The only modification I have done is moving from CUDA to MPS.
when i run the final prompt
animatediff generate -c config/prompts/prompt.json -W 512 -H 128 -C 16
Then I get the following error
loc("varianceEps"("(mpsFileLoc): /AppleInternal/Library/BuildRoots/c2cb9645-dafc-11ed-aa26-6ec1e3b3f7b3/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShadersGraph/mpsgraph/MetalPerformanceShadersGraph/Core/Files/MPSGraphUtilities.mm":228:0)): error: input types 'tensor<1x154x1xf16>' and 'tensor<1xf32>' are not broadcast compatible LLVM ERROR: Failed to infer result type(s). Abort trap: 6
I am using the M1 pro from macbook.
If I change it from CUDA to CPU it work (takes longer)
Any tips?
Following a tutorial (https://www.youtube.com/watch?v=7_hh3wOD81s)
I manage to get almost to the end of tutorial.
The only modification I have done is moving from CUDA to MPS. when i run the final prompt
animatediff generate -c config/prompts/prompt.json -W 512 -H 128 -C 16
Then I get the following error
loc("varianceEps"("(mpsFileLoc): /AppleInternal/Library/BuildRoots/c2cb9645-dafc-11ed-aa26-6ec1e3b3f7b3/Library/Caches/com.apple.xbs/Sources/MetalPerformanceShadersGraph/mpsgraph/MetalPerformanceShadersGraph/Core/Files/MPSGraphUtilities.mm":228:0)): error: input types 'tensor<1x154x1xf16>' and 'tensor<1xf32>' are not broadcast compatible LLVM ERROR: Failed to infer result type(s). Abort trap: 6
I am using the M1 pro from macbook. If I change it from CUDA to CPU it work (takes longer) Any tips?