Transforming text into faces using GANs and deep learning.
D2F (Description to Face) is an AI research project where I developed a Generative Adversarial Network (GAN) model that generates hyper-realistic facial images based solely on descriptive text inputs. I led the entire pipeline: from NLP preprocessing and dataset curation to GAN architecture tuning and model training. The project achieved an impressive FID score of 98.45 and was published on SSRN.