dalle-mini

DALL·E Mini - Generate images from a text prompt

https://github.com/borisdayma/dalle-mini

Science Score: 77.0%

This score indicates how likely this project is to be science-related based on various indicators:

✓
CITATION.cff file
Found CITATION.cff file
✓
codemeta.json file
Found codemeta.json file
✓
.zenodo.json file
Found .zenodo.json file
✓
DOI references
Found 1 DOI reference(s) in README
✓
Academic publication links
Links to: arxiv.org
✓
Committers with academic emails
4 of 28 committers (14.3%) from academic institutions
○
Institutional organization owner
○
JOSS paper metadata
○
Scientific vocabulary similarity
Low similarity (11.9%) to scientific vocabulary

Last synced: 6 months ago · JSON representation ·

Repository

DALL·E Mini - Generate images from a text prompt

Basic Info

Host: GitHub
Owner: borisdayma
License: apache-2.0
Language: Python
Default Branch: main
Homepage: https://www.craiyon.com
Size: 17.9 MB

Statistics

Stars: 14,814
Watchers: 112
Forks: 1,222
Open Issues: 99
Releases: 4

Created over 4 years ago · Last pushed over 2 years ago

Metadata Files

Readme Funding License Citation

DALL·E Mini

How to use it?

You can use the model on 🖍️ craiyon

How does it work?

Refer to our reports:

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:

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 Text-to-Image Generation" with image quantization from "Learning Transferable Visual Models From Natural Language Supervision".

Image encoder from "Taming Transformers for High-Resolution Image Synthesis".

Sequence to sequence model based on "BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension" with implementation of a few variants:

Main optimizer (Distributed Shampoo) from "Scalable Second Order Optimization for Deep Learning".

Citations

text @misc{ title={Zero-Shot Text-to-Image Generation}, author={Aditya Ramesh and Mikhail Pavlov and Gabriel Goh and Scott Gray and Chelsea Voss and Alec Radford and Mark Chen and Ilya Sutskever}, year={2021}, eprint={2102.12092}, archivePrefix={arXiv}, primaryClass={cs.CV} }

text @misc{ title={Learning Transferable Visual Models From Natural Language Supervision}, author={Alec Radford and Jong Wook Kim and Chris Hallacy and Aditya Ramesh and Gabriel Goh and Sandhini Agarwal and Girish Sastry and Amanda Askell and Pamela Mishkin and Jack Clark and Gretchen Krueger and Ilya Sutskever}, year={2021}, eprint={2103.00020}, archivePrefix={arXiv}, primaryClass={cs.CV} }

text @misc{ title={Taming Transformers for High-Resolution Image Synthesis}, author={Patrick Esser and Robin Rombach and Björn Ommer}, year={2021}, eprint={2012.09841}, archivePrefix={arXiv}, primaryClass={cs.CV} }

text @misc{ title={BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension}, author={Mike Lewis and Yinhan Liu and Naman Goyal and Marjan Ghazvininejad and Abdelrahman Mohamed and Omer Levy and Ves Stoyanov and Luke Zettlemoyer}, year={2019}, eprint={1910.13461}, archivePrefix={arXiv}, primaryClass={cs.CL} }

text @misc{ title={Scalable Second Order Optimization for Deep Learning}, author={Rohan Anil and Vineet Gupta and Tomer Koren and Kevin Regan and Yoram Singer}, year={2021}, eprint={2002.09018}, archivePrefix={arXiv}, primaryClass={cs.LG} }

text @misc{ title={GLU Variants Improve Transformer}, author={Noam Shazeer}, year={2020}, url={https://arxiv.org/abs/2002.05202} }

text @misc{ title={DeepNet: Scaling transformers to 1,000 layers}, author={Wang, Hongyu and Ma, Shuming and Dong, Li and Huang, Shaohan and Zhang, Dongdong and Wei, Furu}, year={2022}, eprint={2203.00555} archivePrefix={arXiv}, primaryClass={cs.LG} }

