PGPT is a chatbot and image-generating tool built using Tkinter for the interface, allowing users to chat with a persona-driven AI and receive AI-generated images in response to specific prompts.
- Chat System: A text-based chat system with a custom persona that can be edited in real-time.
- Image Generation: Generates AI images based on prompts embedded in the conversation, such as
. - Settings Management: The persona and image style settings are stored in a
settings.jsonfile and can be edited through the UI. - Retry Logic: Includes retry logic for AI conversation errors, with configurable delays between retries.
- Dynamic Image Display: Displays images generated by AI directly within the chat window, allowing users to click and view an enlarged version.
-
Clone the Repository:
git clone https://github.com/Tolerable/PGPT.git
-
Install Required Dependencies: Make sure you have the required Python libraries installed:
pip install requests pillow
-
Run the Application:
python PGPT.py
- Editing Persona: Click on "Options" in the menu and select "Edit Persona" to change the persona that guides the chatbot's responses.
- Editing Image Style: Similarly, you can adjust the image style prompts by selecting "Edit Photo Style".
- Sending Messages: Type your message into the text box and press "Enter" to send it. The AI will respond, and if there’s an image request in the response, it will be generated and displayed in the chat window.
PGPT.py: The main script that handles the chat and image generation.settings.json: Stores the persona and image style settings..gitignore: IgnoresPGPT-*.pyfiles and other unnecessary files.LICENSE: The MIT License under which this project is distributed.
This project is licensed under the MIT License. See the LICENSE file for details.