Diffusion Bee is the easiest way to run Stable Diffusion locally on your M1 Mac. Comes with a one-click installer. No dependencies or technical knowledge needed.
Logs:
Metal device set to: Apple M1 Pro
2022-09-24 10:24:42.126093:1 tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305]Could not identify NUMA node of platform GPU ID 0, defaulting to O. Your kernel may not have been built with NUMA support.
2022-09-24 10:24:42.126237:1 tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device V/job:localhost/replica:O/task:O/device:GPU:O with O MB memory) -> physical
PluggableDevice (device: O, name: METAL, pci bus id: «undefined>)
WARNING:tensorflow:AutoGraph could not transform <bound method CLIPTextTransformer.call of stable_diffusion_tf.clip_encoder.CLIPTextTransformer object at 0x303c6d0d0>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, export AUTOGRAPH_VERBOSITY=10') and attach the full output.
Cause: Unable to locate the source code of <bound method CLIPTextTransformer.call of stable_diffusion_tf.clip_encoder.CLIPTextTransformer object at 0×303c6d0d0>>. Note that functions defined in certain environments, like the interactive Python shell, do not expose their source code. If that is the case, you should define them in a py source file. If you are certain the code is graph-compatible, wrap the call using @tf.autograph.experimental.do_not_convert. Original error: could not get source code
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert
WARNING:tensorflow:AutoGraph could not transform <bound method CLIPTextEmbeddings.call of <stable_diffusion_tf.clip_encoder.CLIPTextEmbeddings object at 0×303c6d370>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, 'export AUTOGRAPH _VERBOSITY=10) and attach the full output.
Cause: Unable to locate the source code of <bound method CLIPTextEmbeddings.call of stable_diffusion_tf.clip_encoder.CLIPTextEmbeddings object at 0x303c6d370>>. Note that functions defined in certain environments, like the interactive Python shell, do not expose their source code. If that is the case, you should define them in a py source file. If you are certain the code is graph-compatible, wrap the call using @tf.autograph.experimental.do_not_convert. Original error: could not get source code
To silence this warning, decorate the function with @f.autograph.experimental.do_not_convert
WARNING:tensorflow:AutoGraph could not transform <bound method CLIPEncoder.call of <stable_diffusion_tf.clip_encoder CLIPEncoder object at 0×303c6d940>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, 'export AUTOGRAPH_VERBOSITY=10') and attach the full output.
Cause: Unable to locate the source code of <bound method CLIPEncoder.call of <stable_diffusion_tf.clip_encoder.CLIPEncoder object at 0x303c6d940>>. Note that functions defined in certain environments, like the interactive Python shell, do not expose their source code. If that is the case, you should define them in a py source file. If you are certain the code is graph-compatible, wrap the call using @tf.autograph.experimental.do_not_convert. Original error: could not get source code
To silence this warning, decorate the function with @f.autograph.experimental.do_not_convert
WARNING:tensorflow: AutoGraph could not transform <bound method CLIPEncoderLayer.call of <stable_diffusion_tf.clip_encoder.CLIPEncoderLayer object at 0x303c6dd90>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, 'export AUTOGRAPH_VERBOSITY=10' and attach the full output.
Cause: Unable to locate the source code of <bound method CLIPEncoderLayer.call of stable_diffusion_tf.clip_encoder.CLIPEncoderLayer object at 0x303c6dd90>>. Note that functions defined in certain environments, like the interactive Python shell, do not expose their source code. If that is the case, you should define them in a py source file. If you are certain the code is graph-compatible, wrap the call using @f.autograph.experimental.do_not_convert. Original error: could not get source code
To silence this warning, decorate the function with @tf.autograph.experimental.do_not_convert
WARNING:tensorflow: AutoGraph could not transform <bound method CLIPAttention.call of <stable_diffusion_tf.clip_encoder.CLIPAttention object at 0×305218070>> and will run it as-is.
Please report this to the TensorFlow team. When filing the bug, set the verbosity to 10 (on Linux, 'export AUTOGRAPH _VERBOSITY=10) and attach the full output.
Cause: Unable to locate the source code of <bound method CLIPAttention.call of stable_diffusion_tf.clip_encoder. CLIPAttention object at 0×305218070>>. Note that functions defined in certain environments, like the interactive Python shell, do not expose their source code. If that is the case, you should define them in a py source file. If you are certain the code is graph-compatible, wrap the call using @f.autograph.experimental.do_not_convert. Original error: could not get source code
To silence this warning, decorate the function with @f.autograph.experimental.do_not_convert
I'm not sure if it's an error, just thought you might be interested in logs.
M1 Pro 32Gb RAM 10 CPU 16 GPU Ventura 13.0 Beta
I'm not sure if it's an error, just thought you might be interested in logs.