It takes 1-2 mins for a 512x512 image. It's been a lot of fun since I did this last night.
For reference, inferencing the model on a 2070 takes 10-12 seconds for the same size at max-precision, and the 3070 can synthesize an image in almost 6 seconds.
If you extrapolate the power consumption (3070 @~300w vs M1 Pro GPU@~30-50w) the metrics make a lot of sense.
The answer depends VERY MUCH on RAM.
My M1 with 8GB takes 70-90 minutes per image.
My M1 Pro with 16GB takes 3 minutes per image.
Another data point:
M1 Max with 64GB takes ~40 seconds
Hopefully the library is intentionally going very slowly trying to fit in RAM and that's not just your 8GB machine totally falling over.
Sadly, in this case it's the 8GB machine falling over.