stable-fast version 1.0.0 does not support Windows system？

[vbqgyy]

win10 system installation environment： triton==2.0.0 torch==2.1.0+cu118 xformers==0.0.22.post7+cu118 CUDA==11.8 Python==3.10.6

ComfyUI_stable_fast
After updating the latest version：

Using xformers attention in VAE Working with z of shape (1, 4, 32, 32) = 4096 dimensions. Using xformers attention in VAE missing {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'} left over keys: dict_keys(['cond_stage_model.clip_l.transformer.text_model.embeddings.position_ids']) ERROR:root:!!! Exception during processing !!! ERROR:root:Traceback (most recent call last): File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\execution.py", line 83, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\execution.py", line 76, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\custom_nodes\ComfyUI_stable_fast\node.py", line 101, in apply_stable_fast config = gen_stable_fast_config() File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\custom_nodes\ComfyUI_stable_fast\node.py", line 22, in gen_stable_fast_config import triton File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton__init__.py", line 13, in from . import language File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\language__init__.py", line 2, in from . import core, extern, libdevice, random File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\language\core.py", line 1141, in def abs(x): File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\runtime\jit.py", line 386, in jit return JITFunction(args[0], kwargs) File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\runtime\jit.py", line 315, in init self.run = self._make_launcher() File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\runtime\jit.py", line 282, in _make_launcher scope = {"version_key": version_key(), "get_cuda_stream": get_cuda_stream, File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\runtime\jit.py", line 82, in version_key with open(triton._C.libtriton.file, "rb") as f: AttributeError: partially initialized module 'triton' has no attribute '_C' (most likely due to a circular import)

[lengyanju8]

No module named 'sfast._C

[lengyanju8]

(py310) D:\sd\stable-fast>pip install -e . Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple Obtaining file:///D:/sd/stable-fast Installing build dependencies ... done Checking if build backend supports build_editable ... done Getting requirements to build editable ... error error: subprocess-exited-with-error

× Getting requirements to build editable did not run successfully. │ exit code: 1 ╰─> [19 lines of output] Traceback (most recent call last): File "C:\ProgramData\Anaconda3\envs\lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 353, in main() File "C:\ProgramData\Anaconda3\envs\lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 335, in main json_out['return_val'] = hook(**hook_input['kwargs']) File "C:\ProgramData\Anaconda3\envs\lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 132, in get_requires_for_build_editable return hook(config_settings) File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-rgx9b7up\overlay\Lib\site-packages\setuptools\build_meta.py", line 441, in get_requires_for_build_editable return self.get_requires_for_build_wheel(config_settings) File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-rgx9b7up\overlay\Lib\site-packages\setuptools\build_meta.py", line 325, in get_requires_for_build_wheel return self._get_build_requires(config_settings, requirements=['wheel']) File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-rgx9b7up\overlay\Lib\site-packages\setuptools\build_meta.py", line 295, in _get_build_requires self.run_setup() File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-rgx9b7up\overlay\Lib\site-packages\setuptools\build_meta.py", line 480, in run_setup super(_BuildMetaLegacyBackend, self).run_setup(setup_script=setup_script) File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-rgx9b7up\overlay\Lib\site-packages\setuptools\build_meta.py", line 311, in run_setup exec(code, locals()) File "", line 13, in ModuleNotFoundError: No module named 'torch' [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: subprocess-exited-with-error

× Getting requirements to build editable did not run successfully. │ exit code: 1 ╰─> See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.

