Generated images are constantly blank

[oscarnevarezleal]

What happened?

I downloaded the Model Checkpoints from huggingface and run the inference command but everytime either the output is completely blank or something like the image below

Tech details

Chip: Apple M2
Memory: 8GB
OS: 13.1 Beta (22C5059b)

pip list
Package                        Version    Editable project location
------------------------------ ---------- ----------------------------------------------------------
accelerate                     0.15.0
certifi                        2022.9.24
charset-normalizer             2.1.1
coremltools                    6.1
diffusers                      0.9.0
filelock                       3.8.0
huggingface-hub                0.11.1
idna                           3.4
importlib-metadata             5.1.0
mpmath                         1.2.1
numpy                          1.23.5
packaging                      21.3
Pillow                         9.3.0
pip                            22.3.1
protobuf                       3.20.3
psutil                         5.9.4
pyparsing                      3.0.9
python-coreml-stable-diffusion 0.1.0      /...
PyYAML                         6.0
regex                          2022.10.31
requests                       2.28.1
scipy                          1.9.3
setuptools                     65.5.1
sympy                          1.11.1
tokenizers                     0.13.2
torch                          1.12.0
tqdm                           4.64.1
transformers                   4.25.1
typing_extensions              4.4.0
urllib3                        1.26.13
wheel                          0.38.4
zipp                           3.11.0

python -m python_coreml_stable_diffusion.pipeline --prompt "a photo of an astronaut riding a horse on mars" -i models/coreml-stable-diffusion-v1-4_original_packages -o output --compute-unit CPU_AND_NE --num-inference-steps 50
INFO:__main__:Setting random seed to 93
INFO:__main__:Initializing PyTorch pipe for reference configuration
Fetching 16 files: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 16/16 [00:00<00:00, 17467.17it/s]
INFO:__main__:Removed PyTorch pipe to reduce peak memory consumption
INFO:__main__:Loading Core ML models in memory from models/coreml-stable-diffusion-v1-4_original_packages
INFO:python_coreml_stable_diffusion.coreml_model:Loading text_encoder mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Loading models/coreml-stable-diffusion-v1-4_original_packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_text_encoder.mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Done. Took 5.1 seconds.
INFO:python_coreml_stable_diffusion.coreml_model:Loading unet mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Loading models/coreml-stable-diffusion-v1-4_original_packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_unet.mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Done. Took 116.1 seconds.
INFO:python_coreml_stable_diffusion.coreml_model:Loading a CoreML model through coremltools triggers compilation every time. The Swift package we provide uses precompiled Core ML models (.mlmodelc) to avoid compile-on-load.
INFO:python_coreml_stable_diffusion.coreml_model:Loading vae_decoder mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Loading models/coreml-stable-diffusion-v1-4_original_packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_vae_decoder.mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Done. Took 7.3 seconds.
INFO:python_coreml_stable_diffusion.coreml_model:Loading safety_checker mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Loading models/coreml-stable-diffusion-v1-4_original_packages/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_safety_checker.mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Done. Took 2.2 seconds.
INFO:__main__:Done.
INFO:__main__:Initializing Core ML pipe for image generation
INFO:__main__:Stable Diffusion configured to generate 512x512 images
INFO:__main__:Done.
INFO:__main__:Beginning image generation.
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 51/51 [00:35<00:00,  1.44it/s]
INFO:__main__:Generated image has nsfw concept=False
INFO:__main__:Saving generated image to output/a_photo_of_an_astronaut_riding_a_horse_on_mars/randomSeed_93_computeUnit_CPU_AND_NE_modelVersion_CompVis_stable-diffusion-v1-4.png