I left Stability AI in late July 2024 to join a new stealth HW startup. I want to thank my former Stability AI colleagues for a year and a half filled with exciting challenges, discoveries and technical achievements. I wish them all the best.
Hi, I'm now available for consulting or full-time. If your team is looking for a tech leader with lots of experience in Generative AI R&D, 3D, GPUs, etc -- or if you're looking for a CEO or CTO for a very early stage startup -- I might be your guy.
Today is my last day at @StabilityAI . It’s incredible how quickly the past year has flown by! I’m deeply grateful for the opportunity to work alongside such talented and inspiring colleagues.
A special thank you to Christian @chrlaf for trusting me to lead the speech research
How much VRAM will you need to run MovieGen? The main text-to-video model has 30B params, and assuming BF8 quantization, that might fit in 2 RTX4090s. To run the rest of the models (text encoders etc) you'll need >=80GB, just for the weights alone:
I just listened to the first 3 episodes of @ericries's podcast, the ericriesshow.com ... It's refreshing to hear interviews with entrepreneurs that didn't just get rich but that did it with principles and unequivocally made the world better.