Update README.md add demo

Author: Animadversio

README.md

@@ -11,9 +11,17 @@ This tiny self-contained code base allows you to
 * Rebuild the Stable Diffusion Model in a single Python script. 
 * Train your toy version of stable diffusion on classic datasets like MNIST, CelebA
 ![](https://scholar.harvard.edu/sites/scholar.harvard.edu/files/styles/os_files_xxlarge/public/binxuw/files/stablediffusion_overview.jpg?m=1667438590&itok=n2gM0Xba)
+
 ## Colab notebooks
 * Playing with Stable Diffusion and inspecting the internal architecture of the models. [Open in Colab](https://colab.research.google.com/drive/1TvOlX2_l4pCBOKjDI672JcMm4q68sKrA?usp=sharing)
 * Build your own Stable Diffusion UNet model from scratch in a notebook. (with < 300 lines of codes!) [Open in Colab](https://colab.research.google.com/drive/1mm67_irYu3qU3hnfzqK5yQC38Fd5UFam?usp=sharing)
     * [Self contained script](https://github.com/Animadversio/DiffusionFromScratch/blob/master/StableDiff_UNet_model.py)
     * [Unit tests](https://github.com/Animadversio/DiffusionFromScratch/blob/master/StableDiff_UNet_unittest.py)
 * Build a Diffusion model (with UNet + cross attention) and train it to generate MNIST images based on the "text prompt". [Open in Colab (exercise)](https://colab.research.google.com/drive/1Y5wr91g5jmpCDiX-RLfWL1eSBWoSuLqO?usp=sharing) [Open in Colab (answer)](https://colab.research.google.com/drive/1_MEFfBdOI06GAuANrs1b8L-BBLn3x-ZJ?usp=sharing)
+
+
+## Demo Outputs
+[![IMAGE ALT TEXT HERE](https://img.youtube.com/vi/SmY7vMNen2w/0.jpg)](https://www.youtube.com/watch?v=SmY7vMNen2w)
+
+[Music video](https://github.com/nateraw/stable-diffusion-videos) generated from Stable Diffusion. 
+