@@VJSCHOOL I tried building a model with different res and more steps, but it wouldn't finish... Super impressed with the speed, it's still super jittery and "stabley", but that's just animdif in general I geuss, excited to try out control net!!
@@Djopy i solved this problem by uninstalling the latest python (3.13) then installed (3.11.1) after that i added path in environment variables. this error is gone, but i have now other new errors
Hey VJ SCHOOL!thanks for the tutorial. I get to the point where you have to click "Load Engine" pulse button, but then it doesn't do anything. I'm not sure if this helps figure out what's going wrong, but I noticed in your video at 6:26 the "Active engine" variable updates from "none" to "sd-turbo-512-512-1" whereas for me the "active engine" variable stays on "none" no matter how many times i reload or press the pulse button!
Thanks for this great solution! Amazing performance on 4070 12GB! SD Turbo and 1 sample step. I will test making other engine now. 3 sample steps were slow on 4070.
Hi, i want to tell if there is some solucion to this, when a press load engine, nothing happens at all, thanks you very much for the sharing this video is great !
When trying to Re-init I get - Failed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback): module 'numpy' has no attribute 'dtypes' And when Trying to click pulse for "Load engine" I get - name 'StreamDiffusionWrapper' is not defined maybe that helps...asked gpt and looked through all the issues, just cant seem to fix it
when i hit pulse to refresh the engine nothing happens, engine is missing inside TD but not inside folder "checkpoints". started the pc and TD several times, doesnt help :( what could it be?
I also have errors: Failed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback): module 'numpy' has no attribute '_core' and name 'StreamDiffusionWrapper' is not defined
Amazing video, what are the steps to have live feedback from the camera, remove background then generate on what's left? Like reacting to someone moving live
I try it , it shows Error no module named 'StreamDiffusion' Error Failed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback)：module 'numpy' has no attribute 'dtypes' Error Name 'StreamDiffusionWrapper' is no defined
THIS video talks about the portable version and NOT the manual installation. If you try following this installation for the manual installation, you are going to face errors related to models and engines not being found, for example "cannot access local variable 'pipe' where it is not associated with a value", because the paths for the portable version and the manual version are slightly different. That's why I recommend using the portable version
Very interesting, but when I clicked load engine in touchdesigner, I got an error like "cannot access local variable 'pipe' where it is not associated with a value". What is the problem?
@@VJSCHOOL Tried the portable as well as the manual version. Same error. It may be because Runway shut down their SD1.5 repositories on huggingface? Posted the full log on GitHub Issue. Thanks!
@@VJSCHOOL Hey! I have a little trouble downloading the portable version since only the first zip file can be opened with 7zip, rest is broken. Is there a way to extract them all?
OSError: [WinError 126] The specified module could not be found. Error loading "C:\Users\PC ABU-ABU\Desktop\TouchDiffusion-main\TouchDiffusion-main\.venv\Lib\site-packages\torch\lib\fbgemm.dll" or one of its dependencies. No launch file found please help
Hello, I thought the video was excellent, thanks for sharing the info. I'm on the last step, but when I put an image in TD it doesn't generate the video as fluidly as you do, it gets stuck and only broken images appear, and it says "Error- No module named "steamDiffusion" what can I do?
@@rodrigosimoes3177 thanks ! it works :) But we have a incompatibility issue (still the generation is working) ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts. onnxruntime 1.16.3 requires numpy>=1.24.2, but you have numpy 1.23.5 which is incompatible.
Nevertheless I got finished engine preparation and selected the file which webui includes, it doesnt work.. I tried to press load engine and refresh engine several times, but it dosent work.. how to resolve this :(
hi ,i have followed your tutorial and every step went well .But in TouchDesigner,the log shows :cannot access local variable 'pipe' where it is not associated with a value.I don't know how did it happened
Hi! Thnaks for the video Oleg, I just have one problem at the end of the whole porcess, in TD when I select the touchdiffusion main folder it seem like it dont read the location, I restart the program and pc, but the error keep there, :( what could it be? anyone knows? thnks!!!
amazing fast speeds would you know why using my null of the render tops of my td projects as input isnt working? im getting flashing white and black with some cat images but noise top works normally, denoising value dosent change this would we have to repeat the webui model proceses with higher steps seems like it could be that or a different problem if so how should i do that thanks!
