Home Creators Posts Import Register Favorites Logout

Downloads

Content

Prompt Blocks added for mixing multiple prompts with per prompt weights- 'Normalize Prompt Weights' toggle parameter- 'Total Weight Slider' parameter to set amount to normalize prompt weights.

Seeds Blocks added for mixing multiple seeds with per seed weights- 'Total Seed Noise Multiplier' parameter to boost/reduce overall noise- NOTE: Mixing the same seed isn't recommended, but mixing different seeds should blend.

Improved Installation Process (all moved to the "Install" parameter page)   - Checks for correct python version (3.10) and cuda version (11.8 or 12.1)   - Paired down to essential imports + preps for tensorrt installation.   - Additional Installation Pulse for tensorrt. Need to run after main install. But should be working.   - if you had issues before. delete the venv folder and try with this operator.   - IMPORTANT NOTE [ for TensorRT ]: it will take around 10 minutes or so for the model to build an engine the first time you launch with tensorrt. BE PATIENT. there will be minutes where it seems like nothing is happening. This process only needs to happen once per step count / model id. And the engines that are made are cached inside StreamDiffusion/engines in case you want to delete them later.

Other fixes/improvements !- Fixed the issue that requires the enable/disable after stream starts- Fixed Spout BGR color issue.- Improved handling of NDI 'stream in name' to ensure unique name from the StreamDiffusion serverParameter Menu Pages Cleaned.- Settings/setup changed to Settings 1/2 Page- Settings 1 page is now dedicated to settings that can be changed when the stream is active.- Install page added for dedicated installation/Basefolder parameters

Comments

Function Store

Mate, what a release! (easily v0.2 material)

DotSimulate

Thanks !! and true. it is a bit more than a patch...

hihello

Cant wait to try this!

Jordan Nering

Stoked!!! Finally got a chance to try it out today for my first time. This is just beyond rad! Now another update so fast. Hats off man!!!

Indra's Mirror

Works amazing! Thank you for your hard work!

Dr Augustine Leudar Spatial Audio (edited)

Comment edits

2026-09-08 07:00 tx for being so fast !! nearly all working - the only red error I get now is: "ERROR: Could not find a version that satisfies the requirement torch==2.1.0 (from versions: none) ERROR: No matching distribution found for torch==2.1.0" now as the only error. When I try and pulse to start streaming it cant find torch and the black wibndow dissapears. Also installing venv I see in yellow : DEPRECATION: git+https://github.com/cumulo-autumn/StreamDiffusion.git@main#egg=streamdiffusion[tensorrt] contains an egg fragment with a non-PEP 508 name pip 25.0 will enforce this behaviour change. A possible replacement is to use the req @ url syntax, and remove the egg fragment. Discussion can be found at https://github.com/pypa/pip/issues/11617
2024-02-06 13:31

vento

What a cool tool bro thanks!!!! I'm having an issue: Started with ndi input using CMD. Streming info - not streaming. I've installed apart: NDI SDK, python3.10, linked the model v1-5-pruned-emaonly.ckpt, also ndi/spout installed through the tox 1.1, and the three buttons completed without errors. The error says: unable to create ndi sender for specific name.. but changing name won't affect. Any suggestion? thanks a lot do you prefer sd-turbo instead of sd1.5?

Christian Mu

Perhaps I'm missing something here, but I'm only able to get TensorRT to work with the default 512x512 resolution. When I try to rebuild at a different resolution, it doesn't seem to make much of a difference. Any tips?

Arthur Deleu

Hey man! Amazing work! Was just wonedering how can I know for sure that TensorRT is installed correctly and activated? Also, what degrees of speedups could one expect with it? :)

Juan Hernandez

Hello, can I have the discord please, so I can discuss some issues I had with the tox

DotSimulate

When it is running there will be a clear printout that says 'TensorRT acceleration enabled.' You need to set the acceleration mode under the model parameter to tensorrt, and first time loading it will take a few minutes to build the tensorrt engine. Engine is built based on the model name + step count, and if those settings are the same it won't rebuild when relaunching.

DotSimulate

Yes. looked into this for a bit today and wasn't able to get things working. Not too sure on that front currently

DotSimulate

I've got maybe some fixes for cuda 12.1. There is an issue with the TensorRT 12.1 iinstall currently. Discovered today by someone in the discord. Maybe try with fresh venv and make sure you are using the operator from this post.

Julii Haid

Hello! Thank you very much for this! I bought the .tox and when it's installing TensorRT, it's not progressing while creating the wheel for TensorRT (pyproject.toml).

Kawatin

So genius! It's great that TensorRT was added to the installation flow! Thank you for your great work!

Alex Klauck

Hey there, thank you for your awesome work! Im itching to try out stream diffusion and i think i did all the steps to install all the librarys etc but it doesnt seem to work at all. All i get out when i connect a TOP to the Stream Diffusion Base is the exact same image as the input. Do you have a suggestion what i did wrong? Thanks!

