing

Apply now:

The Runway Student Ambassador Program now spans 21 countries across North America, Europe, Asia and Africa at more than 70 different premiere institutions including: USC, UC Berkeley, UCLA, Columbia, NYU, Harvard, Yale, UBC, Swiss Federal Institute of Technology Lausanne,

Art always evolves and has proven to be much more complex than we first imagined. New forms of creative expression are emerging with AI, and we need to give voices to people who never had them before. We need to recognize and protect the creative freedom that new technologies

Read more:

Director Jon Erwin discusses how his Amazon Prime show, House of David used Runway to achieve his outsized creative vision while staying within budget and shaving off months of tedious work. Learn more at the link below. Season two of House of David is streaming now on Amazon

Read more:

Eggplant Picture & Sound talks about how they brought Runway into their VFX pipeline to get the History Channel's, "Life After People" on air and under budget. Read the full interview at the link below.

Imagine a world where you can build any workflow. A new Runway is coming soon.

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

https://t.co/PAHPyqCGEz

The Runway Student Ambassador Program spans the world's top educational institutes and is designed to help students prepare for careers across creative industries. Ambassadors receive complimentary credits, plans, networking opportunities and more. If you're interested in

Writer and Grammy nominated musician, Claire Evans sits down to talk with celebrated novelist, Stephen Marche. The two discuss everything from the advent of film to the indestructible nature of human creativity.

Today we're launching the Runway API Playground—a new interactive environment that lets developers test and refine their integrations before going to production. Build with confidence and ship faster.

🔥 We adapt powerful yet sequential autoregressive vision-language models for parallel diffusion decoding in my summer @runwayml internship! 👇(1/4)

Diffusion for everything! We share a recipe to start from a pretrained autoregressive VLM and, with very little training compute and some nice annealing tricks, turn it into a SOTA diffusion VLM. Research in diffusion for language is progressing very quickly and in my mind,

This work is a step towards our goal of unifying multimodal understanding and generation in order to build multimodal simulators of the world. Learn more:

A2D-VL outperforms prior diffusion VLMs in visual question-answering while requiring significantly less training compute. Our novel adaptation techniques are critical for retaining model capabilities, finally enabling the conversion of state-of-the-art autoregressive VLMs to

We trained a state-of-the-art diffusion VLM, A2D-VL 7B for parallel generation by finetuning an existing autoregressive VLM on the diffusion language modeling task, using the masked diffusion framework which "noises" tokens by masking them and "de-noises" tokens by predicting the

Standard Vision-language models (VLMs) reason about images and videos through language, powering a wide variety of applications from image captioning to visual question answering. Autoregressive VLMs generate tokens sequentially, which prevents parallelization and limits

Today we're sharing our first research work exploring diffusion for language models: Autoregressive-to-Diffusion Vision Language Models We develop a state-of-the-art diffusion vision language model, Autoregressive-to-Diffusion (A2D), by adapting an existing autoregressive vision