NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devices
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Text-to-Image GenerationModel CompressionSimilar Papers 제목 키워드 기반
NanoFlux: Adversarial Dual-LLM Evaluation and Distillation For Multi-Domain Reasoning
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 ReasoningLess Is More: Elevating RAG via Performance-Driven Context Compression
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 DistillationA Functional Perspective on Knowledge Distillation in Neural Networks
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 DistillationA Unified Knowledge Distillation Framework for Deep Directed Graphical Models
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 CompressionDataset Distillation as Data Compression: A Rate-Utility Perspective
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…