Update README.md

README.md

@@ -1,3 +1,17 @@
+---
+license: openrail
+datasets:
+- ProGamerGov/StableDiffusion-v1-5-Regularization-Images
+- MadVoyager/stable_diffusion_instructional_dataset
+language:
+- yap
+metrics:
+- accuracy
+- charcut_mt
+- character
+library_name: diffusers
+pipeline_tag: text-to-image
+---
 --license: openrail
 datasets:
 - ProGamerGov/StableDiffusion-v1-5-Regularization-Images
@@ -232,4 +246,4 @@ The model was not trained to be factual or true representations of people or eve
 - The autoencoding part of the model is lossy.
 
 ### Bias
-While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.
+While the capabilities of image generation models are impressive, they can also reinforce or exacerbate social biases.