Comments (22)
I checked the log during "install dependencies" got errors:
Installing collected packages: libclang, flatbuffers, wrapt, wheel, werkzeug, termcolor, tensorflow-io-gcs-filesystem, tensorflow-estimator, tensorboard-data-server, pyasn1, protobuf, opt-einsum, oauthlib, ml-dtypes, markdown, keras, h5py, grpcio, google-pasta, gast, cachetools, absl-py, rsa, requests-oauthlib, pyasn1-modules, astunparse, google-auth, google-auth-oauthlib, tensorboard, tensorflow-macos, tensorflow
Successfully installed absl-py-2.0.0 astunparse-1.6.3 cachetools-5.3.2 flatbuffers-23.5.26 gast-0.5.4 google-auth-2.24.0 google-auth-oauthlib-1.1.0 google-pasta-0.2.0 grpcio-1.59.3 h5py-3.10.0 keras-2.15.0 libclang-16.0.6 markdown-3.5.1 ml-dtypes-0.2.0 oauthlib-3.2.2 opt-einsum-3.3.0 protobuf-4.23.4 pyasn1-0.5.1 pyasn1-modules-0.3.0 requests-oauthlib-1.3.1 rsa-4.9 tensorboard-2.15.1 tensorboard-data-server-0.7.2 tensorflow-2.15.0 tensorflow-estimator-2.15.0 tensorflow-io-gcs-filesystem-0.34.0 tensorflow-macos-2.15.0 termcolor-2.4.0 werkzeug-3.0.1 wheel-0.42.0 wrapt-1.14.1
Installing: soundfile module
Collecting PySoundFile
Downloading PySoundFile-0.9.0.post1-py2.py3-none-any.whl (24 kB)
Collecting cffi>=0.6 (from PySoundFile)
Using cached cffi-1.16.0-cp310-cp310-macosx_11_0_arm64.whl.metadata (1.5 kB)
Collecting pycparser (from cffi>=0.6->PySoundFile)
Using cached pycparser-2.21-py2.py3-none-any.whl (118 kB)
Using cached cffi-1.16.0-cp310-cp310-macosx_11_0_arm64.whl (176 kB)
Installing collected packages: pycparser, cffi, PySoundFile
Successfully installed PySoundFile-0.9.0.post1 cffi-1.16.0 pycparser-2.21
Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 567, in import_module
subprocess.call([python_exe, "import ", packageName])
NameError: name 'packageName' is not defined
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/soundfile.py", line 267, in <module>
_snd = _ffi.dlopen('sndfile')
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 150, in dlopen
lib, function_cache = _make_ffi_library(self, name, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 832, in _make_ffi_library
backendlib = _load_backend_lib(backend, libname, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 827, in _load_backend_lib
raise OSError(msg)
OSError: ctypes.util.find_library() did not manage to locate a library called 'sndfile'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 855, in execute
install_modules(self)
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 699, in install_modules
import_module(self, "soundfile", "PySoundFile")
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 596, in import_module
exec("import " + module)
File "<string>", line 1, in <module>
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/soundfile.py", line 276, in <module>
_snd = _ffi.dlopen(_os.path.join(
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 150, in dlopen
lib, function_cache = _make_ffi_library(self, name, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 832, in _make_ffi_library
backendlib = _load_backend_lib(backend, libname, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 827, in _load_backend_lib
raise OSError(msg)
OSError: cannot load library '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib': dlopen(/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib, 0x0002): tried: '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file), '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file). Additionally, ctypes.util.find_library() did not manage to locate a library called '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib'
Info: Installing: huggingface_hub module.
Info: Installing: accelerate module.
Info: Installing: bark module.
Info: Installing: diffusers module.
Info: Installing: tensorflow module.
Info: Installing: soundfile module.
Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 567, in import_module
subprocess.call([python_exe, "import ", packageName])
NameError: name 'packageName' is not defined
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/soundfile.py", line 267, in <module>
_snd = _ffi.dlopen('sndfile')
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 150, in dlopen
lib, function_cache = _make_ffi_library(self, name, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 832, in _make_ffi_library
backendlib = _load_backend_lib(backend, libname, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 827, in _load_backend_lib
raise OSError(msg)
OSError: ctypes.util.find_library() did not manage to locate a library called 'sndfile'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 855, in execute
install_modules(self)
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 699, in install_modules
import_module(self, "soundfile", "PySoundFile")
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 596, in import_module
exec("import " + module)
File "<string>", line 1, in <module>
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/soundfile.py", line 276, in <module>
_snd = _ffi.dlopen(_os.path.join(
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 150, in dlopen
lib, function_cache = _make_ffi_library(self, name, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 832, in _make_ffi_library
backendlib = _load_backend_lib(backend, libname, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 827, in _load_backend_lib
raise OSError(msg)
OSError: cannot load library '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib': dlopen(/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib, 0x0002): tried: '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file), '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file). Additionally, ctypes.util.find_library() did not manage to locate a library called '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib'
from pallaidium.
