Update README.md

README.md

@@ -7,18 +7,10 @@ sdk: static
 pinned: false
 ---
 # SkeletonDiffusion: Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction
-This is the official Huggingface space of the CVPR2025 paper  _Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction_, codebase available [here](https://github.com/Ceveloper/SkeletonDiffusion/tree/main).
+This is the official Huggingface space of the CVPR2025 paper  _Nonisotropic Gaussian Diffusion for Realistic 3D Human Motion Prediction_.
 
-SkeletonDiffusion is a probabilistic human motion prediction model that takes as input 0.5s of human motion and generates future motions of 2s with a inference time of 0.4s.
-SkeletonDiffusion generates motions that are at the same time realistic and diverse. It is a latent diffusion model that  with a custom graph attention architecture trained with a nonisotropic Gaussian diffusion formulation reflecting body joint connections. 
+Code is available [here](https://github.com/Ceveloper/SkeletonDiffusion/tree/main).
+Interactive Demo from video and pretrained models are available here.
 
-We provide a model for each dataset mentioned in the paper (AMASS, FreeMan, Human3.6M), and a further model trained on AMASS with hands joints (AMASS-MANO).
-
-<img src="./media/trailer.gif" alt="trailer" width="512">
-
-
-## Online demo
-The model trained on AMASS is accessible in a demo workflow that predicts future motions from videos.
-The demo extracts 3D human poses from video via Neural Localizer Fields ([NLF](https://istvansarandi.com/nlf/)) by Sarandi et al., and SkeletonDiffusion generates future motions conditioned on the extracted poses:
-SkeletonDiffusion has not been trained with real-world, noisy data, but despite this fact it can handle most cases reasonably.
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/6501e39f192a9bf2226a864d/S8dKLYvNawBbcqzVngEd_.png)