paper-with-me

홈 › Papers

NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices

2026-02-06 · Ruchika Chavhan, Malcolm Chadwick, Alberto Gil Couto Pimentel Ramos, Luca Morreale, Mehdi Noroozi, Abhinav Mehrotra arxiv

While large-scale text-to-image diffusion models continue to improve in visual quality, their increasing scale has widened the gap between state-of-the-art models and on-device solutions. To address this gap, we introduce NanoFLUX, a 2.4B text-to-image flow-matching model distilled from 17B FLUX.1-Schnell using a progressive compression pipeline designed to preserve generation quality. Our contributions include: (1) A model compression strategy driven by pruning redundant components in the diffusion transformer, reducing its size from 12B to 2B; (2) A ResNet-based token downsampling mechanism that reduces latency by allowing intermediate blocks to operate on lower-resolution tokens while preserving high-resolution processing elsewhere; (3) A novel text encoder distillation approach that leverages visual signals from early layers of the denoiser during sampling. Empirically, NanoFLUX generates 512 x 512 images in approximately 2.5 seconds on mobile devices, demonstrating the feasibility of high-quality on-device text-to-image generation.

📄 PDF Abstract BibTeX arXiv:2602.06879

Code (0)

등록된 구현이 없습니다.

Tasks

Text-to-Image GenerationModel Compression

Similar Papers 제목 키워드 기반

NanoFlux: Adversarial Dual-LLM Evaluation and Distillation For Multi-Domain Reasoning

2025-09-27 · Raviteja Anantha, Soheil Hor, Teodor Nicola Antoniu, Layne C. Price arxiv

We present NanoFlux, a novel adversarial framework for generating targeted training data to improve LLM reasoning, where adversarially-generated datasets containing fewer than 200 examples outperform conventional fine-tu…

Mathematical Reasoning

Less Is More: Elevating RAG via Performance-Driven Context Compression

2025-08-24 · Ziqiang Cui, Yunpeng Weng, Xing Tang, Peiyang Liu 외 arxiv

Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm for improving the timeliness of knowledge updates and the factual accuracy of large language models. However, incorporating a large volume of retri…

Knowledge Distillation

A Functional Perspective on Knowledge Distillation in Neural Networks

2025-10-14 · Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis arxiv

Knowledge distillation is considered a compression mechanism when judged on the resulting student's accuracy and loss, yet its functional impact is poorly understood. We quantify the compression capacity of knowledge dis…

Knowledge Distillation

A Unified Knowledge Distillation Framework for Deep Directed Graphical Models

2021-09-29 · CVPR 2023 1 · Yizhuo Chen, Kaizhao Liang, Zhe Zeng, Yifei Yang 외

Knowledge distillation (KD) is a technique that transfers the knowledge from a large teacher network to a small student network. It has been widely applied to many different tasks, such as model compression and federate…

Continual LearningFederated LearningKnowledge DistillationModel Compression

Dataset Distillation as Data Compression: A Rate-Utility Perspective

2025-07-23 · Youneng Bao, Yiping Liu, Zhuo Chen, Yongsheng Liang 외 arxiv

Driven by the ``scale-is-everything'' paradigm, modern machine learning increasingly demands ever-larger datasets and models, yielding prohibitive computational and storage requirements. Dataset distillation mitigates th…