Update model card

README.md

@@ -1,4 +1,5 @@
 ---
+license: mit
 library_name: pytorch
 tags:
 - diffusion
@@ -12,8 +13,8 @@ tags:
 Pretrained weights and training data of the toy example (Figure 2) in
 [Compositional Visual Planning via Inference-Time Diffusion Scaling](https://arxiv.org/abs/2603.02646)
 ([project page](https://comp-visual-planning.github.io/)). A short-horizon diffusion model is trained on
-circular arc clips; at test time three 120° arc generators are composed into a three-petal "flower" by
-enforcing boundary agreement between the chunks at every denoising step.
+circular arc clips. At test time, three 120° arc generators are composed into a three-petal "flower" by
+enforcing agreement at the chunk boundaries at every denoising step.
 
 ## Files
 
@@ -24,7 +25,7 @@ enforcing boundary agreement between the chunks at every denoising step.
 
 ## Usage
 
-The toy example code downloads both files automatically when they are missing locally. To fetch them by hand:
+The toy example code downloads both files when they are missing locally. To download them by hand:
 
 ```bash
 pip install -U huggingface_hub