https://github.com/faezeh-gholamrezaie/text-to-face-

A Novel Encoder-Decoder Approach for Text-to-Face Conversion using Generative Adversarial Networks and Attention Mechanism
https://github.com/faezeh-gholamrezaie/text-to-face-

celeba gan pytorch sentence-transformers text-to-face text-to-image text2image transformer

Last synced: 3 months ago
JSON representation

A Novel Encoder-Decoder Approach for Text-to-Face Conversion using Generative Adversarial Networks and Attention Mechanism

• Host: GitHub
• URL: https://github.com/faezeh-gholamrezaie/text-to-face-
• Owner: faezeh-gholamrezaie
• Created: 2024-01-26T11:48:39.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-07-16T09:26:55.000Z (7 months ago)
• Last Synced: 2024-07-16T12:00:04.350Z (7 months ago)
• Topics: celeba, gan, pytorch, sentence-transformers, text-to-face, text-to-image, text2image, transformer
• Language: Python
• Homepage:
• Size: 295 KB
• Stars: 2
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Text to Face

A Novel Encoder-Decoder Approach for Text-to-Face Conversion using Generative Adversarial Networks and Attention Mechanism

This repository contains a TensorFlow implementation for generating face images using the GAN-CLS Algorithm, as described in the paper [Generative Adversarial Text-to-Image Synthesis][1](https://proceedings.mlr.press/v48/reed16.html). The model is built upon the solid foundation of the [DCGAN in TensorFlow][2](https://github.com/tensorlayer/DCGAN).

With the ability to handle input descriptions in over 100 languages, this implementation is highly versatile and adaptable. This means you can generate face images based on textual descriptions in various languages.

To train and evaluate the model, we utilize the large-scale CelebFaces Attributes (CelebA) dataset, which provides a diverse set of realistic human faces.







Image Source : [https://s3-us-west-1.amazonaws.com/udacity-dlnfd/datasets/celeba.zip]


Caption source : [https://raw.githubusercontent.com/midas-research/text2facegan/master/data/caps.txt]

## Results

-The man sports a 5 o’clock shadow.He has big nose.The young attractive man is smiling.







##text-to-face evaluation (human evaluation) : 

[Text2FaceGAN][3](https://ieeexplore.ieee.org/abstract/document/8919389).







## text-to-face evaluation (Frechet Inception Distance (FID)) :

|      Model     |      FID   |

| -------------- | ---------- |

| Cycle Text2Face| 1.20±0.081 |

| Text2FaceGan   | 1.4±0.7    |

# References

Article cycle text2face: cycle text-to-face gan via transformers : [https://arxiv.org/abs/2206.04503]