RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910891744690176 |
|---|---|
| author | Shao, Huiyang Xia, Xin Yang, Yuhong Ren, Yuxi Wang, Xing Xiao, Xuefeng |
| author_facet | Shao, Huiyang Xia, Xin Yang, Yuhong Ren, Yuxi Wang, Xing Xiao, Xuefeng |
| contents | Diffusion models have achieved remarkable success across various domains. However, their slow generation speed remains a critical challenge. Existing acceleration methods, while aiming to reduce steps, often compromise sample quality, controllability, or introduce training complexities. Therefore, we propose RayFlow, a novel diffusion framework that addresses these limitations. Unlike previous methods, RayFlow guides each sample along a unique path towards an instance-specific target distribution. This method minimizes sampling steps while preserving generation diversity and stability. Furthermore, we introduce Time Sampler, an importance sampling technique to enhance training efficiency by focusing on crucial timesteps. Extensive experiments demonstrate RayFlow's superiority in generating high-quality images with improved speed, control, and training efficiency compared to existing acceleration techniques. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_07699 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories Shao, Huiyang Xia, Xin Yang, Yuhong Ren, Yuxi Wang, Xing Xiao, Xuefeng Machine Learning Computer Vision and Pattern Recognition I.2.10; I.4.8 Diffusion models have achieved remarkable success across various domains. However, their slow generation speed remains a critical challenge. Existing acceleration methods, while aiming to reduce steps, often compromise sample quality, controllability, or introduce training complexities. Therefore, we propose RayFlow, a novel diffusion framework that addresses these limitations. Unlike previous methods, RayFlow guides each sample along a unique path towards an instance-specific target distribution. This method minimizes sampling steps while preserving generation diversity and stability. Furthermore, we introduce Time Sampler, an importance sampling technique to enhance training efficiency by focusing on crucial timesteps. Extensive experiments demonstrate RayFlow's superiority in generating high-quality images with improved speed, control, and training efficiency compared to existing acceleration techniques. |
| title | RayFlow: Instance-Aware Diffusion Acceleration via Adaptive Flow Trajectories |
| topic | Machine Learning Computer Vision and Pattern Recognition I.2.10; I.4.8 |
| url | https://arxiv.org/abs/2503.07699 |