StreamDiffusionTD 0.1.7 🖼️🚀 [ Changelog ]

Hi, i have been trying everything, and have setup a vpn but it doesn't seem to work, and i am fairly new with the hugging face website. what are the steps i have to take to get a model locally? ps: i have updated to tox 0.1.9

Michael Claessens

Thank you so much for the update!!! I tried loading a custom SDXL model in the tox - apologies if you've covered this somewhere, but are there different settings that are needed for running SDXL models? Right now all my images are turning out hazy

Jacky Lu

When I load the tox. all the parameter tabs are empty except extension, common and custom

Torben Zs

Could likely be that it is not accessible in your region or firewal or vpn might be cutting off the connection. also changing location via vpn could help.

dotsimulate

hi i first of all, very nice work! i wanted to try it out but i also get an error where the model isn't loading, and i restarted and now i cant seem to get a CMD window popping up. is it possible that the hugging API is down? During handling of the above exception, another exception occurred: Traceback (most recent call last): File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\streamdiffusionTD\..\utils\wrapper.py", line 417, in _load_model pipe: StableDiffusionPipeline = StableDiffusionPipeline.from_pretrained( File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1090, in from_pretrained cached_folder = cls.download( File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1649, in download info = model_info( File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 119, in _inner_fn return fn(*args, **kwargs) File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\huggingface_hub\hf_api.py", line 2227, in model_info r = get_session().get(path, headers=headers, timeout=timeout, params=params) File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 600, in get return self.request("GET", url, **kwargs) File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 587, in request resp = self.send(prep, **send_kwargs) File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\requests\sessions.py", line 701, in send r = adapter.send(request, **kwargs) File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_http.py", line 68, in send return super().send(request, *args, **kwargs) File "C:\Users\mc\Desktop\SDtouchdesigner\StreamDiffusion\venv\lib\site-packages\requests\adapters.py", line 547, in send raise ConnectionError(err, request=request) requests.exceptions.ConnectionError: (ProtocolError('Connection aborted.', ConnectionResetError(10054, 'An existing connection was forcibly closed by the remote host', None, 10054, None)), '(Request ID: 83d6f800-b779-4497-8eb9-f5809bda6156)') Model load has failed. Doesn't exist.

Michael Claessens

it may be due to something with connection to model or getting stuff in the loading process. I had this happen to me once when huggingface api was down for the day.

dotsimulate

Perhaps something is disconnected with ndi . if you can send a screenshot, I am happy to look

dotsimulate

everything is done but can't show the result, how can i fix it?

Rajendra Raga

Hi Dotsimulate! I’m facing an issue where the command window gets stuck at the “preparing stream….” Line. This is after all the set up has been done. Im using the “stabilityai/ sd-turbo” as my SD model. Please let me know if there is a solution?

_ Wykes

I recently started subscribing to you. Thanks for useful tox! I'd like to ask you about stream diffusion tox. It seems that we can set some step parameters. I'm not sure what multiple settings are associated with, could you please explain?

mu_shr

cant wait for the non local inference update!

Ahmad Haqqi

I just can't get past this error, had it trying to get 1.0 and 1.5 working too. Leading to the cmd window just popping up and disappearing when I start the stream. I can't find how to remedy this error either way, so I'm at a loss. From what I gather, the venv is short of json, re, shutil, traceback and glob. error: subprocess-exited-with-error × Getting requirements to build wheel did not run successfully. │ exit code: 1 ╰─> [4 lines of output] Traceback (most recent call last): File "E:\StreamDiffusion-for-windows\venv\lib\site-packages\pip\_vendor\pyproject_hooks\_in_process\_in_process.py", line 15, in import json ModuleNotFoundError: No module named 'json' [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.

Jimi Vex

Likely should be able to help but might be a bit more info. Can you dm the full log or send message on discord with screenshots. Is likely an easy fix.

dotsimulate

It should list it in the cmd window. But also if launching from TouchDesigner should be launching with a cmd that sets the sender name based on the Streaminname parameter in StreamSettings2 page. Maybe make sure that that is set to a unique name and you don't have other projects / versions of StreamDiffusionTD open.

dotsimulate

How do you find the number for the corresponding ndi output

tmoney

you may have a console message asking you to input the number of the ndi sender you d like to use as written at the end of your error message (""Enter the number of the NDI source you want to use: ")) - 1 ValueError: invalid literal for int() with base 10: ** "). I had this too , you just have to type the number coresponding to your chosen ndi output and hit enter to continue

virusvjvisuals

Alessia Zucca

I've been trying to get this working with TD 2023.11600 and .11340 to no avail. Whenever I try to start the stream the cmd prompt asks for an NDI source number to use but immediately crashes no matter the response. Traceback (most recent call last): File "D:\StableDiffusion\StreamDiffusion\streamdiffusionTD\main_ndi.py", line 648, in fire.Fire(main) File "D:\StableDiffusion\StreamDiffusion\venv\lib\site-packages\fire\core.py", line 143, in Fire component_trace = _Fire (component, args, parsed_flag_args, context, name) File "D:\StableDiffusion\StreamDiffusion\venv\lib\site-packages\fire\core.py", line 477, in _Fire component, remaining_args = _CallAndUpdateTrace( File "D:\StableDiffusion\StreamDiffusion\venv\lib\site-packages\fire\core.py", line 693, in _CallAndUpdateTrace component = fn(*varargs, **kwargs) File "D:\StableDiffusion\StreamDiffusion\streamdiffusionTD\main_ndi.py", line 578, in main ndi_sender_name = select_ndi_source(args.sender) # Pass args.sender to the function line 207, in select_ndi_source File "D:\StableDiffusion\StreamDiffusion\streamdiffusionTD\ndi_spout_utils.py", selected_index = int(input("Enter the number of the NDI source you want to use: ")) - 1 ValueError: invalid literal for int() with base 10: **

tmoney

I gotta crack this baby open soon!

Dr. Mindset

Yes!!! The update I have been waiting for!! Thank you so much 👏👏

Malich Coory