Jonathan Granskog

A few gaussian splats from the BAFTAs I worked on with @harrynelder. Trained with LichtFeld Studio @janusch_patas.

@MoldyMagnet exciting weird future ahead of us :)

@jongranskog I read the news, but seeing the demo in this video made me realize how crazy this is

Three years after releasing Gen-2, the first text-to-video model available in a product, we’re sharing a research preview of instant high-quality video generation. Just type your prompt and visualize immediately. Possible with Vera Rubin and our real-time generation research.

@thehackettman @runwayml thanks, appreciate the feedback!

@jongranskog @runwayml Just not immediately accessible would be good and still allow for people to keep making while their project doesn't slow down. Google flow does this really well. Just not much else..

My last short was me trying out workflows in @runwayml and forming an opinion on how it can be used to make stories. Which I spent alot of time working and fighting with. Im gonna do a bts, but for sure these tools are pretty powerful if used to their strengths.

A breakthrough in real-time video generation. As a research preview developed with @NVIDIA and shared at @NVIDIAGTC this week, we trained a new real-time video model running on Vera Rubin. HD videos generate instantly, with time-to-first-frame under 100ms. Unlocking an entirely new creative paradigm and bolstering the foundations of our General World Model, GWM-1. Real-time generation opens a fundamentally different design space for video models and world simulation. We're investing in co-designing our models alongside advances in hardware to keep pushing this frontier.

FaceTime but all the characters are completely generated with @runwayml characters.

Experimenting a bit with more collaborative agentic workflows in my photo editor. The LLM creates a plan, the user selects every effect at each step out of five options given by the LLM. Can always stop to give feedback, and adjust settings by hand during the process.

@TuliMathieu it sounds like there is plenty of control in game engines being able to choose what gets adjusted. I have faith in the DLSS team at NV.

@jongranskog the only axis of concern I have when seeing these demos is the lack of artistic intent that seems to have been captured - many of the scenes/faces changes completely - not sure this matters to everyone though, or that it will be a problem in the limit of the tech

Naturally there will be a spectrum of models depending on how much control you want. From world models without any geometric 3d representation to a refinement pass over your game renders.

@hoanhle_ 😅😅😅

@jongranskog time to come back to work on dlss jonathan :p

DLSS 5 looks impressive and, as always in AI, note that it'll always get better. There are so many parts of graphics that are difficult to model and render with traditional methods. Using generative models makes a lot of sense if you can run it quickly and consistently.

I love how game graphics from each generation of hardware are being refined into their own art style now. When games looked like this we couldn't wait to get to realism, but now we can appreciate the aesthetic of each era and find beauty in it. Those cigarette shots at the end 👌

@ctnzr congrats Bryan and ADLR! 👏👏👏

So proud of DLSS5: Fully generative neural rendering, in real-time, in real games. Mind-blowing realism. A whole new generation of real-time graphics. A decade of continuous research and development. Coming soon to PCs everywhere. 💚

Earlier this week, we launched Runway Characters which represents a new type of real-time interaction with AI. These kinds of immersive simulated experiences are going to reshape the way we experience and engage with the internet. Building a technology this powerful means grappling with how it might be misused. Learn more at the link below about how we're building responsibly towards this new internet.

Today we are introducing Runway Labs, a generative AI incubator led by our co-founder and Chief Innovation Officer, Alejandro Matamala Ortiz. Runway Labs will focus on broadly exploring the transformative power of AI video and General Worlds Models across all industries. From film and television to healthcare and education, gaming, advertising, real estate and more. We will be partnering with creators, enterprises, institutions and foundations to find new applications for these technologies and opportunities across industries. Learn more at the link below.

@andreintg 😅 I feel the same way

@jongranskog wow. Everytime I blink, runway has introduced a new tool 😆

Our first real-time experience is here. Real-time generated characters that you can interact with. You can even create custom characters and give them their own knowledge and personalities.

Using Runway Character's API, I built a character with the entire map knowledge base of Bungie's latest title @MarathonTheGame. It can read the screen, guide you to objectives, and help you decide which valuables to extract. Just a preview of how gaming will change with AI.

Using @runwayml's new real-time Characters to ID some Japanese carts I just picked up

Introducing 'Benny Smalls - The Worlds Worst Comedian' 🎙️😎 Made with the new @runwayml Characters interactive avatars feature. Gave him a 1970's retro comedian persona with some guidance / knowledge on what makes bad jokes! Insane! Who wants to book Benny for a gig ? 😅