Rename READEME.md to README.md

READEME.md → README.md

@@ -5,7 +5,7 @@
 <p>
 
 <p align="center">
-    🖥️ <a href="https://github.com/HiDream-ai/MotionPro">GitHub</a> &nbsp&nbsp ｜ &nbsp&nbsp  🌐 <a href="https://zhw-zhang.github.io/MotionPro-page/"><b>Project Page</b></a> &nbsp&nbsp  | &nbsp&nbsp🤗 <a href="https://huggingface.co/zzwustc/MotionPro/tree/main">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="">Paper </a> &nbsp&nbsp | &nbsp&nbsp 📖 <a href="">PDF</a> &nbsp&nbsp 
+    🖥️ <a href="https://github.com/HiDream-ai/MotionPro">GitHub</a> &nbsp&nbsp ｜ &nbsp&nbsp  🌐 <a href="https://zhw-zhang.github.io/MotionPro-page/"><b>Project Page</b></a> &nbsp&nbsp  | &nbsp&nbsp🤗 <a href="https://huggingface.co/HiDream-ai/MotionPro/tree/main">Hugging Face</a>&nbsp&nbsp | &nbsp&nbsp 📑 <a href="">Paper </a> &nbsp&nbsp | &nbsp&nbsp 📖 <a href="">PDF</a> &nbsp&nbsp 
 <br>
 
 [**MotionPro: A Precise Motion Controller for Image-to-Video Generation**](https://zhw-zhang.github.io/MotionPro-page/) <be>
@@ -27,18 +27,14 @@ Additionally, our repository provides more tools to benefit the research communi
 
 ## Video Demos
 
+
+https://github.com/user-attachments/assets/2af6d638-e09c-4e98-a565-43c8ca30f91b
+
+
 <div align="center">
-  <video src="assets/func_1.mp4" width="70%" autoplay loop muted playsinline poster="">
-  </video>
   <p><em>Examples of different motion control types by our MotionPro.</em></p>
 </div>
 
-<!-- <div align="center">
-  <video src="assets/func_1.mp4" width="70%" autoplay loop muted playsinline poster="">
-  </video>
-  <p><em>Figure 2: Synchronized video generation and Video recapture.</em></p>
-</div> -->
-
 ## 🔥 Updates
 - [x] **\[2025.03.26\]** Release inference and training code.
 - [ ] **\[2025.03.27\]** Upload gradio demo usage video.
@@ -68,11 +64,11 @@ pip install -r requirements.txt
 
 | Models            | Download Link                                                                 | Notes                                      |
 |-------------------|-------------------------------------------------------------------------------|--------------------------------------------|
-| MotionPro  | 🤗[Huggingface](https://huggingface.co/zzwustc/MotionPro/blob/main/MotionPro-gs_16k.pt)                | Supports both object and camera control. This is the default model mentioned in the paper.   |
-| MotionPro-Dense   | 🤗[Huggingface](https://huggingface.co/zzwustc/MotionPro/blob/main/MotionPro_Dense-gs_14k.pt)           | Supports synchronized video generation when combined with MotionPro. MotionPro-Dense shares the same architecture as Motion, but the input conditions are modified to include: dense optical flow and per-frame visibility masks relative to the first frame. |
+| MotionPro  | 🤗[Huggingface](https://huggingface.co/HiDream-ai/MotionPro/blob/main/MotionPro-gs_16k.pt)                | Supports both object and camera control. This is the default model mentioned in the paper.   |
+| MotionPro-Dense   | 🤗[Huggingface](https://huggingface.co/HiDream-ai/MotionPro/blob/main/MotionPro_Dense-gs_14k.pt)           | Supports synchronized video generation when combined with MotionPro. MotionPro-Dense shares the same architecture as Motion, but the input conditions are modified to include: dense optical flow and per-frame visibility masks relative to the first frame. |
 
 
-Download the model from HuggingFace at high speeds (30-80MB/s):
+Download the model from HuggingFace at high speeds (30-75MB/s):
 ```
 cd tools/huggingface_down
 bash download_hfd.sh
@@ -104,7 +100,7 @@ python demo_sparse_flex_wh_pure_camera.py
 By combining MotionPro and MotionPro-Dense, we can achieve the following functionalities:
 - Synchronized video generation. We assume that two videos, `pure_obj_motion.mp4` and `pure_camera_motion.mp4`, have been generated using the respective demos. By combining their motion flows and using the result as a condition for MotionPro-Dense, we obtain `final_video`. By pairing the same object motion with different camera motions, we can generate `synchronized videos` where the object motion remains consistent while the camera motion varies. [More Details](assets/README_syn.md)
 
-Here, you need to first download the [model_weights](https://huggingface.co/zzwustc/MotionPro/tree/main/tools/co-tracker/checkpoints) of cotracker and place them in the `tools/co-tracker/checkpoints` directory.
+Here, you need to first download the [model_weights](https://huggingface.co/HiDream-ai/MotionPro/blob/main/tools/co-tracker/checkpoints/scaled_offline.pth) of cotracker and place them in the `tools/co-tracker/checkpoints` directory.
 
 ```
 python inference_dense.py --ori_video 'assets/cases/dog_pure_obj_motion.mp4' --camera_video 'assets/cases/dog_pure_camera_motion_1.mp4' --save_name 'syn_video.mp4' --ckpt_path 'MotionPro-Dense CKPT-PATH'
@@ -117,7 +113,7 @@ python inference_dense.py --ori_video 'assets/cases/dog_pure_obj_motion.mp4' --c
 <details open>
 <summary><strong>Data Prepare</strong></summary>
 
-We have packaged several demo videos to help users debug the training code. Simply 🤗[download](https://huggingface.co/zzwustc/MotionPro/tree/main/data), extract the files, and place them in the `./data` directory.
+We have packaged several demo videos to help users debug the training code. Simply 🤗[download](https://huggingface.co/HiDream-ai/MotionPro/tree/main/data), extract the files, and place them in the `./data` directory.
 
 Additionally, `./data/dot_single_video` contains code for processing raw videos using [DOT](https://github.com/16lemoing/dot) to generate the necessary conditions for training, making it easier for the community to create training datasets.