1) everything installed in venv, so it not affecting main Python env. 2) if you want to try with Python 3.10, then provide path to it in webui & use TouchDesigner version before 2023
Hello, first of all congratulations on the tremendous work I have been using the DSD patch for a long time without any problems, but now I have a constant error that I cannot solve As soon as I open the project it tells me that I have a problem with the line 4 of the TouchDiffusionExt operator that does not find the Torch module within the project...
@@VJSCHOOL I fixed this error but again, when I click on the "make engine" button, It does not work and a simple "error" appears without any info about it.
@@VJSCHOOL Did you find a solution? I have the same problem... "Invalid Engine; Please ensure the engine was built correctly" I've Nvidia Quadro P4000...
@@alexandraganiari706 Did you find a solution? I have the same problem... "Invalid Engine; Please ensure the engine was built correctly" I've Nvidia Quadro P4000...
Git is installed. Creating .venv directory... The filename, directory name, or volume label syntax is incorrect. Failed to create virtual environment. What is the problem?
I don't understand how it's posssible to have multiple frames per second with 20 steps. Why don't we use TensorRT on normal UI's like Automatic or Comfy ? Sorry in advance for having such a vague question but i find this quite amazing haha.
Real-time can be achieved with Turbo models and Acceleration Lora, on low steps like 1-4 with TensorRT. TouchDesigner allow to copy data from and to GPU, that decrease latency.
excuse me, i follow every step you said, but when i click the webui button, it was going to fail, would you tell me why? here are the flows: Downloading StreamDiffusion... Cloning into 'StreamDiffusion'... remote: Enumerating objects: 2735, done. remote: Counting objects: 100% (1115/1115), done. remote: Compressing objects: 100% (294/294), done. error: RPC failed; curl 92 HTTP/2 stream 5 was not closed cleanly: CANCEL (err 8) error: 7789 bytes of body are still expected fetch-pack: unexpected disconnect while reading sideband packet fatal: early EOF fatal: fetch-pack: invalid index-pack output Failed to download StreamDiffusion
@@VJSCHOOL yeah I got it to run stable diffusion but it was quite slow, and then I couldn’t figure out how to put it in touch designer, I’ll just bite the bullet return this computer and get one with an nvidia videographics card
[W] Model does not contain ONNX domain opset information! Using default opset. UNet: original .. 0 nodes, 0 tensors, 0 inputs, 0 outputs UNet: cleanup .. 0 nodes, 0 tensors, 0 inputs, 0 outputs [I] Folding Constants | Pass 1 [W] Model does not contain ONNX domain opset information! Using default opset. Only support models of onnx opset 7 and above. getting this error, while creating the engine from model, anybody knows the fix?
the webui.bat did not create any folders (venv, streamdiffusion, models, engines) but tells me they already exist after relaunching, what am I doing wrong?
the .venv folder is hidden so make sure you have Show Hidden Folders turned on in Windows Explorer. It didn't create the models/engines directories for me either, I just copied and pasted them manually from the StreamDiffusion folder once it was generated and that did the trick.
amazing job explaining the entire process...
this is great! lean and clean, thank you!
instnaly fast and so nice to be in 512, congrats on this one, cant wait for more features!
Custom resolutions already available, but keep in mind, that it will affect FPS.
@@VJSCHOOL I tried building a model with different res and more steps, but it wouldn't finish...
Super impressed with the speed, it's still super jittery and "stabley", but that's just animdif in general I geuss, excited to try out control net!!
how can i fix the error in TD "name 'StreamDiffusionWrapper' is not defined"plzzzz
same problem in here - already tried the process several times but nothing works
@@Djopy i solved this problem by uninstalling the latest python (3.13) then installed (3.11.1) after that i added path in environment variables. this error is gone, but i have now other new errors
im having the same issue
Thanks for making this free, much love
Hey VJ SCHOOL!thanks for the tutorial. I get to the point where you have to click "Load Engine" pulse button, but then it doesn't do anything. I'm not sure if this helps figure out what's going wrong, but I noticed in your video at 6:26 the "Active engine" variable updates from "none" to "sd-turbo-512-512-1" whereas for me the "active engine" variable stays on "none" no matter how many times i reload or press the pulse button!
i have the same problem
@@vjflame pip3 install numpy==1.23.5
hey i am facing the same issue ? were you able to solve it? Pls let me know
@@vjflame were you able to solve it? pls tell me too i am stuck at same issue
Thanks for this great solution! Amazing performance on 4070 12GB! SD Turbo and 1 sample step. I will test making other engine now. 3 sample steps were slow on 4070.
