StreamDiffusionTD 0.2.0🚀🖼️
Added 2024-08-18 16:02:00 +0000 UTC👋 Hey friends! StreamDiffusionTD 0.2.0 is here with major improvements across the entire operator including ControlNet support, offline usage, and new features like V2V temporal consistency and pause/play/unload commands. I am releasing a tutorial series covering 0.2.0 - the first video on installation is up now, with more coming very soon.
Also ! it has been a little bit since my last update, which means I've got lots to share - including updates to nearly every operator I've released + a few exciting new ones. I'm finally ready to get these into your hands, so you can expect more regular updates from me moving forward. I am also making an effort to include more video tutorials and better documentation.
A huge thanks to all of you for your support ! and special shoutout to all who have helped test and given feedback on this batch of updates as well as in the past. All of your support, ideas, and feedback (yes including error messages) is very much appreciated and drive me to keep pushing forward. Looking forward to seeing what you create with these new features! 🧪✨
-Lyell
Get the TOX here >>> https://www.patreon.com/posts/110313168
See the changelog here >>> https://www.patreon.com/posts/109087864
StreamDiffusionTD 0.2.0 [ Installation + Setup ] >>> https://www.youtube.com/watch?v=F2JSWAKex4k=
Comments
Hello, I don't know if this is the good place to ask for help, let me know if there is actually an other. While attempting to start stream, a window signal "ModuleNotFoundError: No module named 'cv2'". What can I do to repair this? Thank you
Airelle Dubois
2025-06-20 12:40:44 +0000 UTCi hve an isue. I cant instal Failed to activate virtual environment. Please check the path and ensure the venv exists.
MIkhail Loginev
2024-11-15 10:54:01 +0000 UTCsame isue
MIkhail Loginev
2024-11-15 09:34:23 +0000 UTCHey there, do you know how can i solve this problem? Current directory: C:\Users\lumaia86\Documents\Touchdesigner\STREAM DIFFUSION TEST 2.2\StreamDiffusion Changed directory to: C:\Users\lumaia86\Documents\Touchdesigner\STREAM DIFFUSION TEST 2.2\StreamDiffusion Creating Python venv at: "C:/Users/lumaia86/Documents/Touchdesigner/STREAM DIFFUSION TEST 2.2/StreamDiffusion\venv" C:\python-3.10.11-embed-amd64\python.exe: No module named venv Attempting to activate virtual environment... El sistema no puede encontrar la ruta especificada. Failed to activate virtual environment. Please check the path and ensure the venv exists. Path to venv: "C:/Users/lumaia86/Documents/Touchdesigner/STREAM DIFFUSION TEST 2.2/StreamDiffusion\venv" VIRTUAL_ENV: "" Presione una tecla para continuar . . .
Luciana Maia
2024-11-15 06:31:56 +0000 UTCDowngrading huggingface-hub to version 0.24.6 fixed it for me.
MoritzW
2024-10-07 14:35:00 +0000 UTCsame issue here
Eduardo Ortega
2024-09-25 13:48:09 +0000 UTCsame issue
Andreas
2024-09-17 22:23:18 +0000 UTCmine gives this error when I click on the pulse of the star stream: Traceback (most recent call last): File "M:\Ai_1\StreamDiffusion\streamdiffusionTD\wrapper_td.py", line 683, in _load_model pipe = pipeline_class.from_pretrained( File "M:\Ai_1\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1090, in from_pretrained cached_folder = cls.download( File "M:\Ai_1\StreamDiffusion\venv\lib\site-packages\diffusers\pipelines\pipeline_utils.py", line 1856, in download cached_folder = snapshot_download( File "M:\Ai_1\StreamDiffusion\venv\lib\site-packages\huggingface_hub\utils\_validators.py", line 114, in _inner_fn return fn(*args, **kwargs) File "M:\Ai_1\StreamDiffusion\venv\lib\site-packages\huggingface_hub\_snapshot_download.py", line 216, in snapshot_download raise LocalEntryNotFoundError( huggingface_hub.errors.LocalEntryNotFoundError: Cannot find an appropriate cached snapshot folder for the specified revision on the local disk and outgoing traffic has been disabled. To enable repo look-ups and downloads online, pass 'local_files_only=False' as input. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "M:\Ai_1\StreamDiffusion\streamdiffusionTD\wrapper_td.py", line 687, in _load_model except huggingface_hub.utils._errors.LocalEntryNotFoundError: AttributeError: module 'huggingface_hub.utils' has no attribute '_errors' Failed to load model due to: module 'huggingface_hub.utils' has no attribute '_errors'
Vj Igor Cardoso
2024-09-17 20:21:43 +0000 UTCis it possible to see just the result of the control-net, for example the openpose or the hed? just to make sure this part works as expected. thanks, love your work
Frédéric Bussière
2024-09-16 23:32:12 +0000 UTCThis is brill! However I keep getting 'status: server connected, not streaming' do you know what this could be? Thanks!
fidlar
2024-09-12 19:17:06 +0000 UTCNot sure who needs this, but Python 3.12 gave me some errors. Just use the recommended python 3.10.9. Once I changed, the installation went perfect.
