Using --compute-unit CPU_AND_GPU results in a black image

[AlDante]

python -m python_coreml_stable_diffusion.pipeline --prompt "highly detailed photo of assistant professor getting lost in a data labyrinth with venomous snakes" -i output-mlpackages -o images --compute-unit ALL --seed 93 produces the attached image.

python -m python_coreml_stable_diffusion.pipeline --prompt "highly detailed photo of assistant professor getting lost in a data labyrinth with venomous snakes" -i output-mlpackages -o images --compute-unit CPU_AND_GPU --seed 93 produces a black image (also attached).

Both runs on M1 Max MacBook with Ventura, and default installation of ml-stable-diffusion.

Model Name:	MacBook Pro
  Model Identifier:	MacBookPro18,2
  Model Number:	Z14X0002GD/A
  Chip:	Apple M1 Max
  Total Number of Cores:	10 (8 performance and 2 efficiency)
  Memory:	32 GB
  System Firmware Version:	8419.41.10
  OS Loader Version:	8419.41.10

Chipset Model:	Apple M1 Max
  Type:	GPU
  Bus:	Built-In
  Total Number of Cores:	32
  Vendor:	Apple (0x106b)
  Metal Support:	Metal 3
![randomSeed_93_computeUnit_ALL_modelVersion_CompVis_stable-diffusion-v1-4](https://user-images.githubusercontent.com/3430712/205510539-7aeccfa0-75bb-491b-a100-176d19ac5731.png)
![randomSeed_93_computeUnit_CPU_AND_GPU_modelVersion_CompVis_stable-diffusion-v1-4](https://user-images.githubusercontent.com/3430712/205510545-b1e08456-cc10-49cd-b43e-3527f2f6d8c3.png)