[lengyanju8]

C:\ProgramData\Anaconda3\envs\py310>python -m pip install D:\sd\stable-fast Looking in indexes: https://pypi.tuna.tsinghua.edu.cn/simple Processing d:\sd\stable-fast Installing build dependencies ... done Getting requirements to build wheel ... error error: subprocess-exited-with-error

× Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> [17 lines of output] Traceback (most recent call last): File "C:\ProgramData\Anaconda3\envs\lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 353, in main() File "C:\ProgramData\Anaconda3\envs\lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 335, in main json_out['return_val'] = hook(**hook_input['kwargs']) File "C:\ProgramData\Anaconda3\envs\lib\site-packages\pip_vendor\pyproject_hooks_in_process_in_process.py", line 118, in get_requires_for_build_wheel return hook(config_settings) File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-f9lupbm6\overlay\Lib\site-packages\setuptools\build_meta.py", line 325, in get_requires_for_build_wheel return self._get_build_requires(config_settings, requirements=['wheel']) File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-f9lupbm6\overlay\Lib\site-packages\setuptools\build_meta.py", line 295, in _get_build_requires self.run_setup() File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-f9lupbm6\overlay\Lib\site-packages\setuptools\build_meta.py", line 480, in run_setup super(_BuildMetaLegacyBackend, self).run_setup(setup_script=setup_script) File "C:\Users\Administrator\AppData\Local\Temp\pip-build-env-f9lupbm6\overlay\Lib\site-packages\setuptools\build_meta.py", line 311, in run_setup exec(code, locals()) File "", line 13, in ModuleNotFoundError: No module named 'torch' [end of output]

note: This error originates from a subprocess, and is likely not a problem with pip. error: subprocess-exited-with-error

× Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> See above for output.

note: This error originates from a subprocess, and is likely not a problem with pip.

[lengyanju8]

C:\ProgramData\Anaconda3\envs\py310>pip show torch Name: torch Version: 2.1.1 Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration Home-page: https://pytorch.org/ Author: PyTorch Team Author-email: packages@pytorch.org License: BSD-3 Location: c:\programdata\anaconda3\lib\site-packages Requires: jinja2, fsspec, typing-extensions, networkx, sympy, filelock Required-by: torchaudio, pytorch-wavelets, openai-whisper, accelerate

[chengzeyi]

@lengyanju8 Your torch is installed in a different python virtual env from stable-fast. You need to make sure that torch exists before stable-fast.

[chengzeyi]

win10 system installation environment： triton==2.0.0 torch==2.1.0+cu118 xformers==0.0.22.post7+cu118 CUDA==11.8 Python==3.10.6

ComfyUI_stable_fast After updating the latest version：

Using xformers attention in VAE Working with z of shape (1, 4, 32, 32) = 4096 dimensions. Using xformers attention in VAE missing {'cond_stage_model.clip_l.text_projection', 'cond_stage_model.clip_l.logit_scale'} left over keys: dict_keys(['cond_stage_model.clip_l.transformer.text_model.embeddings.position_ids']) ERROR:root:!!! Exception during processing !!! ERROR:root:Traceback (most recent call last): File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\execution.py", line 153, in recursive_execute output_data, output_ui = get_output_data(obj, input_data_all) File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\execution.py", line 83, in get_output_data return_values = map_node_over_list(obj, input_data_all, obj.FUNCTION, allow_interrupt=True) File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\execution.py", line 76, in map_node_over_list results.append(getattr(obj, func)(slice_dict(input_data_all, i))) File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\custom_nodes\ComfyUI_stable_fast\node.py", line 101, in apply_stable_fast config = gen_stable_fast_config() File "D:\0AI\0StableDiffusion\ComfyUI\ComfyUI\custom_nodes\ComfyUI_stable_fast\node.py", line 22, in gen_stable_fast_config import triton File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\tritoninit.py", line 13, in from . import language File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\languageinit.py", line 2, in from . import core, extern, libdevice, random File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\language\core.py", line 1141, in def abs(x): File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\runtime\jit.py", line 386, in jit return JITFunction(args[0], kwargs) File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\runtime\jit.py", line 315, in init self.run = self._make_launcher() File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\runtime\jit.py", line 282, in _make_launcher scope = {"version_key": version_key(), "get_cuda_stream": get_cuda_stream, File "D:\0AI\0StableDiffusion\ComfyUI\python_embeded\lib\site-packages\triton\runtime\jit.py", line 82, in version_key with open(triton._C.libtriton.file, "rb") as f: AttributeError: partially initialized module 'triton' has no attribute '_C' (most likely due to a circular import)

triton is currently not officially supported on Windows. Please disable it if you face problems.