GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing

• URL: http://arxiv.org/abs/2603.21176v1
• Date: Sun, 22 Mar 2026 11:33:30 GMT
• Title: GIDE: Unlocking Diffusion LLMs for Precise Training-Free Image Editing
• Abstract summary: We introduce GIDE (Grounded Inversion forDLLM Image Editing), a unified framework designed to bridge the gap between continuous diffusion models and training-free image editing.<n>GIDE incorporates a novel Discrete Noise Inversion mechanism that accurately captures latent noise patterns within the discrete token space.<n>To overcome the limitations of existing single-step evaluation protocols, we introduce GIDE-Bench.
• Score: 30.230365555184193
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While Diffusion Large Language Models (DLLMs) have demonstrated remarkable capabilities in multi-modal generation, performing precise, training-free image editing remains an open challenge. Unlike continuous diffusion models, the discrete tokenization inherent in DLLMs hinders the application of standard noise inversion techniques, often leading to structural degradation during editing. In this paper, we introduce GIDE (Grounded Inversion for DLLM Image Editing), a unified framework designed to bridge this gap. GIDE incorporates a novel Discrete Noise Inversion mechanism that accurately captures latent noise patterns within the discrete token space, ensuring high-fidelity reconstruction. We then decompose the editing pipeline into grounding, inversion, and refinement stages. This design enables GIDE supporting various editing instructions (text, point and box) and operations while strictly preserving the unedited background. Furthermore, to overcome the limitations of existing single-step evaluation protocols, we introduce GIDE-Bench, a rigorous benchmark comprising 805 compositional editing scenarios guided by diverse multi-modal inputs. Extensive experiments on GIDE-Bench demonstrate that GIDE significantly outperforms prior training-free methods, improving Semantic Correctness by 51.83% and Perceptual Quality by 50.39%. Additional evaluations on ImgEdit-Bench confirm its broad applicability, demonstrating consistent gains over trained baselines and yielding photorealistic consistency on par with leading models.

Related papers

• DuET: Dual Expert Trajectories for Diffusion Image Editing [42.49842620609682]
  We introduce DuET, a training-free inference method that temporarily relaxes source-image conditioning.<n>DuET consistently improves instruction relevance, semantic fidelity, and perceptual quality across diverse models and benchmarks.
  arXiv  Detail & Related papers  (2026-06-11T12:58:48Z)
• MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching [91.83651402045108]
  MT-EditFlow is a flow-matching reinforcement learning framework designed to optimize reward signals for sequential image editing.<n>We show that MT-EditFlow significantly improves performance across diverse base models.
  arXiv  Detail & Related papers  (2026-06-01T09:46:10Z)
• Training-Free Multi-Concept Image Editing [14.75123947134721]
  Concept Distillation Sampling (CDS) is a training-free framework for target-less, multi-concept image editing.<n>It overcomes the linguistic bottleneck of previous methods by integrating a highly stable distillation backbone.<n>Our method preserves instance fidelity without requiring reference samples of the desired edit.
  arXiv  Detail & Related papers  (2026-02-24T12:27:51Z)
• Edge-Aware Image Manipulation via Diffusion Models with a Novel Structure-Preservation Loss [32.26030534230571]
  We propose a novel Structure Preservation Loss (SPL) to quantify structural differences between input and edited images.<n>Our training-free approach integrates SPL directly into the diffusion model's generative process to ensure structural fidelity.<n> Experiments confirm SPL enhances structural fidelity, delivering state-of-the-art performance in latent-diffusion-based image editing.
  arXiv  Detail & Related papers  (2026-01-23T11:06:51Z)
• DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing [73.12011187146481]
  Inversion within Diffusion models aims to recover the latent noise representation for a real or generated image.<n>Most inversion approaches suffer from an intrinsic trade-off between reconstruction accuracy and editing flexibility.<n>We introduce Dual-Conditional Inversion (DCI), a novel framework that jointly conditions on the source prompt and reference image.
  arXiv  Detail & Related papers  (2025-06-03T07:46:44Z)
• Multimodal LLM-Guided Semantic Correction in Text-to-Image Diffusion [52.315729095824906]
  MLLM Semantic-Corrected Ping-Pong-Ahead Diffusion (PPAD) is a novel framework that introduces a Multimodal Large Language Model (MLLM) as a semantic observer during inference.<n>It performs real-time analysis on intermediate generations, identifies latent semantic inconsistencies, and translates feedback into controllable signals that actively guide the remaining denoising steps.<n>Extensive experiments demonstrate PPAD's significant improvements.
  arXiv  Detail & Related papers  (2025-05-26T14:42:35Z)
• Stable Flow: Vital Layers for Training-Free Image Editing [74.52248787189302]
  Diffusion models have revolutionized the field of content synthesis and editing.<n>Recent models have replaced the traditional UNet architecture with the Diffusion Transformer (DiT)<n>We propose an automatic method to identify "vital layers" within DiT, crucial for image formation.<n>Next, to enable real-image editing, we introduce an improved image inversion method for flow models.
  arXiv  Detail & Related papers  (2024-11-21T18:59:51Z)
• Taming Rectified Flow for Inversion and Editing [57.3742655030493]
  Rectified-flow-based diffusion transformers like FLUX and OpenSora have demonstrated outstanding performance in the field of image and video generation.<n>Despite their robust generative capabilities, these models often struggle with inaccuracies.<n>We propose RF-r, a training-free sampler that effectively enhances inversion precision by mitigating the errors in the inversion process of rectified flow.
  arXiv  Detail & Related papers  (2024-11-07T14:29:02Z)
• Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing [42.45138713525929]
  Effective editing requires inverting the source image into a latent space, a process often hindered by prediction errors inherent in DDIM inversion. We introduce the Logistic Schedule, a novel noise schedule designed to eliminate singularities, improve inversion stability, and provide a better noise space for image editing. Our approach requires no additional retraining and is compatible with various existing editing methods.
  arXiv  Detail & Related papers  (2024-10-24T14:07:02Z)
• Task-Oriented Diffusion Inversion for High-Fidelity Text-based Editing [60.730661748555214]
  We introduce textbfTask-textbfOriented textbfDiffusion textbfInversion (textbfTODInv), a novel framework that inverts and edits real images tailored to specific editing tasks. ToDInv seamlessly integrates inversion and editing through reciprocal optimization, ensuring both high fidelity and precise editability.
  arXiv  Detail & Related papers  (2024-08-23T22:16:34Z)
• High-Fidelity Diffusion-based Image Editing [19.85446433564999]
  The editing performance of diffusion models tends to be no more satisfactory even with increasing denoising steps. We propose an innovative framework where a Markov module is incorporated to modulate diffusion model weights with residual features. We introduce a novel learning paradigm aimed at minimizing error propagation during the editing process, which trains the editing procedure in a manner similar to denoising score-matching.
  arXiv  Detail & Related papers  (2023-12-25T12:12:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.