mlsanityData to 14 Oct 2026

MobileDiffusion: Instant Text-to-Image Generation on Mobile Devices

arXiv 2311.16567 ↗First posted 28 Nov 2023cs.CVcited by 42

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

The deployment of large-scale text-to-image diffusion models on mobile devices is impeded by their substantial model size and slow inference speed. In this paper, we propose MobileDiffusion, a highly efficient text-to-image diffusion model obtained through extensive optimizations in both architecture and sampling techniques. We conduct a comprehensive examination of model architecture design to reduce redundancy, enhance computational efficiency, and minimize model's parameter count, while preserving image generation quality. Additionally, we employ distillation and diffusion-GAN finetuning techniques on MobileDiffusion to achieve 8-step and 1-step inference respectively. Empirical studies, conducted both quantitatively and qualitatively, demonstrate the effectiveness of our proposed techniques. MobileDiffusion achieves a remarkable sub-second inference speed for generating a 512×512 image on mobile devices, establishing a new state of the art.

Key facts. Cited by 42 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 55 of its 64 references that are in the map. First posted on arXiv 28 Nov 2023.

Builds on

55 of 64 references.

Closest ancestors · 10

Same direction, newest first

  1. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs14 Nov
  2. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds1 Jun
  3. 2023Your Diffusion Model is Secretly a Zero-Shot Classifier28 Mar
  4. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models16 Feb
  5. 2023Adding Conditional Control to Text-to-Image Diffusion Models10 Feb
  6. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers2 Nov
  7. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  9. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  10. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec

Other references · 45

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  6. 2020Denoising Diffusion Implicit Modelscited by 9,781
  7. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  8. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,255
  9. 2022Scalable Diffusion Models with Transformerscited by 6,054
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  11. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  12. 2022A ConvNet for the 2020scited by 3,579
33 more
  1. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  2. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,431
  3. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,245
  4. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
  5. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,937
  6. 2020GLU Variants Improve Transformercited by 1,804
  7. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  8. 2023AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuningcited by 1,433
  9. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,173
  10. 2016Deep Networks with Stochastic Depthcited by 979
  11. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  12. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 906
  13. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  14. 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
  15. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 846
  16. 2022PaLI: A Jointly-Scaled Multilingual Language-Image Modelcited by 766
  17. 2022On Distillation of Guided Diffusion Modelscited by 725
  18. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 516
  19. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 502
  20. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  21. 2020MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devicescited by 482
  22. 2023Simple diffusion: End-to-end diffusion for high resolution imagescited by 422
  23. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 395
  24. 2023Open-Vocabulary Panoptic Segmentation with Text-to-Image Diffusion Modelscited by 375
  25. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Modelscited by 334
  26. 2018Slimmable Neural Networkscited by 305
  27. 2023Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystackcited by 279
  28. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Modulecited by 211
  29. 2022Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Modelscited by 180
  30. 2021LAFITE: Towards Language-Free Training for Text-to-Image Generationcited by 128
  31. 2022GENIE: Higher-Order Denoising Diffusion Solverscited by 127
  32. 2023Replacing softmax with ReLU in Vision Transformerscited by 44
  33. 2023Squeezing Large-Scale Diffusion Models for Mobilecited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 5; 2025: 21; 2026: 16.

42 papers.

Sort:

By area:

