Missing modules and unable to launch locally

[Aspecky]

I am trying to run the app locally with the provided script: https://github.com/nateraw/stable-diffusion-videos#run-the-app-locally

Upon running the code, i get missing torch, torchvision and cv2 (opencv-python), then when i install them i get told to install realesrgan, finally after installing it, i receive an assertion error saying Torch not compiled with CUDA enabled

I used to be able to run the app when the script was

from stable_diffusion_videos import interface
interface.launch()

[nateraw]

There are new directions to run the app in the readme, and the colab is updated as well.

[nateraw]

The torch/cv2 issues you mention are unrelated to any changes here

[Aspecky]

There are new directions to run the app in the readme, and the colab is updated as well.

I followed the steps as instructed but i still get the same issue. Here's what I do, I am on windows and my python version is 3.10.8:

python -m venv venv
venv\Scripts\activate.bat
pip install stable_diffusion_videos
huggingface-cli login

in the same dir i create a file called launch.py with the following code:

from stable_diffusion_videos import StableDiffusionWalkPipeline
import torch

pipeline = StableDiffusionWalkPipeline.from_pretrained(
    "CompVis/stable-diffusion-v1-4",
    torch_dtype=torch.float16,
    revision="fp16",
).to("cuda")

interface = Interface(pipeline)
interface.launch()

and then I run it using python launch.py which leads to the errors mentioned in the post.

Apologies if I am doing something wrong that's painfully obvious, I followed the provided instructions and that's what they led me to. It worked a week ago following the same steps before the readme changed.

[Aspecky]

Maybe the stable_diffusion_videos pip package didnt get updated?

Here's what pip freeze lists after running pip stable_diffusion_videos in a venv:

certifi==2022.9.24
charset-normalizer==2.1.1
colorama==0.4.5
filelock==3.8.0
huggingface-hub==0.10.1
idna==3.4
packaging==21.3
pyparsing==3.0.9
PyYAML==6.0
requests==2.28.1
tqdm==4.64.1
typing_extensions==4.4.0
urllib3==1.26.12

[screan]

I am trying to run the app locally with the provided script: https://github.com/nateraw/stable-diffusion-videos#run-the-app-locally

Upon running the code, i get missing torch, torchvision and cv2 (opencv-python), then when i install them i get told to install realesrgan, finally after installing it, i receive an assertion error saying Torch not compiled with CUDA enabled

I used to be able to run the app when the script was

from stable_diffusion_videos import interface
interface.launch()

I am getting the same issue.

my cuda: Cuda compilation tools, release 11.8, V11.8.89 Build cuda_11.8.r11.8/compiler.31833905_0

[Sejf]

Try installing opencv as sudo sudo pip install opencv-python