Increible trabajo bro, saludos desde Costa Rica
The test was successful, very cool...
May I ask when ControlNet will be supported?
Hi, i want to tell if there is some solucion to this, when a press load engine, nothing happens at all, thanks you very much for the sharing this video is great !
Same Problem here
same problem here - anyone can help?
When trying to Re-init I get
- Failed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback): module 'numpy' has no attribute 'dtypes'
And when Trying to click pulse for "Load engine" I get
- name 'StreamDiffusionWrapper' is not defined
maybe that helps...asked gpt and looked through all the issues, just cant seem to fix it
@@Till9R same here
@@lucascattolin6312 same here : D : D funny laught problem. need help, all of us pls
when i hit pulse to refresh the engine nothing happens, engine is missing inside TD but not inside folder "checkpoints". started the pc and TD several times, doesnt help :( what could it be?
the same problem, nothing happens when pressing load engine
@@andresmonrealescolano8579 same thing happening here.
I have the same problem but it used to always work a few days ago, has anyone solved the issue related to pulse engine?
@@federicogentile6363 I am working on it. i will let you know
I think my error is the same - name 'StreamDiffusionWrapper' is not defined
I also have errors: Failed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback):
module 'numpy' has no attribute '_core' and name 'StreamDiffusionWrapper' is not defined
Thank you very much for sharing this video!
Amazing video, what are the steps to have live feedback from the camera, remove background then generate on what's left? Like reacting to someone moving live
you can use TOOP> 'Nvidia Background'
Halo, i have faceing some problem, I dont have LCM option on 4:03, how do i deal with that?
I try it , it shows
Error no module named 'StreamDiffusion'
Error Failed to import diffusers.models.autoencoders.autoencoder_tiny because of the following error (look up to see its traceback)：module 'numpy' has no attribute 'dtypes'
Error Name 'StreamDiffusionWrapper' is no defined
I also had this issue!!!
pip3 install numpy==1.23.5
@@rodrigosimoes3177 I’ll try it thank you
@@rodrigosimoes3177thank you so much🎉 it is working!
Thanks for sharing your knowledge , i appreciate it 🎉
THIS video talks about the portable version and NOT the manual installation. If you try following this installation for the manual installation, you are going to face errors related to models and engines not being found, for example "cannot access local variable 'pipe' where it is not associated with a value", because the paths for the portable version and the manual version are slightly different. That's why I recommend using the portable version
Hi, I've downloaded the portable version when i use the webui.bat, should I still set the python location to my local file? thanks
thank you so much! great tutorial. is it possible to use other kind of
models?
by any chance mps would work? I am on Mac no CUDA is available
Thanks for the great tutorial. How can I add Loras? put lora in lora file and then just name them in the prompt?
Thank you ! I made it work but it just creates the image only when i press load engine button and its a stable image. How can i make it live =?
ehi, i have the same issue.. did u find out how to fix it?
Very interesting, but when I clicked load engine in touchdesigner, I got an error like "cannot access local variable 'pipe' where it is not associated with a value". What is the problem?
That’s mean either model or engine can’t be found
Have you solved it?
@@yanyu813 download portable version on Github and try with it.
@@VJSCHOOL Tried the portable as well as the manual version. Same error. It may be because Runway shut down their SD1.5 repositories on huggingface?
Posted the full log on GitHub Issue.
Thanks!
@@VJSCHOOL Hey! I have a little trouble downloading the portable version since only the first zip file can be opened with 7zip, rest is broken. Is there a way to extract them all?
OSError: [WinError 126] The specified module could not be found. Error loading "C:\Users\PC ABU-ABU\Desktop\TouchDiffusion-main\TouchDiffusion-main\.venv\Lib\site-packages\torch\lib\fbgemm.dll" or one of its dependencies.
No launch file found
please help
Hey! Did u find the answer? I have the same problem
use python 3.10 instead
"Dependencies not installed" how do i solve this problem?
amazing and quick tutorial! DO you know how to fix the stable immage? becasue in my case is not generating new ones.. THANKS!
Hello, I thought the video was excellent, thanks for sharing the info. I'm on the last step, but when I put an image in TD it doesn't generate the video as fluidly as you do, it gets stuck and only broken images appear, and it says "Error- No module named "steamDiffusion" what can I do?
