# cycle text2face: cycle text-to-face gan via transformers

arXiv: https://arxiv.org/abs/2206.04503 · HTML: https://mlsanity.com/paper/2206.04503/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 9 Jun 2022.

## Builds on (most cited first, 12 of 12)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1612.03242/) (2016)
- [StackGAN++: Realistic Image Synthesis with Stacked Generative Adversarial Networks](https://mlsanity.com/paper/1710.10916/) (2017)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [An efficient framework for learning sentence representations](https://mlsanity.com/paper/1803.02893/) (2018)
- [Attribute2Image: Conditional Image Generation from Visual Attributes](https://mlsanity.com/paper/1512.00570/) (2015)
- [Text2FaceGAN: Face Generation from Fine Grained Textual Descriptions](https://mlsanity.com/paper/1911.11378/) (2019)
- [Cycle Text-To-Image GAN with BERT](https://mlsanity.com/paper/2003.12137/) (2020)

## Abstract (arXiv)

Text-to-face is a subset of text-to-image that require more complex architecture due to their more detailed production. In this paper, we present an encoder-decoder model called Cycle Text2Face. Cycle Text2Face is a new initiative in the encoder part, it uses a sentence transformer and GAN to generate the image described by the text. The Cycle is completed by reproducing the text of the face in the decoder part of the model. Evaluating the model using the CelebA dataset, leads to better results than previous GAN-based models. In measuring the quality of the generate face, in addition to satisfying the human audience, we obtain an FID score of 3.458. This model, with high-speed processing, provides quality face images in the short time.