Open 0ihsan opened 1 year ago
Hello @0ihsan, this looks like the same confusion point as #267 in that the model you pointed to uses --attention-implementation ORIGINAL
which is compatible with --compute-units cpuAndGPU
whereas the newly published coreml-stable-diffusion-xl-base-ios uses --attention-implementation SPLIT_EINSUM
which is compatible with --compute-units cpuAndNeuralEngine
. We are considering reorganizing the published model folder to make this clearer. (cc: @pcuenca)
For your references. I test with DreamShaper XL1.0 on MacBook Air M2, 25 steps about 290 seconds. => 0.08 step/sec
using
StableDiffusionCLI
withcomputeUnits = .cpuAndGPU
and this specific model: https://huggingface.co/apple/coreml-stable-diffusion-mixed-bit-palettization/tree/main/coreml-stable-diffusion-xl-base_mbp_4_50_palettized/compiledfinishes generating image. image looks not usable: major flaws. (that's another issue).
memory: 8gb
also tried:
computeUnits = .cpuAndNeuralEngine
:ANECompilerService
never finishes (waited 10+ mins) it's job and sampling never starts. needsplit_einsum
version i assume.computeUnits = .cpuOnly
: gets killed, due to memory issues i guess.