This Gradio-powered web application integrates multiple AI models from Hugging Face via their pipeline API and Stable Diffusion for image generation. It provides a user-friendly interface for several advanced tasks, including Chat Bot, Image Generation, Image Captioning, Object Detection, Text Summarization, and Named Entity Recognition (NER).
- Chat Bot: Engage with a conversational AI model based on Hugging Face's pre-trained models.
- Image Generation: Generate images from text prompts using Hugging Face's Stable Diffusion models.
- Image Captioning: Automatically generate captions for images with Hugging Face's image captioning models.
- Object Detection: Detect and classify objects within images using Hugging Face's object detection models.
- Text Summarization: Condense long pieces of text into summaries using Hugging Face's summarization models.
- Named Entity Recognition (NER): Identify and categorize named entities like names, dates, and locations in text.
- Gradio: Web interface framework for building the app.
- Hugging Face's Transformers: Provides pre-trained models for natural language processing tasks (e.g., Chat Bot, Text Summarization, NER).
- Diffusers: Used for running the Stable Diffusion model to generate images from text prompts.
- Torch: Deep learning library used for model execution and computation.
- Pillow (PIL): Python Imaging Library used for image manipulation (e.g., image captioning, object detection).
- NumPy: Used for handling numerical operations and image processing.
- Base64 & io: For encoding and decoding image data (used for image inputs and outputs).
- Random & Time: Used for generating random values and managing delays (if needed).
 |
 |
 |
 |
 |
 |
To run this app locally, you will need Python 3.8 or higher.
- Clone the repository:
git clone git@github.com:amiralisahraei/ai-toolbox-gradio.git cd ai-toolbox-gradio pip install -r requirements.txt - Then Just run the notebook file