[CVPR2020] Adversarial Latent Autoencoders

A large-scale face dataset for face parsing, recognition, generation and editing.

A face recognition solution on mobile device.

[ECCV 2024 Oral 🔥] Arc2Face: A Foundation Model for ID-Consistent Human Faces ------------------------ [ICCVW 2025] ID-Consistent, Precise Expression Generation with Blendshape-Guided Diffusion

[ECCV 2018] ReenactGAN: Learning to Reenact Faces via Boundary Transfer

[CVPR 2023] Collaborative Diffusion

TF implementation of our ECCV 2018 paper: Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model

This is the accompanying code for the Medium article: https://medium.com/@karol_majek/high-resolution-face2face-with-pix2pix-1024x1024-37b90c1ca7e8

Simple deepfake pet-project

This is the official implementation of "Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors", which is accepted at ICLR2025.

Generate Random Faces which do not exists. I trained a Deep Convolution GAN (DCGAN) on 100k celebrities photos.

MaskGAN, face parsing, recognition, generation and editing. + train code

face generating DCGAN implemented by Keras

[CVPR 2023 Highlight] StyleGene: Crossover and Mutation of Region-level Facial Genes for Kinship Face Synthesis

Experimental repository attempting to project facial landmarks into the StyleGAN2 latent space.

[CVPR '23] Unite and Conquer: Plug & Play Multi-Modal Synthesis using Diffusion Models

Face Generation using Generative Adversarial Networks

StarGAN - tensorflow implementation

A controllable generative model using a Convolutional Variational Autoencoder (VAE) with GUI to generate faces with desirable features.

An AI model that removes facial masks.