DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models

• URL: http://arxiv.org/abs/2607.12539v1
• Date: Tue, 14 Jul 2026 09:09:52 GMT
• Title: DiTailed: Ensuring Visual Object Consistency in Text-Image-to-Image Flow Matching Models
• Abstract summary: We introduce ABO-Edit, a dataset specifically designed to study object consistency.<n>Second, we uncover an overlooked property of image-editing rectified flow models: the conditioning embedding space.<n>Third, exploiting this finding, we propose FlowMirror, a parameter-free auxiliary loss that supervises this conditioning embedding space.
• Score: 5.68358172889959
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite remarkable progress in text-guided image editing, generative models frequently fail to preserve visual object consistency, defined as the preservation of a subject's key attributes throughout the editing process. We address this limitation through three contributions. First, we introduce ABO-Edit, a dataset specifically designed to study object consistency, comprising over 12,000 triplets of source images, editing prompts, and high-quality target images rendered from artist-designed 3D assets, with multi-view coverage and human-verified quality control. Second, we uncover an overlooked property of image-editing rectified flow models: the conditioning embedding space, not directly supervised during training, encodes a prediction of the final generated image even at high noise levels. Third, exploiting this finding, we propose FlowMirror, a parameter-free auxiliary loss that supervises this conditioning embedding space. Without architectural changes, our method improves generation quality across several metrics over baselines.

Related papers

• Advancing 3D Gaussian Splatting Editing with Complementary and Consensus Information [4.956066467858058]
  We present a novel framework for enhancing the visual fidelity and consistency of text-guided 3D Gaussian Splatting (3DGS) editing.<n>Our method demonstrates superior performance in rendering quality and view consistency compared to state-of-the-art approaches.
  arXiv  Detail & Related papers  (2025-03-14T17:15:26Z)
• Add-it: Training-Free Object Insertion in Images With Pretrained Diffusion Models [78.90023746996302]
  Add-it is a training-free approach that extends diffusion models' attention mechanisms to incorporate information from three key sources. Our weighted extended-attention mechanism maintains structural consistency and fine details while ensuring natural object placement. Human evaluations show that Add-it is preferred in over 80% of cases.
  arXiv  Detail & Related papers  (2024-11-11T18:50:09Z)
• DiffUHaul: A Training-Free Method for Object Dragging in Images [78.93531472479202]
  We propose a training-free method, dubbed DiffUHaul, for the object dragging task. We first apply attention masking in each denoising step to make the generation more disentangled across different objects. In the early denoising steps, we interpolate the attention features between source and target images to smoothly fuse new layouts with the original appearance.
  arXiv  Detail & Related papers  (2024-06-03T17:59:53Z)
• CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models [85.69959024572363]
  CustomNet is a novel object customization approach that explicitly incorporates 3D novel view synthesis capabilities into the object customization process. We introduce delicate designs to enable location control and flexible background control through textual descriptions or specific user-defined images. Our method facilitates zero-shot object customization without test-time optimization, offering simultaneous control over the viewpoints, location, and background.
  arXiv  Detail & Related papers  (2023-10-30T17:50:14Z)
• Text-to-image Editing by Image Information Removal [19.464349486031566]
  We propose a text-to-image editing model with an Image Information Removal module (IIR) that selectively erases color-related and texture-related information from the original image. Our experiments on CUB, Outdoor Scenes, and COCO shows that our edited images are preferred 35% more often than prior work.
  arXiv  Detail & Related papers  (2023-05-27T14:48:05Z)
• iEdit: Localised Text-guided Image Editing with Weak Supervision [53.082196061014734]
  We propose a novel learning method for text-guided image editing. It generates images conditioned on a source image and a textual edit prompt. It shows favourable results against its counterparts in terms of image fidelity, CLIP alignment score and qualitatively for editing both generated and real images.
  arXiv  Detail & Related papers  (2023-05-10T07:39:14Z)
• Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion Models [55.04969603431266]
  This paper proposes a method for generating images of customized objects specified by users. The method is based on a general framework that bypasses the lengthy optimization required by previous approaches. We demonstrate through experiments that our proposed method is able to synthesize images with compelling output quality, appearance diversity, and object fidelity.
  arXiv  Detail & Related papers  (2023-04-05T17:59:32Z)
• In-N-Out: Faithful 3D GAN Inversion with Volumetric Decomposition for Face Editing [28.790900756506833]
  3D-aware GANs offer new capabilities for view synthesis while preserving the editing functionalities of their 2D counterparts. GAN inversion is a crucial step that seeks the latent code to reconstruct input images or videos, subsequently enabling diverse editing tasks through manipulation of this latent code. We address this issue by explicitly modeling OOD objects from the input in 3D-aware GANs.
  arXiv  Detail & Related papers  (2023-02-09T18:59:56Z)
• Object-Centric Image Generation from Layouts [93.10217725729468]
  We develop a layout-to-image-generation method to generate complex scenes with multiple objects. Our method learns representations of the spatial relationships between objects in the scene, which lead to our model's improved layout-fidelity. We introduce SceneFID, an object-centric adaptation of the popular Fr'echet Inception Distance metric, that is better suited for multi-object images.
  arXiv  Detail & Related papers  (2020-03-16T21:40:09Z)

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.