Update README.md

README.md

@@ -7,4 +7,20 @@ tags: []
 
 Official Repository of the paper: *[Scaling Down Text Encoders of Text-to-Image Diffusion Models](https://github.com/LifuWang-66/ScalingDownTextEncoder/tree/main)*.
 
-Project Page: https://lifuwang-66.github.io/ScalingDownTE/
+Project Page: https://lifuwang-66.github.io/ScalingDownTE/
+
+## Model Descriptions:
+T5-Base distilled from [T5-XXL](https://huggingface.co/google/flan-t5-xxl) using [Flux](https://huggingface.co/runwayml/stable-diffusion-v1-5). 
+It is 50 times smaller and retains most capability of T5-XXL.
+
+## Generation Results:
+
+<p align="center">
+    <img src="teaser.png">
+</p>
+
+By distilling classifier-free guidance into the model's input, LCM can generate high-quality images in very short inference time. We compare the inference time at the setting of 768 x 768 resolution, CFG scale w=8, batchsize=4, using a A800 GPU. 
+
+<p align="center">
+    <img src="speed_fid.png">
+</p>