Pinned
Towards Universal Simulation
agermanidis.com/writings/unive…
Anastasis Germanidis
547 posts
Anastasis Germanidis
@agermanidis
New York, NY
Joined May 2011
- Text to video is coming! Next week, will be sharing more on how this came to be, how it works, and our rollout strategy. In the meantime, go to runwayml.com and sign up for early access :)Make any idea real. Just write it. Text to video, coming soon to Runway. Sign up for early access: runwayml.com
00:00runwayml.comRunway | Building AI to Simulate the WorldWe are building foundational General World Models that will be capable of simulating all possible worlds and experiences. The next frontier of intelligence will come from models that can understand,... 
00:00- Text-to-video was act zero, here's act one. The future of video generation is in building tools that are controllable, expressive, and fun -- and in increasing the space of possible choices that you can make.Introducing, Act-One. A new way to generate expressive character performances inside Gen-3 Alpha using a single driving video and character image. No motion capture or rigging required. Learn more about Act-One below. (1/7)
00:00 
00:00- For @stupidhackathon, made an app that shows the typing indicator to anyone messaging you, forever. Collab w @isiain agermanidis.github.io/facebook-godot/
GIF - Models just want to generalize. For the past years, we’ve been pushing the frontier of controllability in video, releasing new models and techniques for inpainting, outpainting, segmentation, stylization, keyframing, motion and camera control. Aleph is a single in-context modelIntroducing 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
00:00 - We're announcing a new research direction towards building general world models. If next token prediction has gotten us this far, imagine where next frame prediction will take us.Introducing General World Models. We believe the next major advancement in AI will come from systems that understand the visual world and its dynamics, which is why we’re starting a new long-term research effort around general world models. Learn more: bit.ly/3RexmuJ
00:00 - 👨🏻🔬 New experiment: Uncanny Road is a tool for collectively synthesizing a never-ending road with the help of Generative Adversarial Networks. Collaboration with @c_valenzuelab. uncannyroad.com
00:00 - Thrilled to finally share what we’ve been working on: Gen-3 Alpha, our new base model for video generation. A significant improvement in fidelity, geometric consistency, and prompt understanding over Gen-2, and a step towards building General World Models.Introducing Gen-3 Alpha: Runway’s new base model for video generation. Gen-3 Alpha can create highly detailed videos with complex scene changes, a wide range of cinematic choices, and detailed art directions. runwayml.com/gen-3-alpha (1/10)
00:00 - Computer vision researchers rediscovering graphics ideas from a decade ago
- Working on something special for the next @runwayml release: a new way to navigate GAN latent spaces. Coming soon!
00:00