text @misc{ title={NormFormer: Improved Transformer Pretraining with Extra Normalization}, author={Sam Shleifer and Jason Weston and Myle Ott}, year={2021}, eprint={2110.09456}, archivePrefix={arXiv}, primaryClass={cs.CL} }

text @inproceedings{ title={Swin Transformer V2: Scaling Up Capacity and Resolution}, author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo}, booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)}, year={2022} }

text @misc{ title = {CogView: Mastering Text-to-Image Generation via Transformers}, author = {Ming Ding and Zhuoyi Yang and Wenyi Hong and Wendi Zheng and Chang Zhou and Da Yin and Junyang Lin and Xu Zou and Zhou Shao and Hongxia Yang and Jie Tang}, year = {2021}, eprint = {2105.13290}, archivePrefix = {arXiv}, primaryClass = {cs.CV} }

text @misc{ title = {Root Mean Square Layer Normalization}, author = {Biao Zhang and Rico Sennrich}, year = {2019}, eprint = {1910.07467}, archivePrefix = {arXiv}, primaryClass = {cs.LG} }

text @misc{ title = {Sinkformers: Transformers with Doubly Stochastic Attention}, url = {https://arxiv.org/abs/2110.11773}, author = {Sander, Michael E. and Ablin, Pierre and Blondel, Mathieu and Peyré, Gabriel}, publisher = {arXiv}, year = {2021}, }

text @misc{ title = {Smooth activations and reproducibility in deep networks}, url = {https://arxiv.org/abs/2010.09931}, author = {Shamir, Gil I. and Lin, Dong and Coviello, Lorenzo}, publisher = {arXiv}, year = {2020}, }

text @misc{ title = {Foundation Transformers}, url = {https://arxiv.org/abs/2210.06423}, author = {Wang, Hongyu and Ma, Shuming and Huang, Shaohan and Dong, Li and Wang, Wenhui and Peng, Zhiliang and Wu, Yu and Bajaj, Payal and Singhal, Saksham and Benhaim, Alon and Patra, Barun and Liu, Zhun and Chaudhary, Vishrav and Song, Xia and Wei, Furu}, publisher = {arXiv}, year = {2022}, }

Owner

Name: Boris Dayma
Login: borisdayma
Kind: user

Twitter: borisdayma
Repositories: 89
Profile: https://github.com/borisdayma

Building free AI tools 🎉

Citation (CITATION.cff)

# YAML 1.2
---
abstract: "DALL·E mini is a JAX/Flax reimplementation of OpenAI's DALL·E that requires much smaller hardware resources. By simplifying the architecture and model memory requirements, as well as leveraging open-source code and pre-trained models, we were able to create a model that is 27 times smaller than the original DALL·E and train it on a single TPU v3-8 for only 3 days. DALL·E mini achieves impressive results, albeit of a lower quality than the original system. It can be used for exploration and further experimentation on commodity hardware."
authors: 
  -
    family-names: Dayma
    given-names: Boris
  -
    family-names: Patil
    given-names: Suraj
  -
    family-names: Cuenca
    given-names: Pedro
  -
    family-names: Saifullah
    given-names: Khalid
  -
    family-names: Abraham
    given-names: Tanishq
  -
    family-names: "Lê Khắc"
    given-names: "Phúc"
  -
    family-names: Melas
    given-names: Luke
  -
    family-names: Ghosh
    given-names: Ritobrata
cff-version: "1.1.0"
date-released: 2021-07-29
identifiers: 
keywords: 
  - dalle
  - "text-to-image generation"
  - transformer
  - "zero-shot"
  - JAX
license: "Apache-2.0"
doi: 10.5281/zenodo.5146400
message: "If you use this project, please cite it using these metadata."
repository-code: "https://github.com/borisdayma/dalle-mini"
title: "DALL·E Mini"
version: "v0.1-alpha"
...