Jeroen Bocken
2024-09-09 16:32:59 +0000 UTCThanks for this and the guide. I've been having some wierd behaviour with it, I am running it on a 4090 system with a Threadripper 3970X and am getting approx 15fps with default settings, I have a 2nd PC with a 4070 and a 7700x cpu and am getting 16fps, any ideaswhy I'm getting better performance with the cheaper build?
Mark Jones
2024-09-04 15:03:13 +0000 UTCAny updates on when the next update is coming. And your outlook on what’s to come?
Wesley Messina
2024-09-03 15:21:00 +0000 UTCIt's no problem to do that. You have to play around with noise and adding that by using a comp node to get the noise onto your webcam video input. :-)
McPixel
2024-09-02 07:15:08 +0000 UTCany updates on this? our (un)stable diffusion keeps crashing haha
Drew Molleur
2024-09-02 02:29:20 +0000 UTCnot working for me :(
Andrew Hlynsky
2024-09-01 19:04:07 +0000 UTCJust change the Resolution in Setting and after that change the streamout text in setting 2 and it will run. This is a workaround.
Iven
2024-08-30 20:34:10 +0000 UTCStill struggling to change the resolution. I'm just getting started, so I don't have any projects to rebuild. If you feel like sending me the file i would be incredibly thankful!
Andrew Hlynsky
2024-08-30 20:30:36 +0000 UTCHay, thanks for the solution. I keep running into this as soon as I activate acceleration though. Is there a workaround for that to? EDIT: I was using a pretty odd resolution 1920x546 I think that was the reason it did not work, staying with "normal" resolutions seems to work!
Eugene O'Donald
2024-08-30 06:40:26 +0000 UTCHas anyone tried successfully to use another model then the SD Turbo. I cannot understand how to get it to work, since it errors when downloading from hugging face id, and the local ones are not visible in the drop down
Stoyan Stoyanov
2024-08-28 13:32:06 +0000 UTCHey, thank you very much for that great plugin! Do you know when the resolution fix get's online? Thank you! Best Korbi
McPixel
2024-08-28 08:08:57 +0000 UTCNo Mac support?
BreakItDown
2024-08-28 03:07:56 +0000 UTCMac please
BreakItDown
2024-08-27 08:33:32 +0000 UTCHello! I've followed tutorial to download stable diffusion. I don't have any errors appearing, but the output is just black and SD doesn't seem to work. Do you know what could be the problem? Did anyone faced something similar? Thank you!
Veronika Shiliak
2024-08-26 17:25:13 +0000 UTChey thanks for your work on this, is there a path forwards to load civit ai models into streamdiffusionTD?
Enviral Design
2024-08-26 16:12:29 +0000 UTChello, i just bought it. i would like to know that is it can be used commercially?
梓 王
2024-08-26 14:24:31 +0000 UTCHey, awesome work. On my Laoptop everything is fine. But i try to run it on my desktop and i always get this after installing when i try to start streaming in my cmd.exe (...path To RepostreamdiffusionTD\main_sdtd.py:485: SyntaxWarning: invalid escape sequence '\C' print(f"\Controlnet Stream '{input_mem_name} not found. Try changing the Stream Out Name (to SD) parameter in Stream Settings 2 of TD operator.") Sorry i dont get it. Need some help please. Thank You!
Iven
2024-08-26 12:07:42 +0000 UTC<3
Charles Coragem
2024-08-25 15:03:23 +0000 UTCJust to complete it here (as you also answered on discord but it‘s perhaps good to know): it seems to be linked to the models version but I did test LoRas trained on 2.1 that worked and some that didn‘t. I‘ll keep on testing and meanwhile use the working ones, which I am fine with.
