Sync local Space with Hub

README.md

@@ -4,7 +4,7 @@ license: apache-2.0
 
 # Pusa V1.0 Model
 
-[Code Repository](https://github.com/Yaofang-Liu/Pusa-VidGen) | [Project Page](https://yaofang-liu.github.io/Pusa_Web/) |[Dataset](https://huggingface.co/datasets/RaphaelLiu/PusaV1_training) |[Model](https://huggingface.co/RaphaelLiu/PusaV1) |  [Paper (Pusa V1.0)](https://github.com/Yaofang-Liu/Pusa-VidGen/blob/e99c3dcf866789a2db7fbe2686888ec398076a82/PusaV1/PusaV1.0_Report.pdf) | [Paper (FVDM)](https://arxiv.org/abs/2410.03160) | [Follow on X](https://x.com/stephenajason) | [Xiaohongshu](https://www.xiaohongshu.com/explore/67f898dc000000001c008339?source=webshare&xhsshare=pc_web&xsec_token=ABAhG8mltqyMxL9kI0eRxwj7EwiW7MFYH2oPl4n8ww0OM=&xsec_source=pc_share)
+[Code Repository](https://github.com/Yaofang-Liu/Pusa-VidGen) | [Project Page](https://yaofang-liu.github.io/Pusa_Web/) |[Dataset](https://huggingface.co/datasets/RaphaelLiu/PusaV1_training) |[Model](https://huggingface.co/RaphaelLiu/PusaV1) |  [Paper (Pusa V1.0)](https://github.com/Yaofang-Liu/Pusa-VidGen/blob/e99c3dcf866789a2db7fbe2686888ec398076a82/PusaV1/PusaV1.0_Report.pdf) | [Paper (FVDM)](https://arxiv.org/abs/2410.03160) | [Follow on X](https://x.com/stephenajason) | [Xiaohongshu](https://www.xiaohongshu.com/user/profile/5c6f928f0000000010015ca1?xsec_token=YBEf_x-s5bOBQIMJuNQvJ6H23Anwey1nnDgC9wiLyDHPU=&xsec_source=app_share&xhsshare=CopyLink&appuid=5c6f928f0000000010015ca1&apptime=1752622393&share_id=60f9a8041f974cb7ac5e3f0f161bf748)
 
 ## Overview
 
@@ -22,12 +22,6 @@ Pusa not only sets a new standard for image-to-video (I2V) generation but also *
 
 Pusa V1.0, with only 10 inference steps, achieves state-of-the-art performance among open-source models. It surpasses its direct baseline, `Wan-I2V`, which was trained with vastly greater resources. Our model obtains a VBench-I2V total score of **87.32%**, outperforming `Wan-I2V`'s 86.86%.
 
-
-## ✨ Key Features
-
-- **Comprehensive Multi-task Support**:
-// ... existing code ...
-
 ## ✨ Key Features
 
 - **Comprehensive Multi-task Support**:
@@ -66,13 +60,17 @@ Pusa V1.0, with only 10 inference steps, achieves state-of-the-art performance a
 ### Download Weights and Recover The Checkpoint
 
 **Option 1**: Use the Hugging Face CLI:
-```bash
-pip install huggingface_hub
-huggingface-cli download RaphaelLiu/PusaV1 --local-dir <path_to_downloaded_directory>
-cat ./PusaV1/pusa_v1.pt.part* > ./PusaV1/pusa_v1.pt
+```shell
+# Make sure you are in the PusaV1 directory
+# Install huggingface-cli if you don't have it
+pip install -U "huggingface_hub[cli]"
+huggingface-cli download RaphaelLiu/PusaV1 --local-dir ./model_zoo/PusaV1
+
+# (Optional) Please download Wan2.1-T2V-14B to ./model_zoo/PusaV1 is you don't have it, if you have you can directly soft link it to ./model_zoo/PusaV1
+huggingface-cli download Wan-AI/Wan2.1-T2V-14B --local-dir ./model_zoo/PusaV1
 ```
 
-**Option 2**: Download directly from [Hugging Face](https://huggingface.co/RaphaelLiu/PusaV1) to your local machine.
+**Option 2**: Download directly `pusa_v1.pt` or `pusa_v1.safetensors` from [Hugging Face](https://huggingface.co/RaphaelLiu/PusaV1) to your local machine.
 
 ## Related Work