NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
By: NextStep Team , Chunrui Han , Guopeng Li and more
Potential Business Impact:
Creates better pictures from words, faster.
Prevailing autoregressive (AR) models for text-to-image generation either rely on heavy, computationally-intensive diffusion models to process continuous image tokens, or employ vector quantization (VQ) to obtain discrete tokens with quantization loss. In this paper, we push the autoregressive paradigm forward with NextStep-1, a 14B autoregressive model paired with a 157M flow matching head, training on discrete text tokens and continuous image tokens with next-token prediction objectives. NextStep-1 achieves state-of-the-art performance for autoregressive models in text-to-image generation tasks, exhibiting strong capabilities in high-fidelity image synthesis. Furthermore, our method shows strong performance in image editing, highlighting the power and versatility of our unified approach. To facilitate open research, we will release our code and models to the community.
Similar Papers
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale
CV and Pattern Recognition
Creates amazing pictures from words.
NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation
CV and Pattern Recognition
Creates images and videos from text, super fast.
Frequency Autoregressive Image Generation with Continuous Tokens
CV and Pattern Recognition
Creates clearer images from computer code.