Add disclaimer for unsafe instances

@sayakpaul

Could you check if this would be enough please? If not, let me know!

README.md

@@ -17,7 +17,8 @@ base_model: stabilityai/stable-diffusion-xl-base-1.0
 <img src="assets/mapo_overview.png" width=750/>
 </div><br>
 
-We propose **MaPO**, a reference-free, sample-efficient, memory-friendly alignment technique for text-to-image diffusion models. For more details on the technique, please refer to our paper [here] (TODO). 
+We propose **MaPO**, a reference-free, sample-efficient, memory-friendly alignment technique for text-to-image diffusion models. For more details on the technique, please refer to our paper [here] (TODO).
+
 
 ## Developed by
 
@@ -30,7 +31,7 @@ We propose **MaPO**, a reference-free, sample-efficient, memory-friendly alignme
 
 ## Dataset
 
-This model was fine-tuned from [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) on the [Pick-Safety](mapo-t2i/pick-safety). 
+This model was fine-tuned from [Stable Diffusion XL](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) on the [Pick-Safety](mapo-t2i/pick-safety). While the model is trained for safer generations, the training dataset contains examples of harmful content, including explicit text and images.
 
 ## Training Code