Compression using sparse tensors and thresholding

Not sure what the original script did since it had a default alpha value of 0.

```py
parser.add_argument("--str", type=float, help="Strength of the rehydration (-0.05..0.05)", default=0, required=False)`
alpha = args.str
...
for key in tqdm(theta_0.keys(), desc="Stage 1/2?: merge common keys"):
if "model" in key and key in theta_1:
theta_0[key] = theta_0[key] * (1 + alpha) + theta_1[key] * (1 - alpha)
```

Which appears just replaced the final weights with weights that were the same, since `theta_0[key] = theta_0[key] * 1 + theta_1[key] * 0` = `theta_0[key] = theta_0[key]`.

Constructing a patch with M1 - M2 = patch and then M1 + patch = M2 does not work due to lossy FP and seems to give me corrupted models.

What I did instead was use thresholding based on the min/max delta of the individual tensors and then apply the most changed values as a patch.

Here's my code: https://gist.github.com/AmericanPresidentJimmyCarter/1947162f371e601ce183070443f41dc2

This results in an about 60 MB patch, but the quality of transfer is not great. You can increase the THRESHOLD_STRENGTH variable but the file sizes increase dramatically while the quality does not seem to. Here are results at `THRESHOLD_STRENGTH == 2.`.


Test code is:

```py
_, extra_data = engine.sample(
'elon musk in modern disney style',
4,
'heun',
679566949,
25,
scale=7.,
)
```

Using dreambooth'd weights here: https://huggingface.co/nitrosocke/mo-di-diffusion

Start by reviewing the original script excerpt and the linked gist, then reproduce the issue with the provided engine.sample call and the nitrosocke/mo-di-diffusion weights. Compare the thresholding approach's patch size and transfer quality across threshold strengths; done means a documented compression method that avoids corrupted models and has acceptable quality.

Written by the indexing model from the issue text.