In my case my Stripe is image ( I don't understand name and seed, how to setup properly), -- but I believe it will be doing image 2 image, but I have zero generation so far.
1/1
Prompt: impressionist painting apple on table 123454, impressionist painting IMG_4087, impressionist painting IMG_4087, impressionist painting IMG_4087, man and corgi portrait. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form
Negative Prompt: anime, photorealistic, 35mm film, deformed, low contrast, noisy
Load: img2img/vid2img Model
Conversion Model: stabilityai/sdxl-turbo
The config attributes {'feature_extractor': [None, None], 'image_encoder': [None, None]} were passed to StableDiffusionXLImg2ImgPipeline, but are not expected and will be ignored. Please verify your model_index.json configuration file.
Keyword arguments {'feature_extractor': [None, None], 'image_encoder': [None, None]} are not expected by StableDiffusionXLImg2ImgPipeline and will be ignored.
Loading pipeline components...: 29%|████████████████████████████████████▌ | 2/7 [00:00<00:00, 10.21it/s]The config attributes {'attention_type': 'default', 'dropout': 0.0, 'reverse_transformer_layers_per_block': None} were passed to UNet2DConditionModel, but are not expected and will be ignored. Please verify your config.json configuration file.
Loading pipeline components...: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:01<00:00, 5.26it/s]
Seed: 123454
Process: Image to Image
Token indices sequence length is longer than the specified maximum sequence length for this model (132 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form']
Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3636, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 859, in __call__
) = self.encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 332, in encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3636, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 859, in __call__
) = self.encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 332, in encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA eTraceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 4120, in execute
sequencer.generate_image()
File "/Applications/Blender.app/Contents/Resources/3.6/scripts/modules/bpy/ops.py", line 113, in __call__
ret = _op_call(self.idname_py(), None, kw)
RuntimeError: Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3636, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 859, in __call__
) = self.encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 332, in encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Location: /Applications/Blender.app/Contents/Resources/3.6/scripts/modules/bpy/ops.py:113
Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 4120, in execute
sequencer.generate_image()
File "/Applications/Blender.app/Contents/Resources/3.6/scripts/modules/bpy/ops.py", line 113, in __call__
ret = _op_call(self.idname_py(), None, kw)
RuntimeError: Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3636, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 859, in __call__
) = self.encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 332, in encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Location: /Applications/Blender.app/Contents/Resources/3.6/scripts/modules/bpy/ops.py:113
from pallaidium.
Yeah, for some reason it still tries to insist on using CUDA. I tried something and updated the Mac branch. Try to redownload it.
That error with sound file installation, I'll have to investigate. But lets first try to see if that CUDA problem is solvable.
from pallaidium.
maybe just turn off torch cuda thing?
sdxl turbo PINOKIO:
import gradio as gr
from diffusers import AutoPipelineForText2Image, AutoPipelineForImage2Image
from diffusers.utils import load_image
import torch
if torch.cuda.is_available():
device = "cuda"
elif torch.backends.mps.is_available():
device = "mps"
else:
device = "cpu"
pipes = {
"txt2img": AutoPipelineForText2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16").to(device),
"img2img": AutoPipelineForImage2Image.from_pretrained("stabilityai/sdxl-turbo", torch_dtype=torch.float16, variant="fp16").to(device)
}
if device == "cpu":
pipes["txt2img"].enable_model_cpu_offload()
pipes["img2img"].enable_model_cpu_offload()
def run(prompt, image):
print(f"prompt={prompt}, image={image}")
if image is None:
return pipes["txt2img"](prompt=prompt, num_inference_steps=1, guidance_scale=0.0).images[0]
else:
image = image.resize((512,512))
print(f"img2img image={image}")
return pipes["img2img"](prompt, image=image, num_inference_steps=3, strength=0.79, guidance_scale=0.1).images[0]
demo = gr.Interface(
run,
inputs=[
gr.Textbox(label="Prompt"),
gr.Image(type="pil")
],
outputs=gr.Image(width=512,height=512),
live=True
)
#demo.dependencies[0]["show_progress"] = "minimal"
demo.launch()
from pallaidium.
Cool. Thank you. I didn't know about mps on mac. Try now.
