Sign in

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

By Peize Sun and others at
LogoUniversity of Hong Kong
We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive models, e.g., Llama, without inductive biases on visual signals can achieve state-of-the-art image generation performance if scaling... Show more
June 10, 2024
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
Click on play to start listening