Re:Run Stable Diffusion on Your M1 Mac’s GPU
by smoldesu on Thursday September 01, 2022 @01:42PM
(#32680114)
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.
If you extrapolate the power consumption (3070 @~300w vs M1 Pro GPU@~30-50w) the metrics make a lot of sense.