Question about `sd_locked` in ControlNet 1.0 and 1.1

Nobody has claimed this yet.

In the paper, it is said that the parameters of Stable Diffusion(SD) are locked when training ControlNet. However, when I looked into the released ControlNet 1.0 checkpoints, I found that the weights of SD UNet decoder are different from SD1.5 (`v1-5-pruned.ckpt`). I notice that there's an option [`sd_locked`](https://github.com/lllyasviel/ControlNet/blob/main/docs/train.md#sd_locked) that enables training SD UNet decoder. So does this mean that ControlNet 1.0 are trained with `sd_locked=False`?

Furthermore, different from ControlNet 1.0 checkpoints, the ControlNet 1.1 checkpoints don't contain SD weights and need to be used along with `v1-5-pruned.ckpt`, does this mean that ControlNet 1.1 are trained with `sd_locked=True`?

Here is the script I used to compare two checkpoints:

```python
import torch

ckpt = torch.load('./ckpts/v1-5-pruned.ckpt', map_location='cpu')['state_dict']
ckpt2 = torch.load('./ckpts/control_sd15_canny.pth', map_location='cpu')

notclose = []
maxdiff = 0.
for k, v in ckpt.items():
if k.startswith('model') and k in ckpt2:
if not torch.allclose(ckpt2[k], ckpt[k]):
notclose.append(k)
maxdiff = max(maxdiff, torch.max(torch.abs(ckpt2[k] - ckpt[k])).item())

print('notclose:')
print('\n'.join(notclose))
print(f'maxdiff: {maxdiff}')
```

Start with docs/train.md, especially the sd_locked option, then review the checkpoint comparison script and the referenced ControlNet 1.0 and 1.1 checkpoints. Done means documenting whether each checkpoint series used sd_locked and explaining the presence or absence of Stable Diffusion weights.

Written by the indexing model from the issue text.