mlsanityData to 7 Oct 2026

EdgeFusion: On-Device Text-to-Image Generation

arXiv 2404.11925 ↗First posted 18 Apr 2024cs.LG cs.AI cs.CVcited by 12

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling steps, such as Latent Consistency Model (LCM), and on employing architectural optimizations, including pruning and knowledge distillation. Diverging from existing approaches, we uniquely start with a compact SD variant, BK-SDM. We observe that directly applying LCM to BK-SDM with commonly used crawled datasets yields unsatisfactory results. It leads us to develop two strategies: (1) leveraging high-quality image-text pairs from leading generative models and (2) designing an advanced distillation process tailored for LCM. Through our thorough exploration of quantization, profiling, and on-device deployment, we achieve rapid generation of photo-realistic, text-aligned images in just two steps, with latency under one second on resource-limited edge devices.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 22 of its 27 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

22 of 27 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models10 Jan
  2. 2024Progressive Knowledge Distillation Of Stable Diffusion XL Using Layer Level Loss5 Jan
  3. 2023Adversarial Diffusion Distillation28 Nov
  4. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  6. 2023Squeezing Large-Scale Diffusion Models for Mobile3 Jul
  7. 2023BK-SDM: A Lightweight, Fast, and Cheap Version of Stable Diffusion25 May
  8. 2023PTQD: Accurate Post-Training Quantization for Diffusion Models18 May
  9. 2022On Distillation of Guided Diffusion Models6 Oct
  10. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  11. 2021Diffusion Models Beat GANs on Image Synthesis11 May

Other references · 11

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  3. 2022FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awarenesscited by 3,611
  4. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  5. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  6. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  7. 2021Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depthcited by 411
  8. 2019A Comprehensive Overhaul of Feature Distillationcited by 341
  9. 2023SPHINX: The Joint Mixing of Weights, Tasks, and Visual Embeddings for Multi-modal Large Language Modelscited by 283
  10. 2023SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Secondscited by 227
  11. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 7; 2026: 1.

12 papers.

  1. 2024Diffusion Models in Low-Level Vision: A Surveycited by 73
  2. 2024SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Trainingcited by 27
  3. 2025On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devicescited by 14
  4. 2025On-Device Diffusion Transformer Policy for Efficient Robot Manipulationcited by 13
  5. 2024Individual Content and Motion Dynamics Preserved Pruning for Video Diffusion Modelscited by 8
  6. 2025PocketSR: The Super-Resolution Expert in Your Pocket Mobilescited by 8
  7. 2024MoViE: Mobile Diffusion for Video Editingcited by 6
  8. 2026SnapGen++: Unleashing Diffusion Transformers for Efficient High-Fidelity Image Generation on Edge Devicescited by 3
  9. 2025Upcycling Text-to-Image Diffusion Models for Multi-Task Capabilitiescited by 2
  10. 2025Towards Redundancy Reduction in Diffusion Models for Efficient Video Super-Resolutioncited by 2
  11. 2025V.I.P. : Iterative Online Preference Distillation for Efficient Video Diffusion Modelscited by 1
  12. 2025On-device Sora: Enabling Training-Free Diffusion-based Text-to-Video Generation for Mobile Devicescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023A-SDM: Accelerating Stable Diffusion through Redundancy Removal and Performance Optimization
  2. 2023KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
  3. 2024A-SDM: Accelerating Stable Diffusion through Model Assembly and Feature Inheritance Strategies
  4. 2024Efficiency Meets Fidelity: A Novel Quantization Framework for Stable Diffusion
  5. 2024Taming Stable Diffusion for Text to 360deg Panorama Image Generation
  6. 2024TLCM: Training-efficient Latent Consistency Model for Image Generation with 2-8 Steps
  7. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Module
  8. 2026Nexus: Structured Synergy for Efficient Text-to-Image Generation using Rectified Flow Model