Text to image generation using BERT and GAN

Generating text to images is a difficult task that combines natural language processing and computer vision. Currently available generative adversarial network (GAN)-based models usually employ text encoders that have already been trained on image-text pairs. Nevertheless, these encoders frequently fall short in capturing the semantic complexity of unread text during pre-training, which makes it challenging to produce images that accurately correspond with the written descriptions supplied.Using BERT, a very successful pre-trained language model in natural language processing, we present a novel text-to-image generating model in order to address this problem. BERT's aptitude for picture generating tasks is improved by allowing it to encode rich textual information through fine-tuning on a large text corpus. Results from experiments on a CUB_200_2011 dataset show that our approach performs better than baseline models in both qualitative and quantitative measures.