Update README.md

README.md

@@ -21,7 +21,7 @@ license: apache-2.0
 - This model is finetuned with [VSA](https://arxiv.org/pdf/2505.13389), based on [Wan-AI/Wan2.1-T2V-14B-Diffusers](https://huggingface.co/Wan-AI/Wan2.1-T2V-14B-Diffusers).  
 - It achieves up to 2.1x speed up on a single **H100** GPU.
 - Our model is trained on **77×768×1280** resolution, but it supports generating videos with any resolution.(quality may degrade).
-- We set **VSA attention sparsity** to 0.9, and training runs for **1500 steps (~14 hours)**. You can tune this value from 0 to 0.9 to balance speed and performance.
+- We set **VSA attention sparsity** to 0.9, and training runs for **1500 steps (~14 hours)**. You can tune this value from 0 to 0.9 to balance speed and performance for inference.
 - Both [finetuning](https://github.com/hao-ai-lab/FastVideo/blob/main/scripts/finetune/finetune_v1_VSA.sh) and [inference](https://github.com/hao-ai-lab/FastVideo/blob/main/scripts/inference/v1_inference_wan_VSA.sh) scripts are available in the [FastVideo](https://github.com/hao-ai-lab/FastVideo) repository.  
 - Try it out on **FastVideo** — we support a wide range of GPUs from **H100** to **4090**
 - We use [FastVideo 720P Synthetic Wan dataset](https://huggingface.co/datasets/FastVideo/Wan-Syn_77x768x1280_250k) for training.