SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices

• URL: http://arxiv.org/abs/2601.08303v1
• Date: Tue, 13 Jan 2026 07:46:46 GMT
• Title: SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devices
• Authors: Dongting Hu, Aarush Gupta, Magzhan Gabidolla, Arpit Sahni, Huseyin Coskun, Yanyu Li, Yerlan Idelbayev, Ahsan Mahmood, Aleksei Lebedev, Dishani Lahiri, Anujraaj Goyal, Ju Hu, Mingming Gong, Sergey Tulyakov, Anil Kag,
• Abstract summary: Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment.<n>We present an efficient DiT framework tailored for mobile and edge devices that achieves transformer-level generation quality under strict resource constraints.
• Score: 72.0937240883345
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT framework tailored for mobile and edge devices that achieves transformer-level generation quality under strict resource constraints. Our design combines three key components. First, we propose a compact DiT architecture with an adaptive global-local sparse attention mechanism that balances global context modeling and local detail preservation. Second, we propose an elastic training framework that jointly optimizes sub-DiTs of varying capacities within a unified supernetwork, allowing a single model to dynamically adjust for efficient inference across different hardware. Finally, we develop Knowledge-Guided Distribution Matching Distillation, a step-distillation pipeline that integrates the DMD objective with knowledge transfer from few-step teacher models, producing high-fidelity and low-latency generation (e.g., 4-step) suitable for real-time on-device use. Together, these contributions enable scalable, efficient, and high-quality diffusion models for deployment on diverse hardware.

Related papers

• MOBIUS: Big-to-Mobile Universal Instance Segmentation via Multi-modal Bottleneck Fusion and Calibrated Decoder Pruning [91.90342432541138]
  Scaling up model size and training data has advanced foundation models for instance-level perception.<n>High computational cost limits adoption on resource-constrained platforms.<n>We introduce a new benchmark for efficient segmentation on both high-performance computing platforms and mobile devices.
  arXiv  Detail & Related papers  (2025-10-16T18:00:00Z)
• SD3.5-Flash: Distribution-Guided Distillation of Generative Flows [87.45964232927945]
  We present SD3.5-Flash, an efficient few-step distillation framework that brings high-quality image generation to consumer devices.<n>We introduce two key innovations: "timestep sharing" to reduce gradient noise and "split-timestep fine-tuning" to improve prompt alignment.<n>This democratizes access across the full spectrum of devices, from mobile phones to desktop computers.
  arXiv  Detail & Related papers  (2025-09-25T16:07:38Z)
• CollaPipe: Adaptive Segment-Optimized Pipeline Parallelism for Collaborative LLM Training in Heterogeneous Edge Networks [57.95170323315603]
  We introduce CollaPipe, a distributed learning framework that integrates collaborative pipeline parallelism with federated aggregation to support self-evolving networks.<n>In CollaPipe, the encoder part is adaptively partitioned into variable-sized segments and deployed across mobile devices for pipeline-parallel training, while the decoder is deployed on edge servers to handle generative tasks.<n>To enhance training efficiency, we formulate a joint optimization problem that adaptively allocates model segments, micro-batches, bandwidth, and transmission power.
  arXiv  Detail & Related papers  (2025-09-24T07:54:01Z)
• OneCAT: Decoder-Only Auto-Regressive Model for Unified Understanding and Generation [91.45421429922506]
  OneCAT is a unified multimodal model that seamlessly integrates understanding, generation, and editing.<n>Our framework eliminates the need for external components such as Vision Transformers (ViT) or vision tokenizer during inference.
  arXiv  Detail & Related papers  (2025-09-03T17:29:50Z)
• Boosting Generative Image Modeling via Joint Image-Feature Synthesis [15.133906625258797]
  We introduce a novel generative image modeling framework that seamlessly bridges the gap by leveraging a diffusion model to jointly model low-level image latents.<n>Our latent-semantic diffusion approach learns to generate coherent image-feature pairs from pure noise.<n>By eliminating the need for complex distillation objectives, our unified design simplifies training and unlocks a powerful new inference strategy: Representation Guidance.
  arXiv  Detail & Related papers  (2025-04-22T17:41:42Z)
• EasyControl: Adding Efficient and Flexible Control for Diffusion Transformer [15.879712910520801]
  We propose EasyControl, a novel framework designed to unify condition-guided diffusion transformers with high efficiency and flexibility.<n>Our framework is built on three key innovations. First, we introduce a lightweight Condition Injection LoRA Module.<n>Second, we propose a Position-Aware Training Paradigm. This approach standardizes input conditions to fixed resolutions, allowing the generation of images with arbitrary aspect ratios and flexible resolutions.<n>Third, we develop a Causal Attention Mechanism combined with the KV Cache technique, adapted for conditional generation tasks.
  arXiv  Detail & Related papers  (2025-03-10T08:07:17Z)
• OminiControl: Minimal and Universal Control for Diffusion Transformer [68.3243031301164]
  We present OminiControl, a novel approach that rethinks how image conditions are integrated into Diffusion Transformer (DiT) architectures.<n>OminiControl addresses these limitations through three key innovations.
  arXiv  Detail & Related papers  (2024-11-22T17:55:15Z)
• Re-Parameterization of Lightweight Transformer for On-Device Speech Emotion Recognition [10.302458835329539]
  We introduce a new method, namely Transformer Re- parameterization, to boost the performance of lightweight Transformer models. Experimental results show that our proposed method consistently improves the performance of lightweight Transformers, even making them comparable to large models.
  arXiv  Detail & Related papers  (2024-11-14T10:36:19Z)
• OnDev-LCT: On-Device Lightweight Convolutional Transformers towards federated learning [29.798780069556074]
  Federated learning (FL) has emerged as a promising approach to collaboratively train machine learning models across multiple edge devices. We propose OnDev-LCT: Lightweight Convolutional Transformers for On-Device vision tasks with limited training data and resources.
  arXiv  Detail & Related papers  (2024-01-22T02:17:36Z)
• DiffiT: Diffusion Vision Transformers for Image Generation [88.08529836125399]
  Vision Transformer (ViT) has demonstrated strong modeling capabilities and scalability, especially for recognition tasks. We study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT) DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency.
  arXiv  Detail & Related papers  (2023-12-04T18:57:01Z)
• LayoutDM: Transformer-based Diffusion Model for Layout Generation [0.6445605125467572]
  Transformer-based diffusion model (DDPM) is proposed to generate high-quality images. Transformer-based conditional Layout Denoiser is proposed to generate samples from noised layout data. Our method outperforms state-of-the-art generative models in terms of quality and diversity.
  arXiv  Detail & Related papers  (2023-05-04T05:51:35Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.