New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Cosmos Tokenizer (Nvidia) #11

Open

Dongwoo-Im opened this issue Nov 9, 2024 · 0 comments

Labels

Blog

Owner

Dongwoo-Im commented Nov 9, 2024 •

edited

Loading

Github : https://github.com/NVIDIA/Cosmos-Tokenizer

vision-language models (VLMs) with discrete latent codes
diffusion models with continuous latent embeddings

Causal : the model uses only past and present frames when performing tokenization, avoiding future frames

The input is downsampled using 3D wavelets
After the data is processed, an inverse wavelet transform reconstructs the original input

Dongwoo-Im added the Blog label

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment