Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912932623810560 |
|---|---|
| author | Chen, Yuyang Zeng, Linqian ZHou, Yijin Li, Hengjie Zhai, Jidong |
| author_facet | Chen, Yuyang Zeng, Linqian ZHou, Yijin Li, Hengjie Zhai, Jidong |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_00519 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness Chen, Yuyang Zeng, Linqian ZHou, Yijin Li, Hengjie Zhai, Jidong Computer Vision and Pattern Recognition 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. |
| title | Jano: Adaptive Diffusion Generation with Early-stage Convergence Awareness |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2603.00519 |