All black in apple ml-stable-diffusion, any one help me?
python -m python_coreml_stable_diffusion.pipeline
-i ./ai_model
-o ./ai_image
--compute-unit CPU_AND_GPU
--seed 4444
--prompt "1girl, sexy extreme Gstring micro Bikini, mini bikini, Slutty, on beach, big boob, good looking, attractive face, smiling, full body, running, highly detailed, hyper-realistic "
--negative-prompt "ugly,grayscale, extra limbs, extra arms, missing arms, bad tongue, strange fingers"
--model-version emilianJR/chilloutmix_NiPrunedFp32Fix
/Volumes/User/Project/ml-stable-diffusion/python_coreml_stable_diffusion/pipeline.py:9: FutureWarning: Importing DiffusionPipeline or ImagePipelineOutput from diffusers.pipeline_utils is deprecated. Please import from diffusers.pipelines.pipeline_utils instead.
from diffusers.pipeline_utils import DiffusionPipeline
WARNING:coremltools:scikit-learn version 1.3.0 is not supported. Minimum required version: 0.17. Maximum required version: 1.1.2. Disabling scikit-learn conversion API.
WARNING:coremltools:Torch version 2.0.1 has not been tested with coremltools. You may run into unexpected errors. Torch 2.0.0 is the most recent version that has been tested.
INFO:main:Setting random seed to 4444
INFO:main:Initializing PyTorch pipe for reference configuration
unet/diffusion_pytorch_model.safetensors not found
Loading pipeline components...: 71%|█████████▎ | 5/7 [00:01<00:00, 3.48it/s]/Users/linyu/opt/anaconda3/envs/coreml_stable_diffusion/lib/python3.8/site-packages/transformers/models/clip/feature_extraction_clip.py:28: FutureWarning: The class CLIPFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use CLIPImageProcessor instead.
warnings.warn(
Loading pipeline components...: 100%|█████████████| 7/7 [00:03<00:00, 2.11it/s]
INFO:main:Removed PyTorch pipe to reduce peak memory consumption
INFO:main:Loading Core ML models in memory from ./ai_model
INFO:python_coreml_stable_diffusion.coreml_model:Loading text_encoder mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Loading ./ai_model/Stable_Diffusion_version_emilianJR_chilloutmix_NiPrunedFp32Fix_text_encoder.mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Done. Took 1.7 seconds.
INFO:python_coreml_stable_diffusion.coreml_model:Loading unet mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Loading ./ai_model/Stable_Diffusion_version_emilianJR_chilloutmix_NiPrunedFp32Fix_unet.mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Done. Took 12.8 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 ./ai_model/Stable_Diffusion_version_emilianJR_chilloutmix_NiPrunedFp32Fix_vae_decoder.mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Done. Took 5.3 seconds.
INFO:python_coreml_stable_diffusion.coreml_model:Loading safety_checker mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Loading ./ai_model/Stable_Diffusion_version_emilianJR_chilloutmix_NiPrunedFp32Fix_safety_checker.mlpackage
INFO:python_coreml_stable_diffusion.coreml_model:Done. Took 2.0 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.
use - pipe.safety_checker = None