Update README.md

README.md

@@ -140,12 +140,12 @@ ability of the model to generate content with non-English prompts is significant
 
 ## Training
 
-**Training Data**
+### Training Data
 The model developers used the following dataset for training the model:
 
 - LAION-2B (en) and subsets thereof (see next section)
 
-**Training Procedure**
+### Training Procedure
 Stable Diffusion v1-4 is a latent diffusion model which combines an autoencoder with a diffusion model that is trained in the latent space of the autoencoder. During training, 
 
 - Images are encoded through an encoder, which turns images into latent representations. The autoencoder uses a relative downsampling factor of 8 and maps images of shape H x W x 3 to latents of shape H/f x W/f x 4
@@ -162,6 +162,8 @@ filtered to images with an original size `>= 512x512`, estimated aesthetics scor
 - [`stable-diffusion-v1-3`](https://huggingface.co/CompVis/stable-diffusion-v1-3): Resumed from `stable-diffusion-v1-2`. 195,000 steps at resolution `512x512` on "laion-improved-aesthetics" and 10 % dropping of the text-conditioning to improve [classifier-free guidance sampling](https://arxiv.org/abs/2207.12598)
 - [**`stable-diffusion-v1-4`**](https://huggingface.co/CompVis/stable-diffusion-v1-4) *To-fill-here*
 
+### Training details
+
 - **Hardware:** 32 x 8 x A100 GPUs
 - **Optimizer:** AdamW
 - **Gradient Accumulations**: 2