Jano：具有早期阶段收敛意识的自适应扩散生成
Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness
AI总结：
Jano通过自适应区域感知生成方法，提升扩散模型的生成效率，实现2.0至2.4倍的加速，同时保持生成质量。
摘要：
扩散模型在生成式AI中取得了显著成功，但其计算效率仍然是一个重大挑战，特别是对于需要密集全注意力计算的扩散变换器（DiTs）。尽管现有的加速方法专注于内容无关的统一优化策略，但我们观察到生成内容中不同区域在去噪过程中表现出异质的收敛模式。我们提出了Jano，一个无需训练的框架，利用这一洞察进行高效的区域感知生成。Jano引入了一个早期阶段复杂度识别算法，能够准确识别初始去噪步骤中各区域的收敛需求，并结合一个自适应令牌调度运行时，优化计算资源分配。通过在最先进的模型上进行全面评估，Jano实现了显著的加速（平均2.0倍提速，最高2.4倍），同时保持生成质量。我们的工作挑战了传统统一处理假设，并为加速大规模内容生成提供了实用的解决方案。我们的实现源代码可在https://github.com/chen-yy20/Jano上获得。
英文摘要：
Diffusion models have achieved remarkable success in generative AI, yet their computational efficiency remains a significant challenge, particularly for Diffusion Transformers (DiTs) requiring intensive full-attention computation. While existing acceleration approaches focus on content-agnostic uniform optimization strategies, we observe that different regions in generated content exhibit heterogeneous convergence patterns during the denoising process. We present Jano, a training-free framework that leverages this insight for efficient region-aware generation. Jano introduces an early-stage complexity recognition algorithm that accurately identifies regional convergence requirements within initial denoising steps, coupled with an adaptive token scheduling runtime that optimizes computational resource allocation. Through comprehensive evaluation on state-of-the-art models, Jano achieves substantial acceleration (average 2.0 times speedup, up to 2.4 times) while preserving generation quality. Our work challenges conventional uniform processing assumptions and provides a practical solution for accelerating large-scale content generation. The source code of our implementation is available at https://github.com/chen-yy20/Jano.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
