DALL-E and Whisper using Streamlit and Gradio

DALL-E 2 are deep learning models developed by OpenAI to generate digital images from natural language descriptions.

It uses a diffusion model conditioned on CLIP image embeddings, which, during inference, are generated from CLIP text embeddings by a prior model.

It can generate imagery in multiple styles, including photorealistic imagery, paintings, and emoji. It can "manipulate and rearrange" objects in its images.

Demo

https://drive.google.com/drive/folders/18BAnMMTzEx0N7HrCORwsbRgKHqKvh6_c?usp=sharing

Installation

Activate the conda environment

  conda activate environment_name

Install python dependencies

  pip install openai
  pip install streamlit
  pip install urllib
  pip install Pillow

After Installing python dependencies, download the project folder and extract the folder and run the following commands

  streamlit run dalle.py

To run the Whisper gradio app you can directly download the .ipynb file and run the colab environment