paper-with-me

Papers

EasyText: Controllable Diffusion Transformer for Multilingual Text Rendering

2025-05-30 · Runnan Lu, Yuxuan Zhang, Jiaming Liu, Haofan Wang, Yiren Song

Generating accurate multilingual text with diffusion models has long been desired but remains challenging. Recent methods have made progress in rendering text in a single language, but rendering arbitrary languages is still an unexplored area. This paper introduces EasyText, a text rendering framework based on DiT (Diffusion Transformer), which connects denoising latents with multilingual character tokens encoded as character tokens. We propose character positioning encoding and position encoding interpolation techniques to achieve controllable and precise text rendering. Additionally, we construct a large-scale synthetic text image dataset with 1 million multilingual image-text annotations as well as a high-quality dataset of 20K annotated images, which are used for pretraining and fine-tuning respectively. Extensive experiments and evaluations demonstrate the effectiveness and advancement of our approach in multilingual text rendering, visual quality, and layout-aware text integration.

📄 PDF Abstract BibTeX arXiv:2505.24417

Code (1)

songyiren725/easytext 공식 구현 pytorch

Tasks

Denoising

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

ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations

2025-02-16 · Bowen Jiang, Yuan Yuan, Xinyi Bai, Zhuoqun Hao 외

This work demonstrates that diffusion models can achieve font-controllable multilingual text rendering using just raw images without font label annotations. Visual text rendering remains a significant challenge. While re…

Text Segmentation

SceneVTG++: Controllable Multilingual Visual Text Generation in the Wild

2025-01-06 · Jiawei Liu, Yuanzhi Zhu, Feiyu Gao, Zhibo Yang 외

Generating visual text in natural scene images is a challenging task with many unsolved problems. Different from generating text on artificially designed images (such as posters, covers, cartoons, etc.), the text in natu…

AttributeOptical Character RecognitionOptical Character Recognition (OCR)Text Detection+2

NanoControl: A Lightweight Framework for Precise and Efficient Control in Diffusion Transformer

2025-08-14 · Shanyuan Liu, Jian Zhu, Junda Lu, Yue Gong 외 arxiv

Diffusion Transformers (DiTs) have demonstrated exceptional capabilities in text-to-image synthesis. However, in the domain of controllable text-to-image generation using DiTs, most existing methods still rely on the Con…

Text-to-Image Generation

Multilingual Controllable Transformer-Based Lexical Simplification

2023-07-05 · Kim Cheng SHEANG, Horacio Saggion

Text is by far the most ubiquitous source of knowledge and information and should be made easily accessible to as many people as possible; however, texts often contain complex words that hinder reading comprehension and …

Lexical SimplificationReading Comprehension

VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control

2024-07-17 · Sherwin Bahmani, Ivan Skorokhodov, Aliaksandr Siarohin, Willi Menapace 외

Modern text-to-video synthesis models demonstrate coherent, photorealistic generation of complex videos from a text description. However, most existing models lack fine-grained control over camera movement, which is crit…

Video Generation