Add v-1-2 training summary

README.md

@@ -18,7 +18,14 @@ extra_gated_fields:
 ---
 
 # Stable Diffusion v1 Model Card
-This model card focuses on the model associated with the Stable Diffusion model v1-2, available [here](https://github.com/CompVis/stable-diffusion).
+
+Stable Diffusion is a latent text-to-image diffusion model capable of generating photo-realistic images given any text input.
+
+The **Stable-Diffusion-v-1-2** checkpoint was initialized with the weights of the [Stable-Diffusion-v-1-1](https:/steps/huggingface.co/CompVis/stable-diffusion-v-1-1-original) 
+checkpoint and subsequently fine-tuned on 515,000 steps at resolution `512x512` on "laion-improved-aesthetics" (a subset of laion2B-en,
+filtered to images with an original size `>= 512x512`, estimated aesthetics score `> 5.0`, and an estimated watermark probability `< 0.5`.
+
+For more information, please refer to [Training](#training).
 
 ## Model Details
 - **Developed by:** Robin Rombach, Patrick Esser