Chat.py
- For interacting with the GPT-4 and chattingDalle3.py
- For generating multiple images in parallel via DALL·E 3TTS.py
- For generating text-to-speech audio files.
- Make sure any required packages are installed. You can use
pip install -r requirements.txt
- Add your OpenAI API key to
key.txt
- Run a script such as
chat.py
orDalle3.py

- Open
Dalle3.py
and edit any settings you want under "User Settings" near the top. Including the prompt and number of images to generate at once. - After all images are generated and returned, a window with the images will be shown
- Automatically saves the images into an output folder, and records the "revised prompts" for each image (the prompt actually used, that was based on the user-provided prompt)