Baaz-v1

About Model

Baaz is a Hindi T2I generation model using the Generative Adversarial Network (GAN). The model is specifically trained on region-specific data, including a Hindi language dataset, which has been prepared, pre-processed, and fed to the model. The corpus comprises 11,788 bird images from 200 species. Baaz is the first model of its kind developed for Hindi text-to-image generation and can create high-quality images of birds that accurately reflect the semantic content of Hindi text. The experimental results have been published in scientific reports, demonstrating that the Baaz model performs well and produces realistic images. ======================================================================
Steps to Run the Model
1. Clone or Download the Repository git clone https://github.com/srinivasmudhiraj/-Hindi-T2I-generation-
cd -Hindi-T2I-generation-
2. Install Required Dependencies
pip install -r requirements.txt
3. Navigate to cd Hindi-T2I-generation-/Notebook/
4. Download and Place all the data,encoder and Model Files
5. Navigate to cd /codes and Run the Hindi T2I notebook for Testing