paper-with-me

홈 › Papers

SingleInsert: Inserting New Concepts from a Single Image into Text-to-Image Models for Flexible Editing

2023-10-12 · Zijie Wu, Chaohui Yu, Zhen Zhu, Fan Wang, Xiang Bai

Recent progress in text-to-image (T2I) models enables high-quality image generation with flexible textual control. To utilize the abundant visual priors in the off-the-shelf T2I models, a series of methods try to invert an image to proper embedding that aligns with the semantic space of the T2I model. However, these image-to-text (I2T) inversion methods typically need multiple source images containing the same concept or struggle with the imbalance between editing flexibility and visual fidelity. In this work, we point out that the critical problem lies in the foreground-background entanglement when learning an intended concept, and propose a simple and effective baseline for single-image I2T inversion, named SingleInsert. SingleInsert adopts a two-stage scheme. In the first stage, we regulate the learned embedding to concentrate on the foreground area without being associated with the irrelevant background. In the second stage, we finetune the T2I model for better visual resemblance and devise a semantic loss to prevent the language drift problem. With the proposed techniques, SingleInsert excels in single concept generation with high visual fidelity while allowing flexible editing. Additionally, SingleInsert can perform single-image novel view synthesis and multiple concepts composition without requiring joint training. To facilitate evaluation, we design an editing prompt list and introduce a metric named Editing Success Rate (ESR) for quantitative assessment of editing flexibility. Our project page is: https://jarrentwu1031.github.io/SingleInsert-web/

📄 PDF Abstract BibTeX arXiv:2310.08094

Code (0)

등록된 구현이 없습니다.

Tasks

Image GenerationImage to textNovel View Synthesis

Similar Papers 제목 키워드 기반

Rickrolling the Artist: Injecting Backdoors into Text Encoders for Text-to-Image Synthesis

2022-11-04 · ICCV 2023 1 · Lukas Struppek, Dominik Hintersdorf, Kristian Kersting

While text-to-image synthesis currently enjoys great popularity among researchers and the general public, the security of these models has been neglected so far. Many text-guided image generation models rely on pre-train…

Image Generation

Visualizing and Understanding GANs

2019-03-27 · ICLR Workshop DeepGenStruct 2019 · David Bau, Jun-Yan Zhu, Hendrik Strobelt, Bolei Zhou 외

We present an analytic framework to visualize and understand GANs at the unit-, object-, and scene-level. We first identify a group of interpretable units that are closely related to object concepts with a segmentation-b…

Object

Beyond Inserting: Learning Identity Embedding for Semantic-Fidelity Personalized Diffusion Generation

2024-01-31 · Yang Li, Songlin Yang, Wei Wang, Jing Dong

Advanced diffusion-based Text-to-Image (T2I) models, such as the Stable Diffusion Model, have made significant progress in generating diverse and high-quality images using text prompts alone. However, when non-famous use…

Image GenerationPersonalized Image Generation

Graph Integrated Multimodal Concept Bottleneck Model

2025-10-01 · Jiakai Lin, Jinchang Zhang, Guoyu Lu arxiv

With growing demand for interpretability in deep learning, especially in high stakes domains, Concept Bottleneck Models (CBMs) address this by inserting human understandable concepts into the prediction pipeline, but the…

Teleportraits: Training-Free People Insertion into Any Scene

2025-10-07 · Jialu Gao, K J Joseph, Fernando De La Torre arxiv

The task of realistically inserting a human from a reference image into a background scene is highly challenging, requiring the model to (1) determine the correct location and poses of the person and (2) perform high-qua…