Lucid
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!
Vendors
0Third parties this company currently discloses, grouped by function when classified.
No disclosed vendors yet
Vendors appear only once a public disclosure or other published evidence names them.
Customers
0Companies whose current disclosures name this company as a vendor.
No observed customers yet
Customers appear when another company's current disclosure names this company as a vendor.
Potential customers
0Companies using another vendor in one of Lucid’s categories, excluding Lucid’s observed customers.
No potential customers found
Potential customers appear after Lucid has a category assignment and current vendor relationships can be compared.