text2imagebot

Demo

<div> <img src="https://github.com/nuhmanpk/text2imagebot/blob/main/assests/text2image.gif" alt="Image" width="300"/> <img src="https://github.com/nuhmanpk/text2imagebot/blob/main/assests/photo_2023-10-30_22-44-24.jpg" alt="gif-demo" width="267"/> <img src="https://github.com/nuhmanpk/text2imagebot/blob/main/assests/photo_2023-10-30_23-15-22.jpg" alt="Image" width="267"/> <img src="https://github.com/nuhmanpk/text2imagebot/blob/main/assests/photo_2023-10-30_23-15-26.jpg" alt="Image" width="267"/> <img src="https://github.com/nuhmanpk/text2imagebot/blob/main/assests/photo_2023-10-30_23-15-25.jpg" alt="Image" width="267"/> <img src="https://github.com/nuhmanpk/text2imagebot/blob/main/assests/photo_2023-10-30_23-15-24.jpg" alt="Image" width="267"/> </div>

View more demos • Contribute to the project

Text2ImageBot is a Telegram bot that generates images from text inputs using advanced text-to-image generation techniques. This bot utilizes state-of-the-art deep learning models to convert textual descriptions into visually appealing images, providing users with a seamless experience for creating compelling visual content.

How It Works

The bot harnesses the power of Diffusion models, a cutting-edge technique from Hugging Face, to convert textual prompts into visually stunning image outputs. By utilizing this advanced machine learning model, the bot comprehends the provided text and produces corresponding images that vividly represent the described content.

Usage

To use the Text2ImageBot, follow these simple steps:

1. Start a chat with the bot on Telegram.
2. Send a text message containing the desired image description or prompt.
3. The bot will process the text and generate an image based on the provided description.
4. Download the generated image from the bot's response.

Running the Code

To run the code locally, follow the instructions below:

1. Clone the repository to your local machine.
2. Ensure you have the required dependencies installed as specified in the requirements.txt file.
3. Open the text2imagebot.ipynb notebook in your preferred environment (such as Google Colab or Jupyter Notebook).
4. Follow the instructions in the notebook to execute the code and interact with the text2imagebot.

TODO:

• [x] Run on Colab
• [x] Add Multiple Model from Huggingface
• [x] Give user options to customize the model with seed, steps etc
• [ ] Add a perment Deployment Option
• [ ] Provide a Demo Bot For Testing
• [ ] Add Upscaler
• [x] More user friendly UI
• [ ] Add showcase channel
• [x] Add Multi image generation from same prompt
• [ ] Add negative prompt section

Feel free to contribute to the project by submitting bug reports, feature requests, or pull requests. Your contributions are highly appreciated!