Insert Anything: Image Insertion via In-Context Editing in DiT

• URL: http://arxiv.org/abs/2504.15009v1
• Date: Mon, 21 Apr 2025 10:19:12 GMT
• Title: Insert Anything: Image Insertion via In-Context Editing in DiT
• Authors: Wensong Song, Hong Jiang, Zongxing Yang, Ruijie Quan, Yi Yang,
• Abstract summary: We present a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance.<n>Our approach is trained once on our new AnyInsertion dataset--comprising 120K prompt-image pairs covering diverse tasks such as person, object, and garment insertion--and effortlessly generalizes to a wide range of insertion scenarios.
• Score: 19.733787045511775
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work presents Insert Anything, a unified framework for reference-based image insertion that seamlessly integrates objects from reference images into target scenes under flexible, user-specified control guidance. Instead of training separate models for individual tasks, our approach is trained once on our new AnyInsertion dataset--comprising 120K prompt-image pairs covering diverse tasks such as person, object, and garment insertion--and effortlessly generalizes to a wide range of insertion scenarios. Such a challenging setting requires capturing both identity features and fine-grained details, while allowing versatile local adaptations in style, color, and texture. To this end, we propose to leverage the multimodal attention of the Diffusion Transformer (DiT) to support both mask- and text-guided editing. Furthermore, we introduce an in-context editing mechanism that treats the reference image as contextual information, employing two prompting strategies to harmonize the inserted elements with the target scene while faithfully preserving their distinctive features. Extensive experiments on AnyInsertion, DreamBooth, and VTON-HD benchmarks demonstrate that our method consistently outperforms existing alternatives, underscoring its great potential in real-world applications such as creative content generation, virtual try-on, and scene composition.

Related papers

• Object-level Visual Prompts for Compositional Image Generation [75.6085388740087]
  We introduce a method for composing object-level visual prompts within a text-to-image diffusion model.<n>A key challenge in this task is to preserve the identity of the objects depicted in the input visual prompts.<n>We introduce a new KV-mixed cross-attention mechanism, in which keys and values are learned from distinct visual representations.
  arXiv  Detail & Related papers  (2025-01-02T18:59:44Z)
• SGEdit: Bridging LLM with Text2Image Generative Model for Scene Graph-based Image Editing [42.23117201457898]
  We introduce a new framework that integrates large language model (LLM) with Text2 generative model for graph-based image editing. Our framework significantly outperforms existing image editing methods in terms of editing precision and scene aesthetics.
  arXiv  Detail & Related papers  (2024-10-15T17:40:48Z)
• A Survey of Multimodal-Guided Image Editing with Text-to-Image Diffusion Models [117.77807994397784]
  Image editing aims to edit the given synthetic or real image to meet the specific requirements from users. Recent significant advancement in this field is based on the development of text-to-image (T2I) diffusion models. T2I-based image editing methods significantly enhance editing performance and offer a user-friendly interface for modifying content guided by multimodal inputs.
  arXiv  Detail & Related papers  (2024-06-20T17:58:52Z)
• Zero-shot Image Editing with Reference Imitation [50.75310094611476]
  We present a new form of editing, termed imitative editing, to help users exercise their creativity more conveniently. We propose a generative training framework, dubbed MimicBrush, which randomly selects two frames from a video clip, masks some regions of one frame, and learns to recover the masked regions using the information from the other frame. We experimentally show the effectiveness of our method under various test cases as well as its superiority over existing alternatives.
  arXiv  Detail & Related papers  (2024-06-11T17:59:51Z)
• Unified Editing of Panorama, 3D Scenes, and Videos Through Disentangled Self-Attention Injection [60.47731445033151]
  We propose a novel unified editing framework that combines the strengths of both approaches by utilizing only a basic 2D image text-to-image (T2I) diffusion model. Experimental results confirm that our method enables editing across diverse modalities including 3D scenes, videos, and panorama images.
  arXiv  Detail & Related papers  (2024-05-27T04:44:36Z)
• Choose What You Need: Disentangled Representation Learning for Scene Text Recognition, Removal and Editing [47.421888361871254]
  Scene text images contain not only style information (font, background) but also content information (character, texture) Previous representation learning methods use tightly coupled features for all tasks, resulting in sub-optimal performance. We propose a Disentangled Representation Learning framework (DARLING) aimed at disentangling these two types of features for improved adaptability.
  arXiv  Detail & Related papers  (2024-05-07T15:00:11Z)
• VLLMs Provide Better Context for Emotion Understanding Through Common Sense Reasoning [66.23296689828152]
  We leverage the capabilities of Vision-and-Large-Language Models to enhance in-context emotion classification. In the first stage, we propose prompting VLLMs to generate descriptions in natural language of the subject's apparent emotion. In the second stage, the descriptions are used as contextual information and, along with the image input, are used to train a transformer-based architecture.
  arXiv  Detail & Related papers  (2024-04-10T15:09:15Z)
• Locate, Assign, Refine: Taming Customized Promptable Image Inpainting [22.163855501668206]
  We introduce the multimodal promptable image inpainting project: a new task model, and data for taming customized image inpainting.<n>We propose LAR-Gen, a novel approach for image inpainting that enables seamless inpainting of specific region in images corresponding to the mask prompt.<n>Our LAR-Gen adopts a coarse-to-fine manner to ensure the context consistency of source image, subject identity consistency, local semantic consistency to the text description, and smoothness consistency.
  arXiv  Detail & Related papers  (2024-03-28T16:07:55Z)
• Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model [22.975965453227477]
  We introduce a new framework called textitPaste, Inpaint and Harmonize via Denoising (PhD) In our experiments, we apply PhD to both subject-driven image editing tasks and explore text-driven scene generation given a reference subject.
  arXiv  Detail & Related papers  (2023-06-13T07:43:10Z)
• TaleCrafter: Interactive Story Visualization with Multiple Characters [49.14122401339003]
  This paper proposes a system for generic interactive story visualization. It is capable of handling multiple novel characters and supporting the editing of layout and local structure. The system comprises four interconnected components: story-to-prompt generation (S2P), text-to-generation (T2L), controllable text-to-image generation (C-T2I) and image-to-video animation (I2V)
  arXiv  Detail & Related papers  (2023-05-29T17:11:39Z)
• Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion [34.662798793560995]
  We present a simple yet highly effective approach to personalization using highly personalized (PerHi) text embedding. Our method does not require model fine-tuning or identifiers, yet still enables manipulation of background, texture, and motion with just a single image and target text.
  arXiv  Detail & Related papers  (2023-03-15T17:07:45Z)
• SceneComposer: Any-Level Semantic Image Synthesis [80.55876413285587]
  We propose a new framework for conditional image synthesis from semantic layouts of any precision levels. The framework naturally reduces to text-to-image (T2I) at the lowest level with no shape information, and it becomes segmentation-to-image (S2I) at the highest level. We introduce several novel techniques to address the challenges coming with this new setup.
  arXiv  Detail & Related papers  (2022-11-21T18:59:05Z)

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.