YASU_NiL

please update to use with conda

vento

i'm spending a lot of time trying to make it work, but won't work... my last issue is: ERROR: Package 'streamdiffusion' requires a different Python: 3.9.13 not in '>=3.10.0' as you suggest, but uninstalling 3.10 and installing 3.9 doesn't affect the result, they're added to path by installation checkbox. Then when i try to start streaming it say: Error caught was: No module named 'triton' that i'm not able to solve. ModuleNotFoundError: No module named 'pytorch_lightning' any suggestion? please

virusvjvisuals

about Triton , it s a "normal" bug we all have, but doesn"t affect the program as far as it s been said ^^ for python 3.9, tryc to check your env variable PATH and if the 3.10 isn't still there or placed above/before your 3.9 version.. after that i d suggest deleting the 'venv' folder inside your streamdiffusion folder, and from TD2023 opening streamdiffusion toe, and add the main folder path, and update (first button) (read the yellow message to see about update state), reinstall venv with second, and install tensorRT with third .. save your project and restart ... just advices, i m far from being an expert but if it can help a bit .. :)

Sรผleyman Yilmaz

This is an amazing tool, thank you so much. Is there a way to use other checkpoints I want with Stream Diffusion, or can I use other checkpoints as I do in Comfy UI? I saw some other turbo models on the Civit AI website, but I don't have much of an idea on how to use them with Stream Diffusion. Thanks in advance. Best regards.

DotSimulate

You want python 3.10.9 installed and cuda 11.8 The error isn't that easy to read, but it is saying that python 3.9.13 will not work.

Gianluca Colia

I downloaded the python 3.10.9 version but I get the error on the TD window "Python 3.10 executable not found. Please ensure Python 3.10 is installed and accessible" now I was wondering how to make the executable accessible?

Erin Robinson

This is so amazing thank you so much!!! I'm having difficulty getting a lora working with this (using SDXL Loras), do you have to write something in the prompt to activate it similar to automatic1111? Thanks :)

Gordon kummel

I am unable to load sd-turbo by downloading the safetensors file from hugging face (same ID as the default you have). In the load it says path is not a valid local file (and for sure path is valid). I would ideally like to be able to use this disconnected from internet. But its super amazing otherwise thank you so much for making this.

DotSimulate

Yep! I looked into this today for a good bit. Going to push an update that supports fully local. I wasn't aware that it was checking with huggingfacehub for models details each time the stream starts.

vento

thanks but looks like i'm unlucky. py3.10.9 is the only one installed and in path, cuda 11.8 here. i tryied also deleting all at the end and redo from skretch, now it's saying just that below when start streming,, thanks a lot if you can help me, and thanks for your time. 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/

Arthur Deleu

Having the same issue as well! Trying to fix it in the code, if you would have any leads on this, would be very grateful! :)

Raquel F.

Hi there! Thanks a lot for this! Unfortunately after installing everything and press "Start stream" a cmd window appears and then goes away without giving any error message. Stream Info says "Not Streaming". Any idea of what could be the problem? I've also tried with the first version and I have the same problem... Thanks for your help and work!

Raquel F.

Ignore me, I forgot to install the NDI... Once I did that and reinstalled everything again it worked perfectly. Thanks so much! This is so much fun :)

Andrea Tamburrini

@dot thers a way in the development of your code in TD to check different version of cuda or installing parallel cuda (like pyenv for python for example) to perform the last cuda version or the best for the machin?

DotSimulate

Hey Andrea! thanks for the bump. I looked at my code and found a typo that is likely the cause of your error. Posting a few in a hour.

DotSimulate

Glad you got it working ! if there is ever an issue with the stream starting / cmd window disappearing, you can manually edit the .bat file that is created that starts the stream and add 'pause' in a new line, which will force the cmd window to stay open after it errors out. Will need to run the .bat manually from the StreamDiffusion folder, but that would likely have given a ndi lib import error. putting this here for you in future or anyone else that might see this with same issue.

DotSimulate

sdxl isn't supported by streamdiffusion ! sd-turbo is 2.1 based model and doesn't have many or any loras that work I believe. 1.5 models use the LCM lora and you can load loras with them.

DotSimulate

Sorry for not seeing this ! hopefully you made some progress .... but ! if python is installed the operator should be able to find it. Try reinstalling or modifying and fixing the install.

Lucas

Did you solve this? I have the same problem but can't seem to figure this out...

Djoeneuh

Really a wonderfull tool! Love your work, hope our path's with cross somday!

Artwait

I'm getting this error, what's the reason and how can I fix it? Error: Basefolder parameter must be set to '/StreamDiffusion'. 'path/to/StreamDiffusion/venv' not found.