# Text2FaceGAN: Face Generation from Fine Grained Textual Descriptions

arXiv: https://arxiv.org/abs/1911.11378 · HTML: https://mlsanity.com/paper/1911.11378/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Nov 2019.

## Built on by (most cited first, 9 of 9)

- [ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving](https://mlsanity.com/paper/2404.16771/) (2024)
- [AnyFace: Free-style Text-to-Face Synthesis and Manipulation](https://mlsanity.com/paper/2203.15334/) (2022)
- [Towards High-Fidelity Text-Guided 3D Face Generation and Manipulation Using only Images](https://mlsanity.com/paper/2308.16758/) (2023)
- [MM2Latent: Text-to-facial image generation and editing in GANs with multimodal assistance](https://mlsanity.com/paper/2409.11010/) (2024)
- [Remember What You have drawn: Semantic Image Manipulation with Memory](https://mlsanity.com/paper/2107.12579/) (2021)
- [Text-to-Face Generation with StyleGAN2](https://mlsanity.com/paper/2205.12512/) (2022)
- [cycle text2face: cycle text-to-face gan via transformers](https://mlsanity.com/paper/2206.04503/) (2022)
- [Face Generation from Textual Features using Conditionally Trained Inputs to Generative Adversarial Networks](https://mlsanity.com/paper/2301.09123/) (2023)
- [Disentangling 3D from Large Vision-Language Models for Controlled Portrait Generation](https://mlsanity.com/paper/2506.14015/) (2025)

## Abstract (arXiv)

Powerful generative adversarial networks (GAN) have been developed to automatically synthesize realistic images from text. However, most existing tasks are limited to generating simple images such as flowers from captions. In this work, we extend this problem to the less addressed domain of face generation from fine-grained textual descriptions of face, e.g., "A person has curly hair, oval face, and mustache". We are motivated by the potential of automated face generation to impact and assist critical tasks such as criminal face reconstruction. Since current datasets for the task are either very small or do not contain captions, we generate captions for images in the CelebA dataset by creating an algorithm to automatically convert a list of attributes to a set of captions. We then model the highly multi-modal problem of text to face generation as learning the conditional distribution of faces (conditioned on text) in same latent space. We utilize the current state-of-the-art GAN (DC-GAN with GAN-CLS loss) for learning conditional multi-modality. The presence of more fine-grained details and variable length of the captions makes the problem easier for a user but more difficult to handle compared to the other text-to-image tasks. We flipped the labels for real and fake images and added noise in discriminator. Generated images for diverse textual descriptions show promising results. In the end, we show how the widely used inceptions score is not a good metric to evaluate the performance of generative models used for synthesizing faces from text.