Artificial Animation, or "ARTI," came to be in 2022. But we’ve worked with A.I. tools since 2019 when NVIDIA came out with their GauGAN. It was a simple but mind-boggling tool at the time that allowed people to paint landscapes. As students at the University of Southern California, we used GauGAN to make our school’s first A.I. animation. When COVID hit, our curiosity about machine tools grew, and we began our journey. Since then, we’ve worked to heighten the quality of A.I.-supported projects to redefine what “A.I. art” means.
We use new and developing tools to drive novel forms of storytelling. We experimented with face swapping, voice cloning, neural radiance fields (3D landscapes), facial augmentation, body morphs, motion capture, style transfers, machine music, generative imagery/video, text-to-image, text-to-video, and countless different combinations. There’s a lot out there and the list is growing every day. But a few years ago, A.I. was a tough hobby to start. Most machines weren’t strong enough and consumer services like ML Runway weren’t around. So we adapted these tools for Google Colab—a cloud computing site—only to discover people have already done so. There was a mountain of open-source A.I. tools put together by a community and made available for free.
Honoring that, ARTI ensures the use of ethically sourced A.I. models. Our goal is to only use A.I. to aid our process, never to replace artists.
This path led us to work with machine learning tools to combine live-action and animation. Our unique approach reimagines animation by sampling imagery from live footage and transforming it with the help of A.I. ARTI intends to use human work, in collaboration with machines, to imitate nature. We're excited to share our work and process with you.
- Kai Tattersall, Founder
Artificial Animation