  1. 2025SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillationcited by 87
  2. 2025Lux Post Facto: Learning Portrait Performance Relighting with Conditional Video Diffusion and a Hybrid Datasetcited by 28
  3. 2024Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectivescited by 27
  4. 2025OBS-Diff: Accurate Pruning For Diffusion Models in One-Shotcited by 19
  5. 2026ELT: Elastic Looped Transformers for Visual Generationcited by 14
  6. 2025H3AE: High Compression, High Speed, and High Quality AutoEncoder for Video Diffusion Modelscited by 13
  7. 2025Neodragon: Mobile Video Generation using Diffusion Transformercited by 12
  8. 2025SD3.5-Flash: Distribution-Guided Distillation of Generative Flowscited by 11
  9. 2024Learnable Sparsity for Vision Generative Modelscited by 9
  10. 2025Taming Diffusion Transformer for Efficient Mobile Video Generation in Secondscited by 9
  11. 2025PocketSR: The Super-Resolution Expert in Your Pocket Mobilescited by 8
  12. 2024MoViE: Mobile Diffusion for Video Editingcited by 6
30 more
  1. 2025Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generationcited by 6
  2. 2024Communicate Less, Synthesize the Rest: Latency-aware Intent-based Generative Semantic Multicasting with Diffusion Modelscited by 5
  3. 2025Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generationcited by 4
  4. 2025MobileI2V: Fast and High-Resolution Image-to-Video on Mobile Devicescited by 4
  5. 2026DreamLite: A Lightweight On-Device Unified Model for Image Generation and Editingcited by 4
  6. 2024A-SDM: Accelerating Stable Diffusion through Model Assembly and Feature Inheritance Strategiescited by 3
  7. 2025Consistent and Controllable Image Animation with Motion Linear Diffusion Transformerscited by 3
  8. 2025TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimmingcited by 3
  9. 2025Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilitiescited by 2
  10. 2025Flow Diverse and Efficient: Learning Momentum Flow Matching via Stochastic Velocity Field Samplingcited by 2
  11. 2026NanoSD: Edge Efficient Foundation Model for Real Time Image Restorationcited by 2
  12. 2026Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teacherscited by 2
  13. 2025Accelerating Diffusion Sampling via Exploiting Local Transition Coherencecited by 1
  14. 2025Distilling Textual Priors from LLM to Efficient Image Fusioncited by 1
  15. 2025V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Modelscited by 1
  16. 2026EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generationcited by 1
  17. 2026BlazeEdit: Generalist Image Editing on Mobile Devices with Image-to-Image Diffusion Modelscited by 1
  18. 2025Designing Parameter and Compute Efficient Diffusion Transformers using Distillationcited by 0
  19. 2025KDC-Diff: A Latent-Aware Diffusion Model with Knowledge Retention for Memory-Efficient Image Generationcited by 0
  20. 2025ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservationcited by 0
  21. 2026MoGen: A Unified Collaborative Framework for Controllable Multi-Object Image Generationcited by 0
  22. 2026Federated Balanced Learningcited by 0
  23. 2026NanoFLUX: Distillation-Driven Compression of Large Text-to-Image Generation Models for Mobile Devicescited by 0
  24. 2026Quantization with Unified Adaptive Distillation to enable multi-LoRA based one-for-all Generative Vision Models on edgecited by 0
  25. 2026Cross-Resolution Diffusion Models via Network Pruningcited by 0
  26. 2026PoM: A Linear-Time Replacement for Attention with the Polynomial Mixercited by 0
  27. 2026ONOTE: Hypergraph-Grounded Omnimodal Reasoning for Computational Music Sciencecited by 0
  28. 2026Qwen-Image-Flash: Rethinking the Training Recipe for Few-Step Distillationcited by 0
  29. 2026JuZhou 1.0 Technical Report: The First Edge-Native Text-to-Image Foundation Model Trained Entirely on China-Developed AI Acceleratorscited by 0
  30. 2026Nexus: Structured Synergy for Efficient Text-to-Image Generation using Rectified Flow Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training
  2. 2026ElasticDiT: Efficient Diffusion Transformers via Elastic Architecture and Sparse Attention for High-Resolution Image Generation on Mobile Devices
  3. 2023MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation
  4. 2024Mobile Video Diffusion
  5. 2025DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation
  6. 2024CogView3: Finer and Faster Text-to-Image Generation via Relay Diffusion
  7. 2024EdgeFusion: On-Device Text-to-Image Generation
  8. 2025Reusing Computation in Text-to-Image Diffusion for Efficient Generation of Image Sets