Diffusion Transformers (DiTs) demonstrate remarkable generative abilities in AI. However, the iterative denoising process inherent in diffusion incurs substantial computational cost and memory overhead, impeding fast and energy-efficient edge inference. To mitigate the overhead of denoising, we propose a post-training framework that jointly utilizes pruning and quantization for hardware-efficient DiT inference, which is based on the observation that not all denoising blocks within a model are equally important during image generation. We introduce metrics to assess the importance of DiTs’ blocks and layers. To achieve importance-aware dynamic compression, we unify mixed-sparsity pruning and mixed-precision quantization based on importance metrics. Experiments show that our approach achieves a 1.41 \(\times \) inference speedup through pruning with a mixed precision of W3.2A4.9 while incurring minimal accuracy loss. Furthermore, the evaluation of bit-flexible DNN accelerators demonstrates up to 2.78 \(\times \) performance improvement, and 1.99 \(\times \) better energy efficiency can be achieved compared to W8A8 quantization without pruning.