README

DALL·E Mini



 How to use it?

You can use the model on 🖍️ craiyon

 How does it work?

Refer to our reports:

 DALL·E mini - Generate Images from Any Text Prompt
 DALL·E mini - Explained
 DALL·E mega - Training Journal

 Development

 Dependencies Installation

For inference only, use pip install dalle-mini.

For development, clone the repo and use pip install -e ".[dev]".
Before making a PR, check style with make style.

You can experiment with the pipeline step by step through our inference pipeline notebook



 Training of DALL·E mini

Use tools/train/train.py.

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

 FAQ

 Where to find the latest models?

Trained models are on 🤗 Model Hub:

 VQGAN-f16-16384 for encoding/decoding images
 DALL·E mini or DALL·E mega 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 for us.

 Contributing

Join the community on the LAION Discord.
Any contribution is welcome, from reporting issues to proposing fixes/improvements or testing the model with cool prompts!

You can also use these great projects from the community:

 spin off your own app with DALL-E Playground repository (thanks Sahar)

 try DALL·E Flow project for generating, diffusion, and upscaling in a Human-in-the-Loop workflow (thanks Han Xiao)

  

 run on Replicate, in the browser or via API

 Acknowledgements

 🤗 Hugging Face for organizing the FLAX/JAX community week
 Google TPU Research Cloud (TRC) program for providing computing resources
 Weights & Biases for providing the infrastructure for experiment tracking and model management

 Authors & Contributors

DALL·E mini was initially developed by:

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

Many thanks to the people who helped make it better:

 the DALLE-Pytorch and EleutherAI communities for testing and exchanging cool ideas
 Rohan Anil for adding Distributed Shampoo optimizer and always giving great suggestions
 Phil Wang has provided a lot of cool implementations of transformer variants and gives interesting insights with x-transformers
 Katherine Crowson for super conditioning
 the Gradio team made an amazing UI for our app

 Citing DALL·E mini

If you find DALL·E mini useful in your research or wish to refer, please use the following BibTeX entry.

text
@misc{Dayma_DALL·E_Mini_2021,
      author = {Dayma, Boris and Patil, Suraj and Cuenca, Pedro and Saifullah, Khalid and Abraham, Tanishq and Lê Khắc, Phúc and Melas, Luke and Ghosh, Ritobrata},
      doi = {10.5281/zenodo.5146400},
      month = {7},
      title = {DALL·E Mini},
      url = {https://github.com/borisdayma/dalle-mini},
      year = {2021}
}


 References

Original DALL·E from "Zero-Shot