Papers
arxiv:2507.04947

DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer

Published on Jul 7
Authors:
,
,
,
,
,
,
,
,
,

Abstract

A novel masked autoregressive framework with a deep compression hybrid tokenizer achieves superior image generation quality and efficiency compared to diffusion and autoregressive models.

AI-generated summary

We introduce DC-AR, a novel masked autoregressive (AR) text-to-image generation framework that delivers superior image generation quality with exceptional computational efficiency. Due to the tokenizers' limitations, prior masked AR models have lagged behind diffusion models in terms of quality or efficiency. We overcome this limitation by introducing DC-HT - a deep compression hybrid tokenizer for AR models that achieves a 32x spatial compression ratio while maintaining high reconstruction fidelity and cross-resolution generalization ability. Building upon DC-HT, we extend MaskGIT and create a new hybrid masked autoregressive image generation framework that first produces the structural elements through discrete tokens and then applies refinements via residual tokens. DC-AR achieves state-of-the-art results with a gFID of 5.49 on MJHQ-30K and an overall score of 0.69 on GenEval, while offering 1.5-7.9x higher throughput and 2.0-3.5x lower latency compared to prior leading diffusion and autoregressive models.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2507.04947 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2507.04947 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2507.04947 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.