title	emoji	colorFrom	colorTo	sdk	app_file	pinned
DALL·E mini	🥑	yellow	green	streamlit	app/app.py	false

DALL·E Mini

Generate images from a text prompt

Our logo was generated with DALL·E mini using the prompt "logo of an armchair in the shape of an avocado".

You can create your own pictures with the demo (temporarily in beta on Huging Face Spaces but soon to be open to all).

How does it work?

Refer to our report.

Development

Dependencies Installation

The root folder and associated requirements.txt is only for the app.

For development, use dev/requirements.txt or dev/environment.yaml.

Training of VQGAN

The VQGAN was trained using taming-transformers.

We recommend using the latest version available.

Conversion of VQGAN to JAX

Use patil-suraj/vqgan-jax.

Training of Seq2Seq

Refer to dev/seq2seq folder.

You can also adjust the sweep configuration file if you need to perform a hyperparameter search.

Inference Pipeline

To generate sample predictions and understand the inference pipeline step by step, refer to dev/inference/inference_pipeline.ipynb.

FAQ

Where to find the latest models?

Trained models are on 🤗 Model Hub:

• VQGAN-f16-16384 for encoding/decoding images
• DALL·E mini for generating images from a text prompt

Where does the logo come from?

The "armchair in the shape of an avocado" was used by OpenAI when releasing DALL·E to illustrate the model's capabilities. Having successful predictions on this prompt represents a big milestone to us.

Authors

• Boris Dayma
• Suraj Patil
• Pedro Cuenca
• Khalid Saifullah
• Tanishq Abraham
• Phúc Lê Khắc
• Luke Melas
• Ritobrata Ghosh

Acknowledgements

• 🤗 Hugging Face for organizing the FLAX/JAX community week
• Google Cloud team for providing access to TPU's