New Worlds

Do you want to create your own worlds in the Metaverse?

Then look no further. All you need is your Google profile so you can access all of their free tools.

Just follow the instructions below and start spreading your virus!

Instructions

Click on this item, below, to open the Colab file.

Make a copy of the file in your own drive.

Press the play icon to run the cell and remember to take note of the prompts and instructions.

How to run PyTorch with GPU and CUDA 9.2 support on Google Colab.

PyTorch3d

You don't need to download a special application to use this AI. PyTorch3D is a library for deep learning, with 3D data, that Python can import.

RAM : A minimum of 16 GB RAM is required. You can also get on with a 8GB ram, but it has it’s own complications.

GPU : CUDA is compatible with almost all the models from 2006 but a minimum of GTX 1050ti, 1060 and above are required.

SSD or HDD : A SSD with at least 256GB is required for faster processing. The 128GB SSD falls short of space after the installation of the software.

Next Step

Before you start, check that your Runtime is set to GPU ('Ctrl+M' is the keyboard shortcut). Otherwise your program will probably crash. Remember to use the free resource fairly and not to run a free session for over 12 hours.

Another Step

Since some dependencies must be compiled from source code, it will take quite a while to complete, so it might be time to go make a cup of coffee.

Another Step

You will need a video in your drive folder, but make sure its a short clip. If you don't have your own clip then find and download one from the internet. Make sure you take a note of it's aspect ratio (width and height), because this has to match in the next step.

Another Step

If you don't have a subscription to Colab Pro, then it's best to use the lowest resolution on a very short clip. If this crashes (and it will) remember to go back to your drive (previous step) and delete the new, corrupted, video file that it's attempted to create. When it works, come back to this step later, change the output name and use one of the other 4 algorithms and experiment.

Last Step

In this final step your 'input_Filename' is the 'output_Filename' of the last step, so you will need a new 'output_Filename' here. Now you can go back to your drive and view/download the video you've just created.