mlsanityData to 7 Oct 2026

SwiftBrush v2: Make Your One-step Diffusion Model Better Than Its Teacher

arXiv 2408.14176 ↗First posted 26 Aug 2024cs.CV cs.AIcited by 45

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

In this paper, we aim to enhance the performance of SwiftBrush, a prominent one-step text-to-image diffusion model, to be competitive with its multi-step Stable Diffusion counterpart. Initially, we explore the quality-diversity trade-off between SwiftBrush and SD Turbo: the former excels in image diversity, while the latter excels in image quality. This observation motivates our proposed modifications in the training methodology, including better weight initialization and efficient LoRA training. Moreover, our introduction of a novel clamped CLIP loss enhances image-text alignment and results in improved image quality. Remarkably, by combining the weights of models trained with efficient LoRA and full training, we achieve a new state-of-the-art one-step diffusion model, achieving an FID of 8.14 and surpassing all GAN-based and multi-step Stable Diffusion models. The project page is available at https://swiftbrushv2.github.io.

Key facts. Cited by 45 papers in the map (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 44 of its 53 references that are in the map. First posted on arXiv 26 Aug 2024.

Builds on

44 of 53 references.

Closest ancestors · 10

Same direction, newest first

  1. 2024SDXL-Lightning: Progressive Adversarial Diffusion Distillation21 Feb
  2. 2024PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Models10 Jan
  3. 2023One-step Diffusion with Distribution Matching Distillation30 Nov
  4. 2023Adversarial Diffusion Distillation28 Nov
  5. 2023ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models11 Oct
  6. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference6 Oct
  7. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis4 Jul
  8. 2023BOOT: Data-free Distillation of Denoising Diffusion Models with Bootstrapping8 Jun
  9. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance3 Oct
  10. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec

Other references · 34

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  5. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  6. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
  7. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  8. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Modelscited by 3,595
  9. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  11. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  12. 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
22 more
  1. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  2. 2018Averaging Weights Leads to Wider Optima and Better Generalizationcited by 1,194
  3. 2022MaskGIT: Masked Generative Image Transformercited by 1,082
  4. 2019Improved Precision and Recall Metric for Assessing Generative Modelscited by 925
  5. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  6. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 847
  7. 2023Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Modelscited by 696
  8. 2021CogView: Mastering Text-to-Image Generation via Transformerscited by 691
  9. 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
  10. 2023Scaling up GANs for Text-to-Image Synthesiscited by 492
  11. 2023InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generationcited by 387
  12. 2022Dataless Knowledge Fusion by Merging Weights of Language Modelscited by 384
  13. 2023Diffusion Self-Guidance for Controllable Image Generationcited by 305
  14. 2023StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesiscited by 212
  15. 2023JourneyDB: A Benchmark for Generative Image Understandingcited by 203
  16. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165
  17. 2022Fusing finetuned models for better pretrainingcited by 110
  18. 2023SwiftBrush: One-Step Text-to-Image Diffusion Model with Variational Score Distillationcited by 109
  19. 2023Deep Model Fusion: A Surveycited by 89
  20. 2023Divide & Bind Your Attention for Improved Generative Semantic Nursingcited by 80
  21. 2023A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesiscited by 78
  22. 2023HiPA: Enabling One-Step Text-to-Image Diffusion Models via High-Frequency-Promoting Adaptationcited by 16

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 24; 2026: 14.

45 papers.

Sort:

By area:

