Text-to-Image-Generation

In this project, we are Generate the Images from Text Description using the Stack GANs(SGANs).
And also we are using the pytorch framework for this project
Stacked Generative Adversarial Networks To generate high-resolution images with photo-realistic details
It decomposes the text-to-image generative process into two stages:
Stage-I GAN: it sketches the primitive shape and ba-sic colors of the object conditioned on the given textdescription, and draws the background layout from arandom noise vector, yielding a low-resolution image.
Stage-II GAN: it corrects defects in the low-resolutionimage from Stage-I and completes details of the objectby reading the text description again, producing a high-resolution photo-realistic image.

Basic of Stacked Generative Adversarial Networks (SGAN)

https://arxiv.org/abs/1612.04357
https://medium.com/@jonathan_hui/gan-stacked-generative-adversarial-networks-sgan-d9449ac63db8

Architecture of Text-to-Image Generation