DiffiT: Diffusion Vision Transformers for Image Generation
This work addresses the need for more parameter-efficient and high-fidelity image generation models in computer vision, representing an incremental improvement over existing diffusion and Transformer methods.
The paper tackles the problem of improving image generation with diffusion models by integrating Vision Transformers, proposing DiffiT with a Time-dependent Multihead Self Attention mechanism for fine-grained denoising control. It achieves state-of-the-art performance, including an FID score of 1.73 on ImageNet256 with 19.85% and 16.88% fewer parameters than other Transformer-based models.
Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transformer (ViT) has also demonstrated strong modeling capabilities and scalability, especially for recognition tasks. In this paper, we study the effectiveness of ViTs in diffusion-based generative learning and propose a new model denoted as Diffusion Vision Transformers (DiffiT). Specifically, we propose a methodology for finegrained control of the denoising process and introduce the Time-dependant Multihead Self Attention (TMSA) mechanism. DiffiT is surprisingly effective in generating high-fidelity images with significantly better parameter efficiency. We also propose latent and image space DiffiT models and show SOTA performance on a variety of class-conditional and unconditional synthesis tasks at different resolutions. The Latent DiffiT model achieves a new SOTA FID score of 1.73 on ImageNet256 dataset while having 19.85%, 16.88% less parameters than other Transformer-based diffusion models such as MDT and DiT,respectively. Code: https://github.com/NVlabs/DiffiT