Diffusion Transformers (DiT) are a class of diffusion models that leverage the transformer architecture to improve performance and scalability. DiT aims to replace the commonly used U-Net backbone with a transformer, resulting in improved performance and scalability. These models have demonstrated impressive scalability properties, with higher Gflops consistently having lower Frechet Inception Distance (FID). DiT has been applied in various fields, including text-to-video models like OpenAI's SORA, text-to-image generation models like Stable Diffusion 3, and Transformer-based Text-to-Image (T2I) diffusion models like PixArt-α. DiT models have shown significant improvements over state-of-the-art models in terms of image quality, artistry, and semantic control. With its impressive scalability and versatility, DiT is an exciting development in the field of generative modeling.