Lucid
Lucid is a YC Winter 2025 (W25) company. Team of 3.
About Lucid
Summary
Lucid builds neural world models that simulate interactive, photorealistic environments, replacing traditional hard-coded game and physics engines with video-generating neural networks. The models are action-conditioned: a user's inputs drive what the simulation renders next, in real time. Lucid's current architecture uses aggressive tokenizer compression to run at high frame rates on consumer-grade GPUs, with far lower training compute than comparable systems.
From the Y Combinator listing
interactive video models
We are building universe simulations powered by interactive video models. We train video models that simulate hyper-realistic environments with immersive control, replacing hard-coded game or physics engines with dynamic neural networks. We built the fastest action-conditioned diffusion video model (running at 20+fps on a 4090 gaming gpu) to simulate minecraft. It is 5x faster than other minecraft World Models and was trained with 100x less resources. Our unique insight was relying on aggressive compression in our tokenizer (128x versus the traditional 8x), and because attention scales quadratically with # of tokens our model can run blindingly faster. Now we’re training a hyper realistic world model!
Facts
- Consumer / Consumer
- 3
- Active
- Early
Founders (2)
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works