Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Understand

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 properly.
• We reexamine design spaces of image tokenizers, scalability properties of image generation models, and their training data quality.
• The outcome of this exploration consists of: (1) An image tokenizer with downsample ratio of 16, reconstruction quality of 0.94 rFID and codebook usage of 97% on ImageNet benchmark.