Ai-Benchmark

Benchmark script for running different ai models from the Livepeer AI Runner repo

The script runs 22 Benchmarks over 6 different models

sd-turbo
sdxl-turbo
stable-diffusion-v1-5
openjourney-v4
stable-diffusion-xl-base-1.0
stable-video-diffusion-img2vid-xt

(10 text to image, 10 image to image, 2 image to video)

Supported Systems

Windows
Linux
Nvidia GPUs only

Dependancies

Please make sure you have Docker installed and running before starting the Benchmark
You will need Nvidia Driver 535 or greater
For Linux - You may need the Nvidia Container Toolkit with the experimental packages enabled to detect the GPUs properly.

ℹ️ Note: This will download approx 36GB disk space for the models and 10GB for the docker image.

Download from releases and run

Download here

Results

Feel free to add your results to the Spreadsheet.

Or send a copy of your results.txt to my Discord and I can upload them.

Linux Install Commands

sudo apt update

sudo apt upgrade

sudo apt install docker.io

sudo apt install nvidia-driver-535

sudo curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
  && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
    sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
    sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list

sudo sed -i -e '/experimental/ s/^#//g' /etc/apt/sources.list.d/nvidia-container-toolkit.list

sudo apt update

sudo apt install -y nvidia-container-toolkit

sudo nvidia-ctk runtime configure --runtime=docker

sudo systemctl restart docker

rickstaa / ai-benchmark