Improve model card: Add license, project/code links, and usage

README.md

@@ -1,9 +1,11 @@
 ---
 pipeline_tag: unconditional-image-generation
+license: apache-2.0
 ---
+
 ## Boosting Generative Image Modeling via Joint Image-Feature Synthesis
-Arxiv: https://arxiv.org/abs/2504.16064 <br>
 
+[\ud83d\udcda Paper](https://arxiv.org/abs/2504.16064) | [\ud83c\udf10 Project Page](https://representationdiffusion.github.io/) &ensp; [\ud83d\udcbb Code](https://github.com/zelaki/ReDi)
 
 **ReDi** learns to generate coherent image-feature pairs from pure noise, significantly enhancing both generative quality and training efficiency.
 
@@ -11,9 +13,6 @@ Arxiv: https://arxiv.org/abs/2504.16064 <br>
 #### Model Description 
 This model uses [SiT](https://github.com/willisma/SiT) as the base model. We train for 4M steps with a batch size of 256 on ImageNet 256x256.
 
-
-
-
 #### Metrics
 Generative performance on Imagenet Validation Set.
 
@@ -21,5 +20,12 @@ Generative performance on Imagenet Validation Set.
 |---------------------|---------|----------|--------|----------|---------|
 | **SiT-XL/2 w/ ReDi** | 1.64   |   4.63       |   289.3     |    0.65      |    0.77     |
 
+---
+
+## Sample Usage
+
+You can sample from our pre-trained ReDi models with `sample.py`.
 
----
+```bash
+python sample.py SDE --image-size 256 --seed 42 --ckpt /path/to/ckpt
+```