Stable Diffusion Issue on MacOS 14 Sonoma
Reading this story will provide you with two solutions
After upgrading to MacOS 14 Sonoma, users have encountered issues with Stable Diffusion. I will provides two solutions to address this problem.
What happen when upgraded to Sonoma
Upon upgrading to the latest MacOS 14 Sonoma, users have experienced difficulties generating images in Automatic1111’s StableDiffusionWebUI. The problem resembles the one discussed in a GitHub issue. Although the WebUI opens successfully but generating images results in numerous error messages.
Python[13813:192227] ANE Evaluation Error = Error Domain=com.apple.appleneuralengine Code=8 "processRequest:model:qos:qIndex:modelStringID:options:error:: ANEProgramProcessRequestDirect() Failed with status=0x16 : statusType=0x9: Program Inference error" UserInfo={NSLocalizedDescription=processRequest:model:qos:qIndex:modelStringID:options:error:: ANEProgramProcessRequestDirect() Failed with status=0x16 : statusType=0x9: Program Inference error}
Solution 1: Update Torch
- Update Torch to the latest version using the following command:
pip3 install --upgrade --pre torch torchvision --index-url https://download.pytorch.org/whl/nightly/cpu
2. Modify the webui-user.sh
as follows:
#!/bin/bash
#########################################################
# Uncomment and change the variables below to your need:#
#########################################################
# Install directory without trailing slash
#install_dir="/home/$(whoami)"
# Name of the subdirectory
#clone_dir="stable-diffusion-webui"
# Commandline arguments for webui.py, for example: export COMMANDLINE_ARGS="--medvram --opt-split-attention"
export COMMANDLINE_ARGS="--skip-torch-cuda-test --upcast-sampling --no-half-vae --use-cpu interrogate"
# python3 executable
#python_cmd="python3"
# git executable
#export GIT="git"
# python3 venv without trailing slash (defaults to ${install_dir}/${clone_dir}/venv)
#venv_dir="venv"
# script to launch to start the app
#export LAUNCH_SCRIPT="launch.py"
# install command for torch
export TORCH_COMMAND="pip install --pre torch==2.2.0.dev20231012 torchvision==0.17.0.dev20231012 --index-url https://download.pytorch.org/whl/nightly/cpu"
# Requirements file to use for stable-diffusion-webui
#export REQS_FILE="requirements_versions.txt"
# Fixed git repos
#export K_DIFFUSION_PACKAGE=""
#export GFPGAN_PACKAGE=""
# Fixed git commits
#export STABLE_DIFFUSION_COMMIT_HASH=""
#export CODEFORMER_COMMIT_HASH=""
#export BLIP_COMMIT_HASH=""
# Uncomment to enable accelerated launch
#export ACCELERATE="True"
# Uncomment to disable TCMalloc
#export NO_TCMALLOC="True"
###########################################
3. Restart WebUI with this command: ./webui.sh --reinstall-torch
4. It will update your WebUI’s torch version to torch: 2.2.0.dev20231012
After making these changes, the image generation function should work properly.
Solution 2: Emergency Solution
If the above modifications do not work, there is a simple emergency solution. Modify the startup command to: ./webui.sh --half
This allows you to open the UI and generate images, although the speed might be slightly slower than before. It is advisable to use the Torch update method for optimal performance.
This story is published on Generative AI. Connect with us on LinkedIn to get the latest AI stories and insights right in your feed. Let’s shape the future of AI together!