New York, NY
Joined April 2014
- Tweets393
- Following857
- Followers2.8K
- Likes3.9K
Yining Shi retweeted
Built on Claude 🤝
Today, Runway is joining Claude Marketplace.
Enterprise teams already working with @claudeai can now put part of their Anthropic commitment toward Runway Creative, bringing video, image and audio generation into the same budget. Learn more at the link below.
Yining Shi retweeted
From a narrow simulator of pixels to a universal simulator of reality.
This essay is the result of multiple conversations with Packy about Runway’s long-time research thesis on world models.
It's one of the most extensive overviews of our work yet, going over the applications of world models in media, robotics, interfaces, and science.
Runway has been on a tear over the past couple months.
Viral HORSE Video contest
Solaris: the world's first Interface World Model
Praxis-1: open-weight World Action Model for robotics
Project Continuum: operating system research application built around real-time interfaces
A video model. An interface model. A robotics model. An operating system. Are you getting it? These are not separate pretrains. They’re different applications, built around the same General World Model backbone, with different post-training on top.
All of them are examples of what you can do when you can simulate any pixel.
So I asked co-CEO Anastasis Germanidis to co-write an essay with me explaining how video, interfaces, operating systems, and robotics all fit together, why video was the right starting point for World Models, where the world is heading if Runway’s bets are right, and whether or not, as someone who simulates worlds, he believes we’re living in a simulation.
Welcome to the future. Enjoy!
(Video, of course, made with Runway)
We are using Runway Ads internally, we were able to 10X our ads with even cheaper cost per conversion(40% cheaper) and scale up the spend vs return efficiently:
Introducing Runway Ads, an autonomous engine for performance marketing.
Since July, we’ve used Runway Ads to:
-Scale ad volume 1,000% while doubling our return on ad spend
-Increase conversion by 34% with click-through rate holding steady
-Bring our cost per subscriber down 41%
-And add $100M ARR
Now, we’re making it available to select enterprise partners and will be rolling it out widely in the coming weeks.
Learn more and request early access: runway.com/news/company-news…
Yining Shi retweeted
We crossed $200M ARR last week, doubling from $100M in April.
Runway is the world model company. We power the daily work of more than 60 million creators and 95% of the Fortune 100. From award-winning films and ad campaigns to real-time media applications to generalist robotics. Our largest customers are increasingly licensing our frontier models directly.
As we expand our research in robotics, the wonderful team from Kinetix, a Paris-based research lab, is joining Runway to help drive our efforts there.
Proud of the team for getting us here. Back to building the universal world simulator.
A world that you can put any text prompt in to interact with!
Today, we're sharing new research on GWM Worlds 2. Our latest General World Model that generates interactive real-time simulations in continuous 720p video at 24 fps with 48000 Hz audio.
Built on top of our foundational audio-visual generation model, GWM Worlds 2 allows you to define the environment, subjects, visual style, physical rules and ambience of any world. Once inside, you steer it with text actions addressed to any subject or to the scene itself, alongside continuous camera motion.
The world continues from each new input instead of following a fixed clip or script so sessions have no preset length. GWM Worlds 2 creates a new foundation for interactive entertainment, virtual characters, robotics and embodied-agent simulation.
Learn more about GWM Worlds 2 at the link below.
Yining Shi retweeted
Runway Co-Founder & Co-CEO @agermanidis breaks down Solaris, an interface world model that generates interactive applications pixel by pixel:
"Solaris is what we call an interface world model."
"It's an interactive video model that essentially renders an interface for you."
"The difference is that it's all generated pixel by pixel by a video model."
"Unlike traditional interfaces where you write some code, you write some HTML or CSS, and then that renders pixels, you're now rendering pixels directly."
"By doing that you get a ton more flexibility."
"You can kind of leverage everything that the video model can do and create any kind of application on top of it."
Interfaces that are generated, not coded.
Solaris is our first step toward our vision of end-to-end neural software, where user interfaces are streamed directly onto your screen by a real-time video model, without any intermediate code or HTML/CSS. Today we're releasing a technical report and opening it up for limited testing by the community.
Amazing work by the team, combining the best of our research in general world models with Runway's HCI spirit.
Yining Shi retweeted
The winners of our API Hackathon, all built in a weekend with Runway Dev, our API platform for building with the best models from Runway and other frontier labs.
1st, Quigo: turn passive video into interactive stories, no code
2nd, ClinicalSim: rehearse hard conversations with virtual patients
3rd, Scene Fixer: continuity repair for mismatched AI footage
See what they built 🧵
Yining Shi retweeted
Seedance 2.5 is now on Runway. Build entire worlds full of characters with up to 50 references per generation, create clips up to 30 seconds with full sound and dialogue, then edit and extend them however your story needs.
Get started now at the link below.
It was so much fun talking to Pix (the cat) with the SIGGRAPH community! You can try Runway characters here: runwayml.com/product/charact…
Real-Time Live! is always one of SIGGRAPH’s most anticipated events, giving attendees a front-row seat to live demonstrations of the latest advances in computer graphics, AI, and interactive technology.
Among this year’s memorable presentations was Runway’s Characters, where presenters Yining Shi and Kathleen Lewis introduced an expressive feline mascot to demonstrate how a single image can be transformed into a real-time conversational character, complete with natural expressions, lip-sync, and personality. 🐱✨
Yining Shi retweeted
Real-World Superintelligence
I wrote short essay on how to build AI systems that can take the right actions in an unpredictable world.
agermanidis.com/writings/rea…
Yining Shi retweeted
We open-sourced AVTensor, the Rust media decoder behind Runway's training pipelines. It decodes video and audio on one timeline straight into PyTorch tensors, with decode-time resize up to 6× faster than PyTorch's torchcodec. It improved our training MFU by 1.8pp. Check it out!
runwayml.com/news/avtensor-a…
Yining Shi retweeted
Today, we're launching Runway Dev, a new AI media platform for professional developers and enterprise teams.
From search and advertising to ecommerce and gaming, developers are using Runway to cut costs, iterate faster and drive better consumer engagement. Runway Dev gives teams building generative media experiences a single platform from one vendor, removing the need to stitch together a dozen disparate APIs on their own.
Learn more at the link below.
Yining Shi retweeted
Introducing Agent 2.0
Go from a simple prompt to fully realized marketing briefs and campaign assets right inside of Runway Agent. You can also easily analyze your performance data to improve your creative and scale it across platforms, formats and markets.
Agent is being built to become the most capable autonomous agent for real-world work.
A campaign video made from scratch in 5 hours & $26 using Runway API and agent.
I made a campaign film for "OFF SEASON II" @fdotinc
using creative agents I build
in 5 hours & $26.2
@hthieblot @FurqanR
Got good results from @runwayml Ad Localization app.
It can edit detailed text on the product and environment. It only needs the input image and the new language.
You can try it here: app.runwayml.com/?workflowAp…
You can use these 6 Runway API endpoints in your application for your specific use cases.
They are built with Runway's custom prompting and workflows to deliver better, more consistent results.
1. Product Ad
2. Product Swap
3. Multi-Shot Video
4. Product UGC
5. Marketing Stock Image
5. Product Campaign Image
New on the Runway API: Recipes.
Drop production-ready generative media features into your platform, with one API call. Recipes are Runway-built endpoints with our prompting and workflow expertise packaged in. Polished results, without building or maintaining the workflow yourself. Create product ads from an image, swap a product in an existing video and more. At scale.
Use Runway in ChatGPT.
It's in the ChatGPT - Apps marketplace. chatgpt.com/apps/runway/asdk…
