FaceSwap Artist - all levels - London Studio

募集内容

Job Summary:

Position Summary

FaceSwap is a new, exciting, and growing discipline within the visual effects industry, using Machine Learning (AI) to create digital faces and likenesses. We are currently looking for people with a keen eye for, and interest in, photo realism, as well as those comfortable with the technical side of visual effects. The FaceSwap Artist will be a pioneer and trailblazer in a new area of visual effects technology. While a background in compositing is advantageous, artists with visual effects experience in any discipline are encouraged to apply.

What You’ll Do

Use a variety of deep learning based technologies to produce photorealistic images, including open source tools, and proprietary in house software

Create templates to facilitate model evaluation

Monitor the training progress, and assess improvements and quality; making necessary adjustments to the configuration of training

Prepare datasets to train models, which includes gathering reference material from various sources, curating and managing images

Using trained models to perform faceswaps in a shot context, producing slap comps for review in dailies.

What We’re Looking For

Experience in visual effects or CG industry

A curious mind that is interested in learning new things, and enjoys experimentation and testing

Flexible and adaptable to changing workflows, detail oriented and meticulous

Working knowledge of Nuke to prepare precomps and slap comps

Some experience with CG compositing

Comfortable working with or learning command-line based tools

Interested in, or have basic familiarity with, deep neural networks

Familiarity with ComfyUI and other GenAI tools

Nice to have

Experience working on projects with realistic looking CGI humans or other face replacement approaches

Any experience using or training deep neural networks models, such as Nuke Copycat, DeepFaceLab or other face swapping tools

Experience with Keen Tools

Python scripting skills to automate and streamline high volume of repeated day-to-day tasks