Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness
This addresses the problem of high computational costs in generative AI for researchers and practitioners, offering a practical solution for large-scale content generation, though it is incremental as it builds on existing diffusion models.
The paper tackles the computational inefficiency of Diffusion Transformers (DiTs) by proposing Jano, a training-free framework that uses region-aware generation to accelerate the denoising process, achieving an average 2.0 times speedup while maintaining quality.
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.