Abstract

Diffusion transformers have demonstrated remarkable generation quality, albeit requiring longer training iterations and numerous inference steps. In each denoising step, diffusion transformers encode the noisy inputs to extract the lower-frequency semantic component and then decode the higher frequency with identical modules. This scheme creates an inherent optimization dilemma: encoding low-frequency semantics necessitates reducing high-frequency components, creating tension between semantic encoding and high-frequency decoding. To resolve this challenge, we propose a new Decoupled Diffusion Transformer (DDT), with a decoupled design of a dedicated condition encoder for semantic extraction alongside a specialized velocity decoder. Our experiments reveal that a more substantial encoder yields performance improvements as model size increases. For ImageNet 256×256, Our DDT-XL/2 achieves a new state-of-the-art performance of 1.31 FID (nearly 4× faster training convergence compared to previous diffusion transformers). For ImageNet 512×512, Our DDT-XL/2 achieves a new state-of-the-art FID of 1.28. Additionally, as a beneficial by-product, our decoupled architecture enhances inference speed by enabling the sharing self-condition between adjacent denoising steps. To minimize performance degradation, we propose a novel statistical dynamic programming approach to identify optimal sharing strategies.

Paper: https://arxiv.org/abs/2504.05741

Code: https://github.com/MCG-NJU/DDT

Demo: https://huggingface.co/spaces/MCG-NJU/DDT