  1. 2024Adversarial Diffusion Compression for Real-World Image Super-Resolutioncited by 49
  2. 2025One-step Diffusion Models with f-Divergence Distribution Matchingcited by 43
  3. 2024SwiftEdit: Lightning Fast Text-Guided Image Editing via One-Step Diffusioncited by 28
  4. 2024SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Devicecited by 25
  5. 2025One-Step Diffusion-Based Image Compression with Semantic Distillationcited by 23
  6. 2026ChordEdit: One-Step Low-Energy Transport for Image Editingcited by 17
  7. 2024NitroFusion: High-Fidelity Single-Step Diffusion through Dynamic Adversarial Trainingcited by 16
  8. 2024Self-Corrected Flow Distillation for Consistent One-Step and Few-Step Text-to-Image Generationcited by 14
  9. 2025FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistencycited by 13
  10. 2025Normalized Attention Guidance: Universal Negative Guidance for Diffusion Modelscited by 12
  11. 2025Few-Step Diffusion via Score identity Distillationcited by 10
  12. 2025Fast RoPE Attention: Combining the Polynomial Method and Fast Fourier Transformcited by 9
33 more
  1. 2025SD3.5-Flash: Distribution-Guided Distillation of Generative Flowscited by 9
  2. 2024Supercharged One-step Text-to-Image Diffusion Models with Negative Promptscited by 8
  3. 2025Taming Diffusion Transformer for Efficient Mobile Video Generation in Secondscited by 8
  4. 2025Only Large Weights (And Not Skip Connections) Can Prevent the Perils of Rank Collapsecited by 7
  5. 2025CSD-VAR: Content-Style Decomposition in Visual Autoregressive Modelscited by 6
  6. 2025Improved Training Technique for Shortcut Modelscited by 6
  7. 2025Human Body Restoration with One-Step Diffusion Model and A New Benchmarkcited by 5
  8. 2025One-Way Ticket:Time-Independent Unified Encoder for Distilling Text-to-Image Diffusion Modelscited by 5
  9. 2025Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddingscited by 5
  10. 2026Anti-I2V: Safeguarding your photos from malicious image-to-video generationcited by 5
  11. 2024FADA: Fast Diffusion Avatar Synthesis with Mixed-Supervised Multi-CFG Distillationcited by 4
  12. 2025MIND-Edit: MLLM Insight-Driven Editing via Language-Vision Projectioncited by 4
  13. 2025FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editingcited by 4
  14. 2025From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Agingcited by 3
  15. 2026Fast-SAM3D: 3Dfy Anything in Images but Fastercited by 3
  16. 2025One-Step Residual Shifting Diffusion for Image Super-Resolution via Distillationcited by 2
  17. 2025Not All Parameters Matter: Masking Diffusion Models for Enhancing Generation Abilitycited by 2
  18. 2026InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpaintingcited by 2
  19. 2026WhereEdit: Mask-aware Local Latent Editing for One-Step Image Editingcited by 2
  20. 2025FA-Seg: A Fast and Accurate Diffusion-Based Method for Open-Vocabulary Segmentationcited by 1
  21. 2025One-step Diffusion Models with Bregman Density Ratio Matchingcited by 1
  22. 2025Adversarial Concept Distillation for One-Step Diffusion Personalizationcited by 1
  23. 2026SwiftAudio: Data-Efficient Caption-Only Distillation for One-Step Text-to-Audio Diffusion-based Generationcited by 1
  24. 2025Diversity Has Always Been There in Your Visual Autoregressive Modelscited by 0
  25. 2025FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generationcited by 0
  26. 2026WaDi: Weight Direction-aware Distillation for One-step Image Synthesiscited by 0
  27. 2026SwiftPie: Lightning-fast Subject-driven Image Personalization via One step Diffusioncited by 0
  28. 2026ARIA: Adaptive Region-Based Importance Allocation for Conditional Diffusion Distillationcited by 0
  29. 2026Cross-Space Distillation: Teaching One-Step Students with Modern Diffusion Teacherscited by 0
  30. 2026OSVE: One Step Video Editing with One Step Diffusion Modelscited by 0
  31. 2026ChordVideo: One-Step, Training-Free, Temporally Consistent Video Editing via Low-Energy Transportcited by 0
  32. 2026Preserve More Details: Mitigating Content Drift in Real-World Image Super-Resolutioncited by 0
  33. 2026Beyond Temporal Smoothing: Spatial Energy Budgets Stabilize One-Step Diffusion Editingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026i1: A Simple and Fully Open Recipe for Strong Text-to-Image Models
  2. 2021Diffusion Models Beat GANs on Image Synthesis
  3. 2025Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation
  4. 2024Latent Denoising Diffusion GAN: Faster sampling, Higher image quality
  5. 2026Analyzing and Improving Fast Sampling of Text-to-Image Diffusion Models
  6. 2026Abra: Scaling Diffusion Image Training
  7. 2024You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs
  8. 2021Palette: Image-to-Image Diffusion Models