Update README.md

README.md

@@ -12,13 +12,10 @@ pipeline_tag: image-to-image
 <p align="center">
   <strong>Decomposing Images into Editable RGBA Layers</strong>
 </p>
- 
-<!-- Add a teaser image to the repo and it will render here. -->
-<!--
+
 <p align="center">
-  <img src="stable_layers_teaser.jpg" alt="Stable Layers Teaser" width="100%" />
+  <img src="https://stability-ai.github.io/stable-layers.github.io/assets/images/teaser.png" alt="Stable Layers Teaser" width="100%" />
 </p>
--->
 
 <p align="center">
   <span><a href="https://arxiv.org/abs/2605.30257">Paper</a></span>&nbsp;&nbsp;&nbsp;
@@ -32,9 +29,8 @@ pipeline_tag: image-to-image
 **Stable Layers** decomposes a single RGB image into a small stack of back-to-front
 RGBA layers (background plus object layers) suitable for compositing and editing.
 
-This repository hosts the LoRA adapter over `Qwen/Qwen-Image-Layered`. Note: whilst
-the paper used Gemini, this model was retrained using an open VLM, and we found no
-performance loss.
+This repository hosts the LoRA adapter over `Qwen/Qwen-Image-Layered`. This model
+was trained using Qwen 3.5 9b as the VLM teacher.
 
 ## Model Artifacts