I am also facing this issue
Hi, I have the same problem
pip3 install numpy==1.23.5
@@davidec5722 pip3 install numpy==1.23.5
load engine but nothing happens
log
name 'StreamDiffusionWrapper' is not defined
pip3 install numpy==1.23.5
@@rodrigosimoes3177 thanks ! it works :)
But we have a incompatibility issue (still the generation is working)
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
onnxruntime 1.16.3 requires numpy>=1.24.2, but you have numpy 1.23.5 which is incompatible.
Nevertheless I got finished engine preparation and selected the file which webui includes, it doesnt work.. I tried to press load engine and refresh engine several times, but it dosent work.. how to resolve this :(
dont we need cuDNN and ternsorRT? if yes, which versions of each do we need?
does this work with MacOS Silicone?
I was wondering the same thing...
I was able to run streamdiffusion by it self, works great
Okay. So basically this utilizes a tensorrt engine to render in Touchdesinger. This needs an Nvidia card so no for a mac.
hi ,i have followed your tutorial and every step went well .But in TouchDesigner,the log shows :cannot access local variable 'pipe' where it is not associated with a value.I don't know how did it happened
Create issue on GitHub or Discord with full log
hi, i followed every step and there are no erros, but in touchdesigner when i hit pulse on "load engine" nothing happens, can anybody help me?
Create issue on GitHub or Discord and share full log.
Did you find the solution? Same issue
I keep getting an error when i want to create the engine. Any one know what NameError: name 'StreamDiffusionWrapper' is not defined means?
use python 3.10 instead
pip3 install numpy==1.23.5
@@rodrigosimoes3177 what does this mean
why it is showing error in null
Hellllooooo, I just arrive untill 4:05 and this happen : NameError: name 'StreamDiffusionWrapper' is not defined
Any idea how to fix this ?
There is portable version on GitHub, better to try with it
@@VJSCHOOL pip3 install numpy==1.23.5
pip3 install numpy==1.23.5
Hi! Thnaks for the video Oleg, I just have one problem at the end of the whole porcess, in TD when I select the touchdiffusion main folder it seem like it dont read the location, I restart the program and pc, but the error keep there, :( what could it be? anyone knows? thnks!!!
I don't see the radio button option (LCM) under "Add Acceleration Lora". There's only one option and it's "none".
Git is installed.
Creating .venv directory...
Failed to create virtual environment. help!! asap
you need to search for python location yourself, the command where python is broken smh
i have windows 10 so i will install cudas 10 version right ?
amazing fast speeds would you know why using my null of the render tops of my td projects as input isnt working? im getting flashing white and black with some cat images but noise top works normally, denoising value dosent change this would we have to repeat the webui model proceses with higher steps seems like it could be that or a different problem if so how should i do that thanks!
seems the same problem with a default moveifileintop
I figured out I had to reinitalize pulse touchddiffusion folder and possibly clear log too I did both then reload engine
Cool! Can it work with controlnet?
No support for now
What's the difference between this and streamdiffusion?
Explained in first 3 min of video
It’s near x2 faster
Can I use Lora module to make a engine?😢
pip3 install numpy==1.23.5
does it have to be python 311? i have 310 and i don't wanna break all my other installations to try this...
1) everything installed in venv, so it not affecting main Python env.
2) if you want to try with Python 3.10, then provide path to it in webui & use TouchDesigner version before 2023
Hello, first of all congratulations on the tremendous work
I have been using the DSD patch for a long time without any problems, but now I have a constant error that I cannot solve
As soon as I open the project it tells me that I have a problem with the line 4 of the TouchDiffusionExt operator that does not find the Torch module within the project...
Hi, it's because you have two folders with the same name "TouchDiffusion-main" .. at least that's what happened to me when I unzipped.
where i prerating models?
I have tried it.. but say try experimenting with my video camera will it not work?
I get this error "Error installing packages: torch==2.1.0, Failed to install TensorRT" during the installation process. Any ideas how to fix this?
Try with portable version
@@VJSCHOOL I fixed this error but again, when I click on the "make engine" button, It does not work and a simple "error" appears without any info about it.
@@VJSCHOOL Did you find a solution? I have the same problem... "Invalid Engine; Please ensure the engine was built correctly"
I've Nvidia Quadro P4000...
@@alexandraganiari706 Did you find a solution? I have the same problem... "Invalid Engine; Please ensure the engine was built correctly"
I've Nvidia Quadro P4000...
Git is installed.
Creating .venv directory...
The filename, directory name, or volume label syntax is incorrect.
