StreamDiffusionTD 0.2.99🚀🖼️

Process Process-3: Traceback (most recent call last): File "C:\Users\ALIENWARE\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\process.py", line 314, in _bootstrap self.run() File "C:\Users\ALIENWARE\AppData\Local\Programs\Python\Python311\Lib\multiprocessing\process.py", line 108, in run self._target(*self._args, **self._kwargs) File "D:\aigc\StreamDiffusion-main\streamdiffusionTD\main_sdtd.py", line 350, in image_generation_process stream = StreamDiffusionWrapper( ^^^^^^^^^^^^^^^^^^^^^^^ File "D:\aigc\StreamDiffusion-main\streamdiffusionTD\wrapper_td.py", line 223, in __init__ self.stream: StreamDiffusion = self._load_model( ^^^^^^^^^^^^^^^^^ File "D:\aigc\StreamDiffusion-main\streamdiffusionTD\wrapper_td.py", line 562, in _load_model original_config_path = get_sd_model_config(config_type) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "D:\aigc\StreamDiffusion-main\streamdiffusionTD\wrapper_td.py", line 554, in get_sd_model_config raise Exception(f"Failed to download config for {key}") Exception: Failed to download config for sd21 出现这样的问题该如何解决呢

Hi, I’m using version 0.2.99 It works very well on both my Pc in the studio that uses rtx 3080 Ti and 4070. Im currently preparing a show to open next week and I’m getting this error on 2 brand new pc with rtx5060 : Exception : Failed to download config for sd21. I’ve ré-installed with cuda 12.8 Nothing has changed. Please help I’ve been struggling for 4 days now

i tried cuda 11.8 python 3.10.9, always the same error, don't know, why it doesn't work for me. i m on win 11

I'm getting this error after the first execution of StableDissusion: "======================================= Using TensorRT... ERROR: cannot import name 'cudart' from 'cuda' (unknown location)... ERROR: Failed to load TensorRT due to an unexpected error. This feature is Windows only ( I have Windows ) . Check the installation and restart the Stream." Anyone has the same problem? I have followed all the instructions about installation. I Also checked on HQImmersiveInteractive platform that i have but there is nothing about it I'm on python 3.11.9 and cuda 11.8

Some problem...Daydream 400 in v0.2.99.. (Failed to create stream (HTTP 400)

hello there, first of all many thanks for you contribution to TD community, I'm a huge fan. any idea if is possible to run this using a AMD GPU?

Have a trouble. streaming is active but in TD Server Connected, Not Streaming

Hello! Will you support streamdiffusion V2?

Hi, I'm trying to install this on mac and keep failing , any full tutorial for mac?

Hi Dot, it works nice, but trying to use tensor I have this error, I install all the exact libriaries: ERROR: cannot import name 'cudart' from 'cuda' (unknown location)... ERROR: Failed to load TensorRT due to an unexpected error. This feature is Windows only. Check the installation and restart the Stream.

Awesome stuff, great work, thanks! I was wondering how to input negative prompts for example to prevent logos and text from showing.

Thanks so much!

Got it working on both my RTX 5080 desktop and my 5070 Razer Blade 14. You need to install CUDA 12.8 for 5xxx GPUs. Works with a custom LoRA I made as well. Looking forward to the Tensor RT enabled version. Thank you!

Cannot get it working on rtx 5090: it says RuntimeError: operator torchvision::nms does not exist

I got a new desktop with a 5080 card. One thing I'm noticing while installing is that there wasn't any pop up command line style activity. Like the one demonstrated in your instructions video. Having said that I am getting the check mark next to step 1 and step 2. Not step 3. When I click start stream, it just says base folder updated and nothing happens. No errors. I followed all the instructions posted on Discord to get this running properly on 50XX series cards but it's still not working for me. Using the 12.8 CUDA, python 3.11.9. Even did the cudnn 8.x install. Can you let me know why I'm not getting those pop ups when clicking the install buttons in the operator? This might help with a fix for me. Thanks!

First of all, congratulations on a very successful project. I installed it without any problems, thank you. I have a question. I don't know how to change the 9x16 format or the frame sizes. I've been using the software for 15 days, and although I don't know how to use it, I'm just doing it as a hobby. I'm working on real-time camera footage, but I'm curious how I can adjust the frame sizes. Is it possible? I'm wondering what I need to do, and I also couldn't connect the txt box. Thank you in advance for everything.

Hi, thanks for creating the tox. I am using it with a 5080, Cuda 12.8 and Python 3.11.9. While installing I get the error message "Could not find a version that satisfies the requirement xformers". xformers is required for V2V to work with the 5080, or? Is there a fix for this or is this not supported? Thank you Best Tim

Hey, new user here, just signed up and downloaded the .tox, clicked through to the installation guide on your website and the mouse animation gave me motion sickness within seconds. It's not something I'm usually sensitive to. Is there an easy way to switch it off that I missed? I found the gradient toggle but that doesn't help.

Hey Dot! thank you for everything you do for the TD community! Could you please point me in the right direction on how to troubleshoot this? "no module named 'torch.distributed.device_mesh" I have installend and updated everything, cuda, pip, pytorch etc. Is there a forum where i can discuss this? Thank you x

Hello Lyel, i have recently problems with the previous version of the plugin. It stopped working for me from yesterday and crashing my computer completely (black screen and nothing). Is there a chance that you made the older version obsolete? I am just trying to track the source of the problem. Does everyone has to switch to the new version or can use the old version? My whole art performance is dependent on it and it is today actually… Don’t know what to do. Please advise me as soon as you can. Thank you

Hello Dot, incredible as always — you’re such a great creator!! And as a creator myself, I’m proud to have subscribed to you… you truly deserve this support!! Tell me, how could I contact you in private? Can I leave you my professional email address? I know your schedule is very busy, but I would really need your help on a project.