Contributing my code with comments for stable diffusion Issue #8

[neelsoumya]

Contributing my code with comments for stable diffusion Issue #8

1. Adding comments.
2. Adding more code for loading in Google Colab (using a T4 GPU) on my Cambridge account (work in progress).
3. Please note that this PR does not solve the issue.

from google.colab import drive
import os

mount='/content/gdrive'

# mount Google Drive
drive.mount(mount)

# Switch to the directory on the Google Drive that you want to use
drive_root = mount + "/My Drive/diffusion-models"
%cd $drive_root

I can run until here (where I get an error):

# run both experts
image_base = base(
    prompt=prompt,
    num_inference_steps=n_steps,
    denoising_end=high_noise_frac,
    output_type="latent",
).images

image_final = refiner(
    prompt=prompt,
    num_inference_steps=n_steps,
    denoising_start=high_noise_frac,
    image=image_base,
).images[0]
```py


Error message is

```py
---------------------------------------------------------------------------
OutOfMemoryError                          Traceback (most recent call last)
<ipython-input-8-410c6a79b4f8> in <cell line: 0>()
      7 ).images
      8 
----> 9 image_final = refiner(
     10     prompt=prompt,
     11     num_inference_steps=n_steps,

17 frames
/usr/local/lib/python3.11/dist-packages/torch/nn/modules/conv.py in _conv_forward(self, input, weight, bias)
    547                 self.groups,
    548             )
--> 549         return F.conv2d(
    550             input, weight, bias, self.stride, self.padding, self.dilation, self.groups
    551         )

OutOfMemoryError: CUDA out of memory. Tried to allocate 512.00 MiB. GPU 0 h
```py