Generative Adversarial Text to Image Synthesis / Please Star -->
Switch branches/tags
Nothing to show
Clone or download
zsdonghao Merge pull request #12 from arisliang/master
refactoring and folder fix.
Latest commit 275880d Mar 18, 2018
Failed to load latest commit information.
tensorlayer [release] TF1.0 Apr 11, 2017
.gitignore nothing Jun 5, 2017 Create Jun 8, 2017 fix folder. #13 Mar 18, 2018 add download script Jun 8, 2017 inception score Jan 31, 2017 release for TF1.2 Jun 18, 2017
result.png nothing Jun 5, 2017 minor refactoring Mar 18, 2018 [release] TF1.0 Apr 11, 2017

Text To Image Synthesis

This is an experimental tensorflow implementation of synthesizing images. The images are synthesized using the GAN-CLS Algorithm from the paper Generative Adversarial Text-to-Image Synthesis. This implementation is built on top of the excellent DCGAN in Tensorflow.

Model architecture

Image Source : Generative Adversarial Text-to-Image Synthesis Paper



  • The model is currently trained on the flowers dataset. Download the images from here and save them in 102flowers/102flowers/*.jpg. Also download the captions from this link. Extract the archive, copy the text_c10 folder and paste it in 102flowers/text_c10/class_*.

N.B You can downloads all data files needed manually or simply run the and put the correct files to the right directories.



  • download Oxford-102 flower dataset and caption files(run this first).
  • load data for further processing.
  • train a text to image model.
  • helper functions.
  • models.



  • the flower shown has yellow anther red pistil and bright red petals.
  • this flower has petals that are yellow, white and purple and has dark lines
  • the petals on this flower are white with a yellow center
  • this flower has a lot of small round pink petals.
  • this flower is orange in color, and has petals that are ruffled and rounded.
  • the flower has yellow petals and the center of it is brown
  • this flower has petals that are blue and white.
  • these white flowers have petals that start off white in color and end in a white towards the tips.


Apache 2.0