In the realm of text-to-image synthesis, generating realistic human faces from textual descriptions using Generative Adversarial Networks (GANs) poses significant challenges such as complex designs, reliance on additional networks for semanticalignment, and high computational costs. Our approach employed a Deep Con-volutional GAN (DC-GAN) framework, utilizing the CelebA dataset to enhance training, and incorporated a CNN-RNN model to align textual descriptions with facial features.
“ImaginFace” is the human face generation from textual description project, using DC-GAN and DF-GAN on CelebA Dataset which focuses on utilizing GANs to create a range of human faces through training, on extensive datasets of actual human faces. Applied Django Framework to create User Interface and deploy the model in it.
