StreamDiffusionTD 0.1.4

I have this problem and I don't know how to solve it: Process Process-4: Traceback (most recent call last): File "C:\test\StreamDiffusion\streamdiffusionTD\..\utils\wrapper.py", line 417, in _load_model pipe: StableDiffusionPipeline = StableDiffusionPipeline.from_pretrained( File "C:\test\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1090, in from_pretrained cached_folder = cls.download( File "C:\test\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1649, in download info = model_info( File "C:\test\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 110, in _inner_fn validate_repo_id(arg_value) File "C:\test\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 164, in validate_repo_id raise HFValidationError( huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: 'C:\test\StreamDiffusion\sd_xl_turbo_1.0_fp16.safetensors'. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\multiprocessing\process.py", line 314, in _bootstrap self.run() File "C:\Program Files\WindowsApps\PythonSoftwareFoundation.Python.3.10_3.10.3056.0_x64__qbz5n2kfra8p0\lib\multiprocessing\process.py", line 108, in run self._target(*self._args, **self._kwargs) File "C:\test\StreamDiffusion\streamdiffusionTD\main_ndi.py", line 212, in image_generation_process stream = StreamDiffusionWrapper( File "C:\test\StreamDiffusion\streamdiffusionTD\..\utils\wrapper.py", line 152, in __init__ self.stream: StreamDiffusion = self._load_model( File "C:\test\StreamDiffusion\streamdiffusionTD\..\utils\wrapper.py", line 422, in _load_model pipe: StableDiffusionPipeline = StableDiffusionPipeline.from_single_file( File "C:\test\StreamDiffusion\venv\lib\site-packages\diffusers\loaders\single_file.py", line 261, in from_single_file pipe = download_from_original_stable_diffusion_ckpt( File "C:\test\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\stable_diffusion\convert_from_ckpt.py", line 1745, in download_from_original_stable_diffusion_ckpt pipe = pipeline_class( TypeError: StableDiffusionPipeline.__init__() got an unexpected keyword argument 'text_encoder_2'

seems that I can't change resolution like v0.1.2~~

Hi! I have been trying to install this for hours. TouchDesigner's python interpreter is set to 3.11 in my version, but my conda env is 3.10.1 If I don't set the system path to my environment with python==3.10.1, I get no errors in the module, but I get an error on when I try to install SD saying no python 3.10.1 executable can be found. If I set my sys.path to my conda environment with python=3.10.1, the error disappears but instead I fail to import numpy. This is the error: "Please note and check the following: * The Python version is: Python3.11 from "C:\Program Files\Derivative\TouchDesigner\bin\TouchDesigner.exe" * The NumPy version is: "1.24.1" and make sure that they are the versions you expect. Please carefully study the documentation linked above for further help. Original error was: No module named 'numpy.core._multiarray_umath'" I suspect it's an issue between TD's chosen interpreter and my environment libraries..... but I can't figure it out.

Hi DotSimulate, I'm having problems when I try to Start Stream I get errors where it can't fine "par". I don't know how to get it working. https://drive.google.com/file/d/1QgmSWEiR26hnwxP3Gy6LpNcV5RF-iNJ4/view Thank you.

Edit: Solved - figured it out, I'm stll only getting around 11 FPS, is there a way to boost it? or is that kind of the standard? Hi Dot, thank you so much for your SD tox in TD, it's been amazing, I just had a question, I'm getting about 10-15 FPS with SD-Turbo and Dreamshaper 8, when I try run it with Custom LCM, it doesnt seem to work. When loading Custom LCM it only lets me select a folder, do I select my LCM lora folder and run it with the LCM lora active in Lora?

Hi, thanks for the reply. anyway I checked and I have already installed venv in the base folder.

Hi there! when i start the stream i get an error saying: Traceback (most recent call last): file "C:\Streamdiffusion\streamdiffusionID\main_ndi.py", line 20, in from utils.viewer import receive_images ModuleNotFoundError: no module named 'utils'

raise HFValidationError( huggingface_hub.utils._validators.HFValidationError: Repo id must use alphanumeric chars or '-', '_', '.', '--' and '..' are forbidden, '-' and '.' cannot start or end the name, max length is 96: ''. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\multiprocessing\process.py", line 315, in _bootstrap self.run() File "C:\Users\Usuario\AppData\Local\Programs\Python\Python310\lib\multiprocessing\process.py", line 108, in run self._target(*self._args, **self._kwargs) File "C:\StreamDiffusion\StreamDiffusion\streamdiffusionTD\main_ndi.py", line 212, in image_generation_process stream = StreamDiffusionWrapper( File "C:\StreamDiffusion\StreamDiffusion\streamdiffusionTD\..\utils\wrapper.py", line 152, in __init__ self.stream: StreamDiffusion = self._load_model( File "C:\StreamDiffusion\StreamDiffusion\streamdiffusionTD\..\utils\wrapper.py", line 422, in _load_model pipe: StableDiffusionPipeline = StableDiffusionPipeline.from_single_file( File "C:\StreamDiffusion\StreamDiffusion\venv\lib\site-packages\diffusers\loaders\single_file.py", line 235, in from_single_file raise ValueError( ValueError: The provided path is either not a file or a valid huggingface URL was not provided. Valid URLs begin with https://huggingface.co/, huggingface.co/, hf.co/, https://hf.co/

hi there ! is it possible to do img2img with streamdiffusion ? i was playing with the weights but it seems it sticking to the prompt.

