Lucid

interactive video models

Y CombinatorWinter 2025ActiveConsumer

What they do

Problem

Creating and running realistic, controllable simulated environments is slow and resource-intensive when relying on hard-coded game or physics engines.

Solution

They build action-conditioned diffusion video models that simulate hyper-realistic interactive worlds in real time using aggressively compressed tokenization for speed.

Who it's for

Developers and researchers building interactive simulations, games, and AI world models.

Founders

Rami Seid

Co-Founder

A high school dropout who got his first internship as an MLE at a robotics lab, I went on to become the CTO of a govtech contracting company. After that, I cofounded my own telecommunications company while doing ML work on the side. Now I'm building a universe simulator at Lucid.

LinkedIn · X