AI RESEARCH
Long-Text-to-Image Generation via Compositional Prompt Decomposition
arXiv CS.CV
•
ArXi:2604.18258v1 Announce Type: new While modern text-to-image (T2I) models excel at generating images from intricate prompts, they struggle to capture the key details when the inputs are descriptive paragraphs. This limitation stems from the prevalence of concise captions that shape their