Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis
It addresses uncertainty in design choices for multi-modal generation, offering practical guidelines for future research, but is incremental as it focuses on exploration rather than introducing new methods.
This paper tackles the lack of detailed exploration in the deep fusion of large language models and diffusion transformers for text-to-image synthesis by conducting an empirical study with controlled comparisons and providing a reproducible training recipe.
This paper does not describe a new method; instead, it provides a thorough exploration of an important yet understudied design space related to recent advances in text-to-image synthesis -- specifically, the deep fusion of large language models (LLMs) and diffusion transformers (DiTs) for multi-modal generation. Previous studies mainly focused on overall system performance rather than detailed comparisons with alternative methods, and key design details and training recipes were often left undisclosed. These gaps create uncertainty about the real potential of this approach. To fill these gaps, we conduct an empirical study on text-to-image generation, performing controlled comparisons with established baselines, analyzing important design choices, and providing a clear, reproducible recipe for training at scale. We hope this work offers meaningful data points and practical guidelines for future research in multi-modal generation.