DiT-Air: Revisiting the Efficiency of Diffusion Model Architecture Design in Text to Image Generation
Abstract
In this work, we empirically study Diffusion Transformers (DiTs) for text-to-image generation, focusing on architectural choices, text-conditioning strategies, and training protocols. We evaluate a range of DiT-based architectures--including PixArt-style and MMDiT variants--and compare them with a standard DiT variant which directly processes concatenated text and noise inputs. Surprisingly, our findings reveal that the performance of standard DiT is comparable with those specialized models, while demonstrating superior parameter-efficiency, especially when scaled up. Leveraging the layer-wise parameter sharing strategy, we achieve a further reduction of 66% in model size compared to an MMDiT architecture, with minimal performance impact. Building on an in-depth analysis of critical components such as text encoders and Variational Auto-Encoders (VAEs), we introduce DiT-Air and DiT-Air-Lite. With supervised and reward fine-tuning, DiT-Air achieves state-of-the-art performance on GenEval and T2I CompBench, while DiT-Air-Lite remains highly competitive, surpassing most existing models despite its compact size.
Community
GenEval: 82.9
T2I Comp-Bench: 59.5
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Multimodal Representation Alignment for Image Generation: Text-Image Interleaved Control Is Easier Than You Think (2025)
- TIDE : Temporal-Aware Sparse Autoencoders for Interpretable Diffusion Transformers in Image Generation (2025)
- LightGen: Efficient Image Generation through Knowledge Distillation and Direct Preference Optimization (2025)
- Unleashing the Potential of Large Language Models for Text-to-Image Generation through Autoregressive Representation Alignment (2025)
- Goku: Flow Based Video Generative Foundation Models (2025)
- Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation (2025)
- Aligning Text to Image in Diffusion Models is Easier Than You Think (2025)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper
Collections including this paper 0
No Collection including this paper