Failed to create virtual environment.
What is the problem?
chech where the python with "where python" command and copy paste in to webui.bat like he said
you need to install python first; if you don't have it - it won't be able to create virtual environment
thats amazing but i got an ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (tensorrt) please help!
"No module named 'tensorrt'"
I don't understand how it's posssible to have multiple frames per second with 20 steps. Why don't we use TensorRT on normal UI's like Automatic or Comfy ? Sorry in advance for having such a vague question but i find this quite amazing haha.
Real-time can be achieved with Turbo models and Acceleration Lora, on low steps like 1-4 with TensorRT. TouchDesigner allow to copy data from and to GPU, that decrease latency.
its posible with 8gvram?
Amazing
I am getting an error: name 'StreamDiffusionWrapper' is not defined. Any ideas?
same over here :( did you solve it?
Try portable version
any progress with portable version? I can not download it
amazing... this is realy faster,
can we put lora and vae to the folder?
what lora and vae for the best creation
and why icant change the seed ?
Tiny VAE already baked in for best performance. Loras not supported yet.
Seed can be changed in TouchDesigner with seed parameter
any chance for different models to load like SDXL or SD 3.5?
when i press pulse nothing happens
pip3 install numpy==1.23.5
Thanks bro
Hi! Does it also work with Mac?
Only NVIDIA GPU
UnboundLocalError: cannot access local variable 'pipe' where it is not associated with a value helllp!!!!!
I really need a computer to do this. is there a way I could offload that GPU onto Google Collab?
TouchDiffusion component required TouchDesigner, so it can’t run in Google Collab. You can try with original StreamDiffusion repo.
@@VJSCHOOL - Sigh guess i just need better hardware.
@@VJSCHOOLsweet I’ll try that
@@VJSCHOOL I got a new computer with a 3060 Ti =D
HOW MUCH FPS YOU GET MY FRIEND
As I understand it, this miracle cannot be run under Mac?
Only PC & Windows
excuse me, i follow every step you said, but when i click the webui button, it was going to fail, would you tell me why?
here are the flows:
Downloading StreamDiffusion...
Cloning into 'StreamDiffusion'...
remote: Enumerating objects: 2735, done.
remote: Counting objects: 100% (1115/1115), done.
remote: Compressing objects: 100% (294/294), done.
error: RPC failed; curl 92 HTTP/2 stream 5 was not closed cleanly: CANCEL (err 8)
error: 7789 bytes of body are still expected
fetch-pack: unexpected disconnect while reading sideband packet
fatal: early EOF
fatal: fetch-pack: invalid index-pack output
Failed to download StreamDiffusion
How to increase CFG to 7-10 instead of 1?
The quality of generations is very low at 1.
You should try to increase sampling steps (batch size)
Can you do this with AMD Ryzen Somehow?
For now there is no way
@@VJSCHOOL yeah I got it to run stable diffusion but it was quite slow, and then I couldn’t figure out how to put it in touch designer, I’ll just bite the bullet return this computer and get one with an nvidia videographics card
@@SwoleKitchen yep 😄
I got this error when i click on Make Engine "UnboundLocalError: cannot access local variable 'pipe' where it is not associated with a value"
same here. Were you able to solve it?
@@joaopedrofireman8180 Yes i have installed the portable version without any error
[W] Model does not contain ONNX domain opset information! Using default opset.
UNet: original .. 0 nodes, 0 tensors, 0 inputs, 0 outputs
UNet: cleanup .. 0 nodes, 0 tensors, 0 inputs, 0 outputs
[I] Folding Constants | Pass 1
[W] Model does not contain ONNX domain opset information! Using default opset.
Only support models of onnx opset 7 and above.
getting this error, while creating the engine from model, anybody knows the fix?
how about mac~ pls❤
Only NVIDIA GPU
Has anyone got this to work recently?
норм
anybody test 4080 laptop fps?
4070 Laptop - 24 FPS with SD Turbo 512x512
Value: 'LCM' (type: ) is not in the list of choices: ['None'] helllp
Faster than stream diffusion?
the webui.bat did not create any folders (venv, streamdiffusion, models, engines) but tells me they already exist after relaunching, what am I doing wrong?
the .venv folder is hidden so make sure you have Show Hidden Folders turned on in Windows Explorer. It didn't create the models/engines directories for me either, I just copied and pasted them manually from the StreamDiffusion folder once it was generated and that did the trick.