Christopher Lensing
2024-08-25 08:17:06 +0000 UTCLikely due to model mismatch. What sd model are you using? You will need to make sure the LoRA is trained for that model pipe (1.5,2.1,sdxl, etc)
dotsimulate
2024-08-24 19:33:42 +0000 UTCI get an error concerning LoRas: ERROR loading LoRA Models: Error(s) in loading state_dict for UNet2DConditionModel: size mismatch for down_blocks.0.attentions.0.proj_in.lora_A.WillemVanAelst.weight: copying a param with shape torch.Size([128, 320, 1, 1]) from checkpoint, the shape in current model is torch.Size([128, 320]). size mismatch for down_blocks.0.attentions.0.proj_in.lora_B.WillemVanAelst.weight: copying a param with shape torch.Size([320, 128, ... (error message shortened by 63 lines). Any idea why?
Christopher Lensing
2024-08-24 19:25:20 +0000 UTCYes that is known bug with this version. it works if you change the streamoutname after changing the resolution but I also have a fix that I am planning on posting today. Trying to get an updater op finalized so replacing it doesn't require project rebuild at all.
dotsimulate
2024-08-23 17:37:10 +0000 UTCcan you do one with live cam being generated as ai, i want to use it for live cam visual
Riverdhan
2024-08-23 16:18:14 +0000 UTCis there a way to use a different resolution than 512x512 like in previous version?
Iven
2024-08-23 13:59:09 +0000 UTCHaving trouble to connect to Discord and having problems with Creating Python venv
João Rodrigues
2024-08-22 20:05:54 +0000 UTCcan you send me a DM (discord ideally just for screenshots,etc or patreon) with more info on this? The operator copies code into the folder each time the stream starts so if you edited and saved the file itself that would actually have no difference. If you changed the code in the operator in order to fix this, this is definitely something for me to take note of.
dotsimulate
2024-08-21 03:38:34 +0000 UTCHit the Install 2 pulse and it will install that library. You are just missing a single additional library that was added in this version.
dotsimulate
2024-08-21 03:36:28 +0000 UTCCheck your firewall or network settings and make sure python.exe or TouchDesigner is not blocked or restricted.
dotsimulate
2024-08-21 03:35:58 +0000 UTCIt was working on mac a couple of versions ago .. to make this one do anything I had to change the hardcoded 'cuda' references in main_sdtd.py:370 ``` input_tensor = torch.empty((3, height, width), dtype=torch.float32, device=device) control_input_tensor = torch.empty((3, height, width), dtype=torch.float32, device=device) pinned_input_buffer = torch.empty((height, width, 3), dtype=torch.uint8, pin_memory=False) pinned_control_buffer = torch.empty((height, width, 3), dtype=torch.uint8, pin_memory=False) ```
Matthieu Tourne
2024-08-20 21:33:58 +0000 UTCA matching Triton is not available, some optimizations will not be enabled. Error caught was: No module named 'triton' Traceback (most recent call last): File "C:\Users\JAM\StreamDiffusion\streamdiffusionTD\main_sdtd.py", line 37, in from wrapper_td import StreamDiffusionWrapper File "C:\Users\JAM\StreamDiffusion\streamdiffusionTD\wrapper_td.py", line 24, in from pipeline_td import StreamDiffusion File "C:\Users\JAM\StreamDiffusion\streamdiffusionTD\pipeline_td.py", line 19, in from v2v_utils import get_nn_latent #V2V File "C:\Users\JAM\StreamDiffusion\streamdiffusionTD\v2v_utils.py", line 5, in from einops import rearrange ModuleNotFoundError: No module named 'einops' why~
jianyu mo
2024-08-20 16:12:34 +0000 UTCPLEASE HELP !When i pulse"download streamdiffusion"TD“No internet connection detected”
疯人
2024-08-20 10:14:11 +0000 UTCLink is in under the About me pulse in the about parameter page.
dotsimulate
2024-08-19 14:52:40 +0000 UTCIs there something comming for Mac Silicon? cant get the mac version to work
Oskar Martinussen
2024-08-19 12:13:04 +0000 UTCAmazing! TensorRT isnt working, can i get the Discord link for support?
Rotem Mor
2024-08-19 06:57:49 +0000 UTCtouch designer doesnt play well with macs
Gus
2024-08-19 02:51:17 +0000 UTClet's go!!! 🔥🔥🔥
Sina Solaimanpour
2024-08-18 21:23:00 +0000 UTCxmas morning!
K N
2024-08-18 19:25:33 +0000 UTClegend, that v2v thing is amazing - makes much smoother
Gus
2024-08-18 19:16:40 +0000 UTCyou star men!!🍒
Գեւորգ Արամ
2024-08-18 17:56:00 +0000 UTCnice update! I been getting error installing tensort will try checking cuda cudnn install. is there a tutorial to this process by chance?
tYk
2024-08-18 17:37:10 +0000 UTCAwesome stuff. When do you think a Mac version will be available?
Drew Molleur
2024-08-18 16:14:06 +0000 UTC
