Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/islam-hady9/generative-ai-models
Generative AI Models is a comprehensive repository dedicated to the implementation of cutting-edge generative AI models using Python. It features various models, including those for image captioning and text-to-image generation, leveraging advanced architectures like Vision Transformers (ViT), GPT-2, and Stable Diffusion.
https://github.com/islam-hady9/generative-ai-models
computervision deeplearning generativeai gpt-2 huggingface-transformers imagecaptioning nlp pytorch stablediffusion text-to-image-generation visiontransformers
Last synced: about 2 hours ago
JSON representation
Generative AI Models is a comprehensive repository dedicated to the implementation of cutting-edge generative AI models using Python. It features various models, including those for image captioning and text-to-image generation, leveraging advanced architectures like Vision Transformers (ViT), GPT-2, and Stable Diffusion.
- Host: GitHub
- URL: https://github.com/islam-hady9/generative-ai-models
- Owner: Islam-hady9
- Created: 2024-08-23T16:59:35.000Z (about 1 month ago)
- Default Branch: main
- Last Pushed: 2024-08-26T06:35:03.000Z (about 1 month ago)
- Last Synced: 2024-09-22T06:02:15.828Z (5 days ago)
- Topics: computervision, deeplearning, generativeai, gpt-2, huggingface-transformers, imagecaptioning, nlp, pytorch, stablediffusion, text-to-image-generation, visiontransformers
- Language: Jupyter Notebook
- Homepage: https://huggingface.co/
- Size: 11.2 MB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Generative AI Models
Generative AI Models
---
Welcome to the **Generative-AI-Models** repository! This repository contains a collection of generative AI models implemented using Python and popular libraries like `transformers`, `torch`, `diffusers`, and more. These models can be used for various generative tasks such as image captioning, text-to-image generation, and more.
## Getting Started
To get started with the models in this repository, you can use Google Colab, which provides a free and powerful environment for running your code with GPU acceleration.
### Prerequisites
Before using the models, make sure you have the following:
- A Google account to access Google Colab.
- Basic knowledge of Python and deep learning concepts.
### Running Models on Google Colab
We have provided Google Colab templates for each model to ensure that you can run them quickly and efficiently. Follow the steps below to get started:
1. **Open Google Colab:** Click the links provided below for each model to open the respective Colab notebook.
2. **Connect to a GPU:** In Colab, go to `Runtime` > `Change runtime type`, and select `GPU` as the hardware accelerator.
3. **Run the Notebook:** Follow the instructions within the notebook to run the cells step by step. The models are pre-configured to run efficiently on Colab's environment.
### Available Models
Below is a list of available models in this repository along with their corresponding Google Colab templates:
#### 1. Text To Image Generator
Generate images from textual descriptions using the Stable Diffusion model.
- **Model Overview:** Uses a diffusion model to create high-quality images from text prompts.
- **Colab Template:** [text_to_image_generator](https://drive.google.com/file/d/1sL1GqOeDoOYhP15I-NQnVr-Wv4POgLxM/view?usp=drive_link)
- **Image Generation Output:**
#### 2. Image To Text Generator
Generate descriptive captions for images using the Vision Transformer (ViT) and GPT-2 models.
- **Model Overview:** Combines ViT for image processing and GPT-2 for text generation.
- **Colab Template:** [image_to_text_generator](https://drive.google.com/file/d/1WtfTozk-zMV2763B3ZMg3Pw4VZdiNiBa/view?usp=drive_link)
- **Text Generation Output:**
### How to Contribute
We welcome contributions from the community! If you have a model implementation you'd like to add or improvements to suggest, please follow these steps:
1. Fork the repository.
2. Create a new branch: `git checkout -b feature/YourFeatureName`.
3. Make your changes and commit them: `git commit -m 'Add some feature'`.
4. Push to the branch: `git push origin feature/YourFeatureName`.
5. Submit a pull request.
### License
This project is licensed under the MIT License.
### Acknowledgments
- [Hugging Face](https://huggingface.co/) for providing the `transformers` and `diffusers` libraries.
- [Google Colab](https://colab.research.google.com/) for offering a free and powerful platform for running deep learning models.