SkyReels-Text: Fine-grained Font-Controllable Text Editing for Poster Design

2025-11-17

AI Summary

This work addresses the fine-grained, font-aware text editing challenge in professional poster design—namely, precisely modifying localized text under multi-font stylistic constraints while preserving visual harmony and layout intent. We propose a diffusion-based framework that requires neither font labels nor test-time fine-tuning. Our method integrates a font-aware text rendering module with a multi-region collaborative editing mechanism, enabling arbitrary font control solely from user-provided glyph crop samples. Compared to existing image editing models, ours achieves significantly improved text fidelity and visual realism, attaining state-of-the-art performance across multiple benchmarks. Notably, it supports complex fonts—including handwritten styles—and, for the first time, enables professional-grade typographic consistency editing without access to font metadata or explicit font identification.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP

Application Category

• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Artistic design such as poster design often demands rapid yet precise modification of textual content while preserving visual harmony and typographic intent, especially across diverse font styles. Although modern image editing models have grown increasingly powerful, they still fall short in fine-grained, font-aware text manipulation, limiting their utility in professional design workflows such as poster editing. To address this issue, we present SkyReels-Text, a novel font-controllable framework for precise poster text editing. Our method enables simultaneous editing of multiple text regions, each rendered in distinct typographic styles, while preserving the visual appearance of non-edited regions. Notably, our model requires neither font labels nor fine-tuning during inference: users can simply provide cropped glyph patches corresponding to their desired typography, even if the font is not included in any standard library. Extensive experiments on multiple datasets, including handwrittent text benchmarks, SkyReels-Text achieves state-of-the-art performance in both text fidelity and visual realism, offering unprecedented control over font families, and stylistic nuances. This work bridges the gap between general-purpose image editing and professional-grade typographic design.

Problem

• Fine-grained font-aware text manipulation for professional design workflows
• Editing multiple text regions with distinct typographic styles simultaneously
• Font-controllable editing without requiring font labels or fine-tuning

Innovation

• Font-controllable framework for precise text editing
• Enables multi-region editing with distinct typographic styles
• Uses glyph patches without font labels or fine-tuning