File size: 803 Bytes
a86ad64 a71a32b a86ad64 710d7a4 a86ad64 9f6f1ef a86ad64 7e43842 |
1 2 3 4 5 6 7 8 9 10 11 12 |
---
license: mit
pipeline_tag: image-to-image
---
# 🌿 Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation
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.
This repo is used for hosting LlamaGen's checkpoints. For more details or tutorials see https://github.com/FoundationVision/LlamaGen
Paper:arxiv.org/abs/2406.06525 |