mlsanityData to 7 Oct 2026

FlowFixer: Towards Detail-Preserving Subject-Driven Generation

arXiv 2602.21402 ↗First posted 24 Feb 2026cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We present FlowFixer, a refinement framework for subject-driven generation (SDG) that restores fine details lost during generation caused by changes in scale and perspective of a subject. FlowFixer proposes direct image-to-image translation from visual references, avoiding ambiguities in language prompts. To enable image-to-image training, we introduce a one-step denoising scheme to generate self-supervised training data, which automatically removes high-frequency details while preserving global structure, effectively simulating real-world SDG errors. We further propose a keypoint matching-based metric to properly assess fidelity in details beyond semantic similarities usually measured by CLIP or DINO. Experimental results demonstrate that FlowFixer outperforms state-of-the-art SDG methods in both qualitative and quantitative evaluations, setting a new benchmark for high-fidelity subject-driven generation.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 49 of its 54 references that are in the map. First posted on arXiv 24 Feb 2026.

Builds on

49 of 54 references.

References · 49

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  7. 2022Scalable Diffusion Models with Transformerscited by 5,931
  8. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  9. 2022Flow Matching for Generative Modelingcited by 5,426
  10. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,290
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  12. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
37 more
  1. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,286
  2. 2023Qwen Technical Reportcited by 3,273
  3. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  4. 2022An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversioncited by 2,231
  5. 2021SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equationscited by 1,903
  6. 2023IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Modelscited by 1,439
  7. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
  8. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,339
  9. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,172
  10. 2022Multi-Concept Customization of Text-to-Image Diffusioncited by 1,099
  11. 2025FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Spacecited by 960
  12. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  13. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
  14. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  15. 2022DiffEdit: Diffusion-based semantic image editing with mask guidancecited by 643
  16. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulationcited by 640
  17. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  18. 2023Zero-shot Image-to-Image Translationcited by 503
  19. 2023BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editingcited by 438
  20. 2024OmniGen: Unified Image Generationcited by 388
  21. 2024OminiControl: Minimal and Universal Control for Diffusion Transformercited by 334
  22. 2025OmniGen2: Towards Instruction-Aligned Multimodal Generationcited by 241
  23. 2023Inpaint Anything: Segment Anything Meets Image Inpaintingcited by 233
  24. 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpaintingcited by 229
  25. 2023A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpaintingcited by 168
  26. 2025Less-to-More Generalization: Unlocking More Controllability by In-Context Generationcited by 153
  27. 2023LEDITS++: Limitless Image Editing using Text-to-Image Modelscited by 147
  28. 2023Localizing Object-level Shape Variations with Text-to-Image Diffusion Modelscited by 142
  29. 2024DreamBench++: A Human-Aligned Benchmark for Personalized Image Generationcited by 131
  30. 2024DiffEditor: Boosting Accuracy and Flexibility on Diffusion-based Image Editingcited by 88
  31. 2023Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulationcited by 61
  32. 2025OminiControl2: Efficient Conditioning for Diffusion Transformerscited by 56
  33. 2024OmniGlue: Generalizable Feature Matching with Foundation Model Guidancecited by 55
  34. 2025FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Modelcited by 31
  35. 2024Analogist: Out-of-the-box Visual In-Context Learning with Image Diffusion Modelcited by 30
  36. 2025Fine-Grained Erasure in Text-to-Image Diffusion-based Foundation Modelscited by 22
  37. 2023BARET : Balanced Attention based Real image Editing driven by Target-text Inversioncited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Diagnosing and Correcting Concept Omission in Multimodal Diffusion Transformerscited by 1