Add qualitative demo grids to model card

.gitattributes

@@ -33,3 +33,7 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+assets/demo_droid.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/demo_droid.webp filter=lfs diff=lfs merge=lfs -text
+assets/demo_re10k.mp4 filter=lfs diff=lfs merge=lfs -text
+assets/demo_re10k.webp filter=lfs diff=lfs merge=lfs -text

README.md

@@ -35,6 +35,19 @@ The same architecture supports two control modalities:
 This Hugging Face repository hosts the MiniWorld model checkpoints. Code,
 training scripts, and evaluation utilities live in the GitHub repository.
 
+## Qualitative Results
+
+Each tile is a 253-frame streaming rollout from the `1B` checkpoint, generated
+from a single observed frame plus the control signal.
+
+<p align="center">
+  <a href="resolve/main/assets/demo_droid.mp4"><img src="assets/demo_droid.webp" width="49%" alt="DROID action-conditioned rollouts"></a>
+  <a href="resolve/main/assets/demo_re10k.mp4"><img src="assets/demo_re10k.webp" width="49%" alt="RealEstate10K camera-conditioned rollouts"></a>
+</p>
+<p align="center">
+  <sub><b>DROID</b> action-conditioned rollouts (left) and <b>RealEstate10K</b> camera-conditioned rollouts (right), shown at 2× speed. Click either grid for the full-resolution video, or see the <a href="https://zhao-yian.github.io/MiniWorld/">project page</a> for all 100 rollouts.</sub>
+</p>
+
 ## Model Summary
 
 MiniWorld uses a block-causal Video Diffusion Transformer trained with Rectified

assets/demo_droid.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81f62bb8e21d18c95e0c0b80fbbe17598c62b6466c281026221bce1a299027d0
+size 3450670

assets/demo_re10k.mp4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:346a9035dd5712a48ea962b0adef5279155920904d3584f94b863e80f37831e7
+size 5755484