A little more info (#2)

- A little more info (0cdbad307991dea0ac972571d5997d930111e100)


Co-authored-by: Sayak Paul <[email protected]>

README.md

@@ -32,6 +32,14 @@ prompt: a tornado hitting grass field, 1980's film grain. overcast, muted colors
 
 ## Usage
 
+Make sure to first install the libraries:
+
+```bash
+pip install accelerate transformers opencv-python diffusers
+```
+
+And then we're ready to go:
+
 ```python
 from diffusers import ControlNetModel, StableDiffusionXLControlNetPipeline, AutoencoderKL
 from diffusers.utils import load_image
@@ -74,8 +82,12 @@ images[0].save(f"hug_lab.png")
 
 ![images_10)](./out_hug_lab_7.png)
 
+To more details, check out the official documentation of [`StableDiffusionXLControlNetPipeline`](https://huggingface.co/docs/diffusers/main/en/api/pipelines/controlnet_sdxl).
+
 ### Training
 
+Our training script was built on top of the official training script that we provide [here](https://github.com/huggingface/diffusers/blob/main/examples/controlnet/README_sdxl.md). 
+
 #### Training data
 This checkpoint was first trained for 20,000 steps on laion 6a resized to a max minimum dimension of 384. 
 It was then further trained for 20,000 steps on laion 6a resized to a max minimum dimension of 1024 and