{"ID":2866121,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2509.21318","arxiv_id":"2509.21318","title":"SD3.5-Flash: Distribution-Guided Distillation of Generative Flows","abstract":"We present SD3.5-Flash, an efficient few-step distillation framework that brings high-quality image generation to accessible consumer devices. Our approach distills computationally prohibitive rectified flow models through a reformulated distribution matching objective tailored specifically for few-step generation. We introduce two key innovations: \"timestep sharing\" to reduce gradient noise and \"split-timestep fine-tuning\" to improve prompt alignment. Combined with comprehensive pipeline optimizations like text encoder restructuring and specialized quantization, our system enables both rapid generation and memory-efficient deployment across different hardware configurations. This democratizes access across the full spectrum of devices, from mobile phones to desktop computers. Through extensive evaluation including large-scale user studies, we demonstrate that SD3.5-Flash consistently outperforms existing few-step methods, making advanced generative AI truly accessible for practical deployment.","short_abstract":"We present SD3.5-Flash, an efficient few-step distillation framework that brings high-quality image generation to accessible consumer devices. Our approach distills computationally prohibitive rectified flow models through a reformulated distribution matching objective tailored specifically for few-step generation. We...","url_abs":"https://arxiv.org/abs/2509.21318","url_pdf":"https://arxiv.org/pdf/2509.21318v1","authors":"[\"Hmrishav Bandyopadhyay\",\"Rahim Entezari\",\"Jim Scott\",\"Reshinth Adithyan\",\"Yi-Zhe Song\",\"Varun Jampani\"]","published":"2025-09-25T16:07:38Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false}