Parallel Jacobi Decoding for Fast Autoregressive Image Generation
Autoregressive (AR) models have demonstrated remarkable performance in generating high-fidelity images. However, their inherently sequential next-token prediction leads to significantly slower inference. Recent studies have introduced Jacobi-style decoding to accelerate autoregressive image generation. Extending the draft sequence initially improves efficiency, yet the acceleration quickly saturates as error propagation in the one-dimensional sequence hinders convergence. Observing that images exhibit strong local spatial correlations, we propose Parallel Jacobi Decoding (PJD), a training-free decoding approach that expands draft tokens in the two-dimensional spatial domain to enable efficient spatially parallel refinement. PJD adjusts the attention mask to mitigate error accumulation and improve convergence stability. Extensive experiments on diverse datasets show that PJD achieves 4.8x-6.4x acceleration across multiple autoregressive image generation models while maintaining competitive generation quality.
Code (0)
등록된 구현이 없습니다.
Tasks
Image GenerationSimilar Papers 제목 키워드 기반
Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
As a new paradigm of visual content generation, autoregressive text-to-image models suffer from slow inference due to their sequential token-by-token decoding process, often requiring thousands of model forward passes to…
Text-to-Image GenerationCLLMs: Consistency Large Language Models
Parallel decoding methods such as Jacobi decoding show promise for more efficient LLM inference as it breaks the sequential nature of the LLM decoding process and transforms it into parallelizable computation. However, i…
Accelerating Transformer Inference for Translation via Parallel Decoding
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network architectures and learning-based methods to solve this issue, which are expensive and re…
Machine TranslationTranslationSJD++: Improved Speculative Jacobi Decoding for Training-free Acceleration of Discrete Auto-regressive Text-to-Image Generation
Large autoregressive models can generate high-quality, high-resolution images but suffer from slow generation speed, because these models require hundreds to thousands of sequential forward passes for next-token predicti…
Text-to-Image GenerationPathRelax: Parallel-Path Relaxed Speculative Jacobi Decoding for Accelerating Auto-Regressive Text-to-Image Generation
The growing need for high-resolution image generation in autoregressive text-to-image models has resulted in extended token sequences, significantly increasing computational costs and inference times. However, existing s…
Text-to-Image Generation