Planning and Rendering in Concert: DeepFusion of Autoregressive Layouts and Diffusion for Visual Text Generation

arXiv:2609.22916 · cs.CV · Submitted 2026-09-19 · Read on arXiv

cs.CV

Submitted: 2026-09-19

Updated: 2026-09-19

Code: https://github.com/kakaobrain/coyo-dataset

Terminology

• Accuracy — 18× in this paper · explained in 1 episode
• Transformer — 14× in this paper · explained in 2 episodes
• Diffusion Model — 10× in this paper · explained in 8 episodes
• Diffusion Models — 8× in this paper · explained in 6 episodes
• Phase-Aware Attention Modulation — 7× in this paper
• Fidelity — 6× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Alignment — 3× in this paper · explained in 1 episode
• Consistency — 3× in this paper · explained in 3 episodes
• Linear probe — 3× in this paper · explained in 2 episodes
• Unified Framework — 3× in this paper · explained in 5 episodes
• Local Optimization — 2× in this paper · explained in 2 episodes
• RAG — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 1× in this paper · explained in 2 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer
• BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset
• BLIP3o-NEXT: Next Frontier of Native Image Generation
• PrismLayers: Open Data for High-Quality Multi-Layer Transparent Image Generative Models
• PosterCraft: Rethinking High-Quality Aesthetic Poster Generation in a Unified Framework
• Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling
• Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement
• Emerging Properties in Unified Multimodal Pretraining
• Investigating Text Insulation and Attention Mechanisms for Complex Visual Text Generation
• Seedream 3.0 Technical Report
• X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
• PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models
• DreamPoster: A Unified Framework for Image-Conditioned Generative Poster Design
• Improving Diffusion Models for Scene Text Editing with Dual Encoders
• ControlText: Unlocking Controllable Fonts in Multilingual Text Rendering without Font Annotations
• JoyType: A Robust Design for Multilingual Visual Text Creation
• TextCenGen: Attention-Guided Text-Centric Background Adaptation for Text-to-Image Generation
• Glyph-ByT5-v2: A Strong Aesthetic Baseline for Accurate Multilingual Visual Text Rendering
• Decoupled Weight Decay Regularization
• Uni-Layout: Integrating Human Feedback in Unified Layout Generation and Evaluation

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models