azadlab/FExGAN-Meta
Demo of the research work.
This tool helps 3D artists, animators, and game developers automatically generate a range of realistic facial expressions for their "Meta-Human" digital characters. You provide an image of a Meta-Human and specify an emotion like 'angry' or 'joy', and it produces an image of that character with the desired expression, preserving their unique identity. It's for anyone working with digital avatars who needs to quickly create specific emotional states.
No commits in the last 6 months.
Use this if you need to generate specific emotional expressions for your Meta-Human digital characters without manually modeling each one.
Not ideal if you are working with real human images or non-Meta-Human 3D models, as it's specifically designed for Meta-Human inputs.
Stars
7
Forks
3
Language
Jupyter Notebook
License
—
Category
Last pushed
Jul 19, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/azadlab/FExGAN-Meta"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
huggingface/pytorch-pretrained-BigGAN
🦋A PyTorch implementation of BigGAN with pretrained weights and conversion scripts.
torchgan/torchgan
Research Framework for easy and efficient training of GANs based on Pytorch
metal3d/keras-video-generators
Keras generators to generate sequences from videos as input
GANs-in-Action/gans-in-action
Companion repository to GANs in Action: Deep learning with Generative Adversarial Networks
junyanz/pytorch-CycleGAN-and-pix2pix
Image-to-Image Translation in PyTorch