Lucid
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!
- Website
- lucid.ai
- City
- San Francisco
- Country
- United States
- YC batch
- Winter 2025
- Team
- 3 people
- Stage
- Early stage
- AI-native
- No
- Hiring
- Open roles
More Consumer in San Francisco
Clubhouse$4bn
Messaging. Valued at $4bn (April 2021).
Niantic$3.95bn
Video games. Valued at $3.95bn (January 2019).
Automattic$3bn
Internet. Valued at $3bn (September 2019).
Turo$1bn
Car sharing. Valued at $1+bn (July 2019).
DoorDashHiring
Restaurant delivery.
Airbnb
Book accommodations around the world.
Claim this profile
Free and instant: prove you run lucid.ai and edit the profile yourself.
- Your logo, office address and founder photos
- The ✓ Verified mark next to Lucid across the site
- Open roles listed on the Hiring board
- A followed link back to your website
A rank card with Lucid's standing on Labspie, or a simple badge. Both link to this profile and update themselves.