(I'll have to go, will check back soonish)
from pallaidium.
Back. Did that solve it?
from pallaidium.
The idea is to have at least SDXL turbo to run. I am not a coder myself so I don't know what's missing. Yes on macOS it's all CPU, slower than NVIdia GPU, but not bad.
from pallaidium.
Did you check the latest version?
from pallaidium.
Latest version, new error:
Info: Installing: bark module.
Info: Installing: diffusers module.
Info: Installing: tensorflow module.
Info: Installing: soundfile module.
Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 578, in import_module
subprocess.call([python_exe, "import ", packageName])
NameError: name 'packageName' is not defined
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/soundfile.py", line 267, in <module>
_snd = _ffi.dlopen('sndfile')
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 150, in dlopen
lib, function_cache = _make_ffi_library(self, name, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 832, in _make_ffi_library
backendlib = _load_backend_lib(backend, libname, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 827, in _load_backend_lib
raise OSError(msg)
OSError: ctypes.util.find_library() did not manage to locate a library called 'sndfile'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 866, in execute
install_modules(self)
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 710, in install_modules
import_module(self, "soundfile", "PySoundFile")
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 607, in import_module
exec("import " + module)
File "<string>", line 1, in <module>
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/soundfile.py", line 276, in <module>
_snd = _ffi.dlopen(_os.path.join(
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 150, in dlopen
lib, function_cache = _make_ffi_library(self, name, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 832, in _make_ffi_library
backendlib = _load_backend_lib(backend, libname, flags)
File "/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/cffi/api.py", line 827, in _load_backend_lib
raise OSError(msg)
OSError: cannot load library '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib': dlopen(/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib, 0x0002): tried: '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file), '/System/Volumes/Preboot/Cryptexes/OS/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file), '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib' (no such file). Additionally, ctypes.util.find_library() did not manage to locate a library called '/Applications/Blender.app/Contents/Resources/3.6/python/lib/python3.10/site-packages/_soundfile_data/libsndfile.dylib'
2023-12-03 03:04:55.102 Blender[44352:2281090] WARNING: Secure coding is not enabled for restorable state! Enable secure coding by implementing NSApplicationDelegate.applicationSupportsSecureRestorableState: and returning YES.
from pallaidium.
Also:
Seed: 123454
Process: Image to Image
Token indices sequence length is longer than the specified maximum sequence length for this model (161 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form']
Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3647, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 859, in __call__
) = self.encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 332, in encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3647, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 859, in __call__
) = self.encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 332, in encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA eTraceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 4131, in execute
sequencer.generate_image()
File "/Applications/Blender.app/Contents/Resources/3.6/scripts/modules/bpy/ops.py", line 113, in __call__
ret = _op_call(self.idname_py(), None, kw)
RuntimeError: Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3647, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 859, in __call__
) = self.encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 332, in encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Location: /Applications/Blender.app/Contents/Resources/3.6/scripts/modules/bpy/ops.py:113
Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 4131, in execute
sequencer.generate_image()
File "/Applications/Blender.app/Contents/Resources/3.6/scripts/modules/bpy/ops.py", line 113, in __call__
ret = _op_call(self.idname_py(), None, kw)
RuntimeError: Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3647, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 859, in __call__
) = self.encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion_xl/pipeline_stable_diffusion_xl_img2img.py", line 332, in encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Location: /Applications/Blender.app/Contents/Resources/3.6/scripts/modules/bpy/ops.py:113
from pallaidium.
Yes, the soundfile I haven't looked into, but what happens when you try to generate something?
from pallaidium.
Above was install, below is when executing also failed:
... truncatedLoad: img2img/vid2img Model
Conversion Model: runwayml/stable-diffusion-v1-5
model_index.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 541/541 [00:00<00:00, 1.86MB/s]
text_encoder/config.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 617/617 [00:00<00:00, 953kB/s]
tokenizer/tokenizer_config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 806/806 [00:00<00:00, 843kB/s]
scheduler/scheduler_config.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 308/308 [00:00<00:00, 1.32MB/s]
safety_checker/config.json: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 4.72k/4.72k [00:00<00:00, 16.1MB/s]
unet/config.json: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 743/743 [00:00<00:00, 5.59MB/s]
vae/config.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 547/547 [00:00<00:00, 9.48MB/s]
diffusion_pytorch_model.fp16.safetensors: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 167M/167M [00:56<00:00, 2.98MB/s]
model.fp16.safetensors: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 246M/246M [01:03<00:00, 3.86MB/s]
model.fp16.safetensors: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 608M/608M [02:07<00:00, 4.77MB/s]
diffusion_pytorch_model.fp16.safetensors: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.72G/1.72G [03:30<00:00, 8.18MB/s]
Fetching 15 files: 100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 15/15 [03:31<00:00, 14.11s/it]
Loading pipeline components...: 14%|██████████████████▊ | 1/7 [00:00<00:00, 6.63it/s]`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["id2label"]` will be overriden.██████████████████████████| 1.72G/1.72G [03:30<00:00, 13.6MB/s]
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["bos_token_id"]` will be overriden.
