mlsanityData to 7 Oct 2026

FlexiEdit: Frequency-Aware Latent Refinement for Enhanced Non-Rigid Editing

arXiv 2407.17850 ↗First posted 25 Jul 2024cs.CVcited by 31

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

Abstract (arXiv)

Current image editing methods primarily utilize DDIM Inversion, employing a two-branch diffusion approach to preserve the attributes and layout of the original image. However, these methods encounter challenges with non-rigid edits, which involve altering the image's layout or structure. Our comprehensive analysis reveals that the high-frequency components of DDIM latent, crucial for retaining the original image's key features and layout, significantly contribute to these limitations. Addressing this, we introduce FlexiEdit, which enhances fidelity to input text prompts by refining DDIM latent, by reducing high-frequency components in targeted editing areas. FlexiEdit comprises two key components: (1) Latent Refinement, which modifies DDIM latent to better accommodate layout adjustments, and (2) Edit Fidelity Enhancement via Re-inversion, aimed at ensuring the edits more accurately reflect the input text prompts. Our approach represents notable progress in image editing, particularly in performing complex non-rigid edits, showcasing its enhanced capability through comparative experiments.

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 35 of its 36 references that are in the map. First posted on arXiv 25 Jul 2024.

Builds on

35 of 36 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024Wavelet-Guided Acceleration of Text Inversion in Diffusion-Based Image Editing18 Jan
  2. 2023Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code2 Oct
  3. 2023Improving Tuning-Free Real Image Editing with Proximal Guidance8 Jun
  4. 2023Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models26 May
  5. 2023StyleDiffusion: Prompt-Embedding Inversion for Text-Based Editing28 Mar
  6. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Models17 Nov
  7. 2022DiffEdit: Diffusion-based semantic image editing with mask guidance20 Oct
  8. 2022Imagic: Text-Based Real Image Editing with Diffusion Models17 Oct
  9. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  10. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr
  11. 2021GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models20 Dec
  12. 2021Blended Diffusion for Text-driven Editing of Natural Images29 Nov
1 more
  1. 2021DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation6 Oct

Other references · 22

  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. 2020Denoising Diffusion Implicit Modelscited by 9,655
  6. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  7. 2022Classifier-Free Diffusion Guidancecited by 5,717
  8. 2022Generative Adversarial Networkscited by 5,603
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2022Prompt-to-Prompt Image Editing with Cross Attention Controlcited by 2,409
  11. 2022Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generationcited by 958
  12. 2022Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translationcited by 897
10 more
  1. 2023MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editingcited by 722
  2. 2017Generative Adversarial Networks: An Overviewcited by 588
  3. 2016StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networkscited by 575
  4. 2023FateZero: Fusing Attentions for Zero-shot Text-based Video Editingcited by 462
  5. 2023TokenFlow: Consistent Diffusion Features for Consistent Video Editingcited by 440
  6. 2023ELITE: Encoding Visual Concepts into Textual Embeddings for Customized Text-to-Image Generationcited by 414
  7. 2022Splicing ViT Features for Semantic Appearance Transfercited by 209
  8. 2023FreeInit: Bridging Initialization Gap in Video Diffusion Modelscited by 93
  9. 2023Object-aware Inversion and Reassembly for Image Editingcited by 29
  10. 2024FRAG: Frequency Adapting Group for Diffusion Video Editingcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 5; 2025: 14; 2026: 12.

31 papers.

Sort:

By area:

  1. 2024Unveil Inversion and Invariance in Flow Transformer for Versatile Image Editingcited by 34
  2. 2025StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfercited by 23
  3. 2024TVG: A Training-free Transition Video Generation Method with Diffusion Modelscited by 15
  4. 2024CLIPDrag: Combining Text-based and Drag-based Instructions for Image Editingcited by 12
  5. 2024TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animationcited by 12
  6. 2025FDS: Frequency-Aware Denoising Score for Text-Guided Latent Diffusion Image Editingcited by 12
  7. 2025ITA-MDT: Image-Timestep-Adaptive Masked Diffusion Transformer Framework for Image-Based Virtual Try-Oncited by 10
  8. 2024MDSGen: Fast and Efficient Masked Diffusion Temporal-Aware Transformers for Open-Domain Sound Generationcited by 9
  9. 2025AttenST: A Training-Free Attention-Driven Style Transfer Framework with Pre-Trained Diffusion Modelscited by 8
  10. 2025FlowDrag: 3D-aware Drag-based Image Editing with Mesh-guided Deformation Vector Flow Fieldscited by 8
  11. 2025FIA-Edit: Frequency-Interactive Attention for Efficient and High-Fidelity Inversion-Free Text-Guided Image Editingcited by 8
  12. 2025Learning Plug-and-play Memory for Guiding Video Diffusion Modelscited by 7
19 more
  1. 2025Cora: Correspondence-aware image editing using few step diffusioncited by 5
  2. 2025PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detectioncited by 5
  3. 2025Delta Rectified Flow Sampling for Text-to-Image Editingcited by 4
  4. 2025Occlusion-robust Stylization for Drawing-based 3D Animationcited by 3
  5. 2026Why Do DiT Editors Drift? Plug-and-Play Low Frequency Alignment in VAE Latent Spacecited by 3
  6. 2026A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion Transformerscited by 2
  7. 2026TanGO: Training-Free 3D Editing via Tangent-Space Guidance and Optimizationcited by 2
  8. 2025Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptationcited by 1
  9. 2026Towards Source-Aware Object Swapping with Initial Noise Perturbationcited by 1
  10. 2025CoStoDet-DDPM: Collaborative Training of Stochastic and Deterministic Models Improves Surgical Workflow Anticipation and Recognitioncited by 0
  11. 2025Q-Align: Alleviating Attention Leakage in Zero-Shot Appearance Transfer via Query-Query Alignmentcited by 0
  12. 2026Beyond Rigid: Benchmarking Non-Rigid Video Editingcited by 0
  13. 2026MIRAGE: Benchmarking and Aligning Multi-Instance Image Editingcited by 0
  14. 2026Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learningcited by 0
  15. 2026BindEdit: Taming Attention Leakage for Precise Multi-Object Image Editingcited by 0
  16. 2026SPECSIA: Stylization Dataset for Novel-View Enhancement in Drawing-based 3D Animationcited by 0
  17. 2026GADA: Geometry-Aware Deformable Aggregation for Image-Based Gaussian Splattingcited by 0
  18. 2026InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360deg Imagecited by 0
  19. 2026Anchoring and Steering Diffusion: Enhancing the Faithfulness of Text-to-Image Generation at Inference Timecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Latent Inversion with Timestep-aware Sampling for Training-free Non-rigid Editing
  2. 2025Tuning-Free Image Editing with Fidelity and Editability via Unified Latent Diffusion Model
  3. 2025FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing
  4. 2026ResetEdit: Precise Text-guided Editing of Generated Image via Resettable Starting Latent
  5. 2024FreeDiff: Progressive Frequency Truncation for Image Editing with Diffusion Models
  6. 2025LatentEdit: Adaptive Latent Control for Consistent Semantic Editing
  7. 2023Inversion-Free Image Editing with Natural Language
  8. 2025InstantEdit: Text-Guided Few-Step Image Editing with Piecewise Rectified Flow