Skip to main content

🏢 Central South University

Beyond Words: Advancing Long-Text Image Generation via Multimodal Autoregressive Models
·2885 words·14 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Image Generation 🏢 Central South University
LongTextAR advances long-text image generation via a novel tokenizer, enabling accurate, controllable, and high-fidelity text rendering in images.