Text-to-image generation based on AttnDM-GAN and DMAttn-GAN: applications and challenges

Razan Bayoumi, Marco Alfonse, Mohamed Roushdy, Abdel-Badeeh M. Salem


The deep fake faces generation using generative adversarial networks (GANs) has reached an incredible level of realism where people can’t differentiate the real from the fake. Text-to-face is a very challenging task compared to other text-to-image syntheses because of the detailed, precise, and complex nature of the human faces in addition to the textual description details. Providing an accurate realistic text-to-image model can be useful for many applications such as criminal identification where the model will be acting as the forensic artist. This paper presents text-to-image generation based on attention dynamic memory (AttnDM-GAN) and dynamic memory attention (DMAttn-GAN) that are applied to different datasets with an analysis that shows the different complexity of different datasets’ categories, the quality of the datasets, and their effect on the results of the resolution and consistency of the generated images.


Computer vision; Conditional image synthesis; Generative adversarial networks; Image generation; Text-to-face

Full Text:


DOI: https://doi.org/10.11591/eei.v12i2.4199


  • There are currently no refbacks.

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Bulletin of EEI Stats

Bulletin of Electrical Engineering and Informatics (BEEI)
ISSN: 2089-3191, e-ISSN: 2302-9285
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).