`text_config_dict` is provided which will be used to initialize `CLIPTextConfig`. The value `text_config["eos_token_id"]` will be overriden.
Loading pipeline components...: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:00<00:00, 11.91it/s]
Seed: 123454
Process: Image to Image
Token indices sequence length is longer than the specified maximum sequence length for this model (161 > 77). Running this sequence through the model will result in indexing errors
The following part of your input was truncated because CLIP can only handle sequences up to 77 tokens: ['loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form. loose brushwork, vibrant color, light and shadow play, captures feeling over form']
Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3657, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py", line 674, in __call__
prompt_embeds = self._encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py", line 338, in _encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
Error: Python: Traceback (most recent call last):
File "/Users/jimmygunawan/Library/Application Support/Blender/3.6/scripts/addons/Pallaidium-Pallaidium_MacOS/__init__.py", line 3657, in execute
image = converter(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py", line 674, in __call__
prompt_embeds = self._encode_prompt(
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/diffusers/pipelines/stable_diffusion/pipeline_stable_diffusion_img2img.py", line 338, in _encode_prompt
text_input_ids.to(device),
File "/Users/jimmygunawan/.local/lib/python3.10/site-packages/torch/cuda/__init__.py", line 239, in _lazy_init
raise AssertionError("Torch not compiled with CUDA enabled")
AssertionError: Torch not compiled with CUDA enabled
from pallaidium.
Maybe Dream Texture addon install can show the way:
https://github.com/carson-katri/dream-textures
from pallaidium.
Question is if something special needs to be done on a Mac to install torch.
from pallaidium.
Also this:
radames/Real-Time-Latent-Consistency-Model#15
from pallaidium.
Could this also help?
https://g.co/bard/share/f8b1565bb26e
from pallaidium.
If you potentially have a lot of old python modules installed, try Uninstall Dependencies. Restart Blender Install Dependencies. If it is using cached versions, search the closed issues here for torch and there is a big thread on how to manually remove python modules completely.
from pallaidium.
I don't quite mess with that, but usually this is done from the addon install requirements?
Anyhow, I think the module isn't properly installed, but I know Dream Texture works on macOS, but slightly slow.
A better way is if Palladium connect to ComfyUI -- as server backend. I have ComfyUI working and fast.
from pallaidium.
If you want to check the python version, get this add-on and hit the list button:
https://github.com/amb/blender_pip
from pallaidium.
btw:
Apple just release "mlx" and probably can install stable diffusion this way via its mlx module?
https://github.com/ml-explore/mlx
Alternatively, I still think the ComfyUI backend is worth testing on your side:
- ComfyUI server running and can generate (also with custom workflow)
- Pallaidium could pull images from generated AI.
- Simpler?
from pallaidium.
In your script, can you just "turn off CUDA" because macOS stable diffusion uses something else?
Like cpu only?
from pallaidium.
We tried a few things, and apparently they do not solve the problems, so, I'm sorry, there is no way I can try to solve the Mac problems without having a Mac, and for that reason I'll have to close this report as it is unsupported.
from pallaidium.
Related Issues (20)
- Please use Releases feature so we can subscribe to updates HOT 1
- basic steps not work HOT 3
- errors on Generate from Strips HOT 3
- Illusion model not loading HOT 5
- Art: Stained Glass calls graffiti style instead HOT 2
- xFormers can't load C++/CUDA extensions HOT 9
- can the add-on share model files with the original software like stable diffusions? HOT 3
- FR: Save metadata HOT 1
- Würstchen is currently not working
- error on 1.6 version when trying to use audio LDM 2 sound and bark HOT 2
- error when installing MusicGen Stereo model HOT 19
- error on 1.7 version HOT 14
- NameError: name '_C' is not defined HOT 13
- Problem: Video, img2img HOT 4
- The system cannot find the specified path: HOT 9
- Animatediff not working? HOT 3
- ModuleNotFoundError: No module named 'google.protobuf HOT 3
- IDEA: Integration with krita-ai-diffusion HOT 3
- Bug - cant find python linux HOT 3
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from pallaidium.