Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Computational EfficiencySimilar Papers 제목 키워드 기반
Stage-adaptive audio diffusion modeling
Recent progress in diffusion-based audio generation and restoration has substantially improved performance across heterogeneous conditioning regimes, including text-conditioned audio generation and audio-conditioned supe…
Spectral ReconstructionAudio GenerationLeveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis
While diffusion models have demonstrated exceptional image generation capabilities, the iterative noise estimation process required for these models is compute-intensive and their practical implementation is limited by s…
DC-DiT: Adaptive Compute and Elastic Inference for Visual Generation via Dynamic Chunking
Diffusion Transformers rely on static patchify tokenization, assigning the same token budget to smooth backgrounds, detailed object regions, noisy early timesteps, and late-stage refinements. We introduce the Dynamic Chu…
TASR: Timestep-Aware Diffusion Model for Image Super-Resolution
Diffusion models have recently achieved outstanding results in the field of image super-resolution. These methods typically inject low-resolution (LR) images via ControlNet.In this paper, we first explore the temporal dy…
DenoisingImage Super-ResolutionSuper-ResolutionNavigating the Exploration-Exploitation Tradeoff in Inference-Time Scaling of Diffusion Models
Inference-time scaling has achieved remarkable success in language models, yet its adaptation to diffusion models remains underexplored. We observe that the efficacy of recent Sequential Monte Carlo (SMC)-based methods l…