after pressing on Install TensorRT I have this error: note: This error originates from a subprocess, and is likely not a problem with pip. ERROR: Failed building wheel for tensorrt Failed to build tensorrt ERROR: Could not build wheels for tensorrt, which is required to install pyproject.toml-based projects Error running command: -m pip install --pre --extra-index-url https://pypi.nvidia.com tensorrt==9.0.1.post11.dev4 --no-cache-dir Traceback (most recent call last): File "C:\Users\matte\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "C:\Users\matte\AppData\Local\Programs\Python\Python310\lib\runpy.py", line 86, in _run_code exec(code, run_globals) File "D:\StreamDiffusion\venv\lib\site-packages\streamdiffusion\tools\install-tensorrt.py", line 54, in fire.Fire(install) File "D:\StreamDiffusion\venv\lib\site-packages\fire\core.py", line 141, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "D:\StreamDiffusion\venv\lib\site-packages\fire\core.py", line 475, in _Fire component, remaining_args = _CallAndUpdateTrace( File "D:\StreamDiffusion\venv\lib\site-packages\fire\core.py", line 691, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "D:\StreamDiffusion\venv\lib\site-packages\streamdiffusion\tools\install-tensorrt.py", line 33, in install run_pip( File "D:\StreamDiffusion\venv\lib\site-packages\streamdiffusion\pip_utils.py", line 52, in run_pip return run_python(f"-m pip {command}", env) File "D:\StreamDiffusion\venv\lib\site-packages\streamdiffusion\pip_utils.py", line 46, in run_python raise RuntimeError(f"Error running command: {command}") RuntimeError: Error running command: -m pip install --pre --extra-index-url https://pypi.nvidia.com tensorrt==9.0.1.post11.dev4 --no-cache-dir TensorRT installation finished

digging around a bit, i think we want to use models that are tagged "stableDiffusionPipeline" such as runwayml/stable-diffusion-v1-5 or stablediffusionapi/juggernaut-xl-v8 the version of juggernaut I was trying to use is a RunDiffusion model

What are the requirements for the models? I was able to get Realistic_Vision_V6 to load, which is an SD1.5 model, but it doesn't want to load an SDXL1.0 model such as JuggernautXL_V8

Great stuff, works like a dream 🤘🏻

hey so I cannot get the stream to start on any of these, is there a troubleshooting info?? I have followed the youtube video but I just cannot get the stream to start, any help is always appreciated

Hey DotSimulate, magnificent work doing this integration, thanks a lot man. It'd be great to have a tutorial so we can learn how to setup this new version.

hi awesome work i have a problem with not squared resolution can you help me?

Awesome work man!, Like to join the discord :)

another error with the tensorrt. {SOLVED] I also had this error trying to install StreamDiffusion directly using their instructions on the github repo. RuntimeError: Error running command: -m pip install --pre --extra-index-url https://pypi.nvidia.com tensorrt==9.0.1.post11.dev4 --no-cache-dir the error on line 34: StreamDiffusion\venv\lib\site-packages\streamdiffusion\toos\install-tensorrt.py and this appears to go all the way up the chain to Nvidia. if you goto the https://pypi.org/project/tensorrt/9.0.1.post11.dev4/ site you'll find this: WARNING: This project is not functional and is a placeholder from NVIDIA. To install, please execute the following: pip install --no-cache-dir --extra-index-url https://pypi.nvidia.com tensorrt replacing the erroneous line with the one from pypi installed tensorrt 9.3.0.post12.dev1

When I click on "Install SD" (after cloning the git repo) nothing happens. I see two windows open and close very quicky. no venv folder gets created. I tried clicking on "Download/Update SD" and update repo and I also see a window flash onscreen very briefly. the textport reported: ==================================== Installation Details: ------------------------------------ Python 3.10 executable: C:\Users\tsepe\AppData\Local\Microsoft\WindowsApps\python.exe CUDA version: cu121 Base folder for venv: C:/Users/tsepe/Documents/StreamDiffusionProject/StreamDiffusion Installing packages for: StreamDiffusionTD ==================================== Writing batch file for installation... Executing batch file: StreamDiffusion\Install_StreamDiffusion.bat StreamDiffusion installation initiated with detected Python 3.10 and CUDA version. python >>> The start and install bat files were created in the folder but it seems the Install_StreamDiffusion.bat didn't want to run from TD. So I opened a command prompt and ran it directly so I could watch the output.

When I run it, this error appears. What is the reason? NotImplementedError: Cannot copy out of meta tensor; no data!

when installing venv + all req there is an issue due to nvidia-pyindex. I ll try try fresch install

Thanks as always mate!