Add demo screenshot

README.md

@@ -9,6 +9,8 @@ language:
 
 This is an attempt to replicate OpenAI's [DALL·E](https://openai.com/blog/dall-e/), a model capable of generating arbitrary images from a text prompt that describes the desired result. 
 
+![DALL·E mini demo screenshot](img/demo_screenshot.png)
+
 This model's architecture is a simplification of the original, and leverages previous open source efforts and available pre-trained models. Results have lower quality than OpenAI's, but the model can be trained and used on less demanding hardware. Our training was performed on a single TPU v3-8 for a few days.
 
 ### Components of the Architecture