Upload folder using huggingface_hub

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 assets/Compare_Recon.png filter=lfs diff=lfs merge=lfs -text
+assets/Recon_Plot.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -11,19 +11,28 @@ InsightTok is a discrete visual tokenizer designed to improve the fidelity of **
 It was introduced in the paper *InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation*.
 
 - **Paper:**: [InsightTok: Improving Text and Face Fidelity in Discrete Tokenization for Autoregressive Image Generation](https://huggingface.co/papers)
-- **Code:** [https://github.com/LeapLabTHU/JustGRPO](https://github.com/LeapLabTHU/JustGRPO)
+- **Code:** [https://github.com/LeapLabTHU/InsightTok](https://github.com/LeapLabTHU/InsightTok)
 
-## Hyperparameters
+## Model Details
 
-- Downsampling Rate: 16x
-- Codebook Size: 16384
-- Latent Dimension: 256
-- Number of parameters: 426M
+| Property | Value |
+|---|---:|
+| Downsampling rate | 16× |
+| Codebook size | 16,384 |
+| Latent dimension | 256 |
+| Number of parameters | 426M |
 
 ## Performance
 
+InsightTok achieves strong text and face reconstruction quality while maintaining a compact discrete representation.
+
+
+<p align="center">
+  <img src="assets/Recon_Plot.png" width="100%">
+</p>
+
 <p align="center">
-  <img src="assets/Compare_Recon.png" width="95%">
+  <img src="assets/Compare_Recon.png" width="100%">
 </p>
 
 ## Usage