paper-with-me

Papers

CustomText: Customized Textual Image Generation using Diffusion Models

2024-05-21 · Shubham Paliwal, Arushi Jain, Monika Sharma, Vikram Jamwal, Lovekesh Vig

Textual image generation spans diverse fields like advertising, education, product packaging, social media, information visualization, and branding. Despite recent strides in language-guided image synthesis using diffusion models, current models excel in image generation but struggle with accurate text rendering and offer limited control over font attributes. In this paper, we aim to enhance the synthesis of high-quality images with precise text customization, thereby contributing to the advancement of image generation models. We call our proposed method CustomText. Our implementation leverages a pre-trained TextDiffuser model to enable control over font color, background, and types. Additionally, to address the challenge of accurately rendering small-sized fonts, we train the ControlNet model for a consistency decoder, significantly enhancing text-generation performance. We assess the performance of CustomText in comparison to previous methods of textual image generation on the publicly available CTW-1500 dataset and a self-curated dataset for small-text generation, showcasing superior results.

📄 PDF Abstract BibTeX arXiv:2405.12531

Code (0)

등록된 구현이 없습니다.

Tasks

DecoderImage GenerationText Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Non-confusing Generation of Customized Concepts in Diffusion Models

2024-05-11 · Wang Lin, Jingyuan Chen, Jiaxin Shi, Yichen Zhu 외

We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, d…

MoE-DiffIR: Task-customized Diffusion Priors for Universal Compressed Image Restoration

2024-07-15 · Yulin Ren, Xin Li, Bingchen Li, Xingrui Wang 외

We present MoE-DiffIR, an innovative universal compressed image restoration (CIR) method with task-customized diffusion priors. This intends to handle two pivotal challenges in the existing CIR methods: (i) lacking adapt…

Image RestorationMixture-of-ExpertsTexture Synthesis

DreamVideo: Composing Your Dream Videos with Customized Subject and Motion

2023-12-07 · CVPR 2024 1 · Yujie Wei, Shiwei Zhang, Zhiwu Qing, Hangjie Yuan 외

Customized generation using diffusion models has made impressive progress in image generation, but remains unsatisfactory in the challenging video generation task, as it requires the controllability of both subjects and …

Image GenerationVideo Generation

Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models

2024-08-20 · Cong Wan, Yuhang He, Xiang Song, Yihong Gong

Diffusion models have revolutionized customized text-to-image generation, allowing for efficient synthesis of photos from personal data with textual descriptions. However, these advancements bring forth risks including p…

Image GenerationText to Image GenerationText-to-Image Generation

DiffMorph: Text-less Image Morphing with Diffusion Models

2024-01-01 · Shounak Chatterjee

Text-conditioned image generation models are a prevalent use of AI image synthesis, yet intuitively controlling output guided by an artist remains challenging. Current methods require multiple images and textual prompts …

Image GenerationImage Morphing