Update README.md

README.md

@@ -24,8 +24,9 @@ base_model:
 
 
 ## Introduction
+We're excited to introduce the FastWan2.1 series—a new line of models finetuned with our novel **Sparse-distill** strategy. This approach jointly integrates DMD and VSA in a single training process, combining the benefits of distillation to shorten diffusion steps and sparse attention to reduce attention computations, enabling even faster video generation.
 
-This model is jointly finetuned with [DMD](https://arxiv.org/pdf/2405.14867) and [VSA](https://arxiv.org/pdf/2505.13389), based on [Wan-AI/Wan2.1-T2V-1.3B-Diffusers](https://huggingface.co/Wan-AI/Wan2.1-T2V-1.3B-Diffusers). It supports efficient 3-step inference and generates high-quality videos at **61×448×832** resolution. We adopt the [FastVideo 480P Synthetic Wan dataset](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x448x832_600k), consisting of 600k synthetic latents.
+FastWan2.1-T2V-1.3B-Diffusers is built upon Wan-AI/Wan2.1-T2V-1.3B-Diffusers. It supports efficient 3-step inference and produces high-quality videos at 61×448×832 resolution. For training, we use the FastVideo 480P Synthetic Wan dataset, which contains 600k synthetic latents.
 
 ---