GitHub Events

Total

Issues event: 1
Watch event: 234
Issue comment event: 3
Pull request event: 1
Fork event: 44

Last Year

Issues event: 1
Watch event: 234
Issue comment event: 3
Pull request event: 1
Fork event: 44

Committers

Last synced: 9 months ago

All Time

Total Commits: 625
Total Committers: 28
Avg Commits per committer: 22.321
Development Distribution Score (DDS): 0.267

Past Year

Commits: 0
Committers: 0
Avg Commits per committer: 0.0
Development Distribution Score (DDS): 0.0

Top Committers

Name	Email	Commits
Boris Dayma	b**a@g**m	458
Pedro Cuenca	p**o@l**m	98
Khalid Saifullah	k**4@g**m	17
patil-suraj	s**5@g**m	11
Abubakar Abid	a**d@s**u	5
Ritobrata Ghosh	5****r	5
Tanishq Abraham	t**m@u**u	4
Blake	3****c	2
Gertie01	6****1	2
Madison Swain-Bowden	b**m@s**u	2
Patrick Berlatto Piccini	6****i	2
Shuming Ma	s**a@p**n	2
Ayush Thakur	a**t@w**m	2
system	s**m@h**o	1
AK391	8****1	1
Chenxi	c**e@g**m	1
Daryl Fritz	d**z@g**m	1
Han Xiao	h**o@j**i	1
Idan Bidani	i**n@g**m	1
Igor Makarov	i**a@g**m	1
Julian Casaburi	j**i@g**m	1
Liam	1****3	1
Muhtasham Oblokulov	m**7@g**m	1
Phúc Lê Khắc	p**h@g**m	1
Ryan Russell	r****l	1
batrlatom	t**a@g**m	1
illtellyoulater	3****r	1
jon-edward	3****d	1

Committer Domains (Top 20 + Academic)

jina.ai: 1 huggingface.co: 1 wandb.com: 1 pku.edu.cn: 1 spu.edu: 1 ucdavis.edu: 1 stanford.edu: 1 latenitesoft.com: 1

Issues and Pull Requests

Last synced: 6 months ago

All Time

Total issues: 78
Total pull requests: 33
Average time to close issues: 16 days
Average time to close pull requests: 22 days
Total issue authors: 75
Total pull request authors: 24
Average comments per issue: 2.69
Average comments per pull request: 2.27
Merged pull requests: 18
Bot issues: 0
Bot pull requests: 0

Past Year

Issues: 2
Pull requests: 1
Average time to close issues: N/A
Average time to close pull requests: N/A
Issue authors: 2
Pull request authors: 1
Average comments per issue: 1.0
Average comments per pull request: 0.0
Merged pull requests: 0
Bot issues: 0
Bot pull requests: 0

View more stats

Top Authors

Issue Authors

loboere (2)
rushic24 (2)
dreamgonfly (2)
fabaff (1)
xxxwangfirexxx (1)
Alexey100687 (1)
codefaux (1)
xiaotingxuan (1)
beifeng15 (1)
metaphorz (1)
Mshz2 (1)
HunterR27 (1)
FreddyE1982 (1)
ioa1994 (1)
ThatUncreativeDude (1)

Pull Request Authors

borisdayma (4)
pcuenca (3)
ayulockin (3)
jon-edward (2)
JesseSkelly (2)
igor-makarov (1)
juliancasaburi (1)
GaetanLepage (1)
0xhayleydev (1)
shravani2688 (1)
SauravMaheshkar (1)
darylf (1)
drdaxxy (1)
Muhtasham (1)
mallorbc (1)

Top Labels

Issue Labels

Pull Request Labels

Packages

Total packages: 7
Total downloads:
- pypi 683
Total docker downloads: 271

Total dependent packages: 0
(may contain duplicates)
Total dependent repositories: 10
(may contain duplicates)
Total versions: 19
Total maintainers: 1

proxy.golang.org: github.com/borisdayma/dalle-mini

Documentation: https://pkg.go.dev/github.com/borisdayma/dalle-mini#section-documentation
License: apache-2.0
Latest release: v0.1.1
published over 3 years ago

Versions: 3
Dependent Packages: 0
Dependent Repositories: 1

Rankings

Stargazers count: 0.5%

Forks count: 0.8%

Average: 3.9%

Dependent repos count: 4.7%

Dependent packages count: 9.6%

Last synced: 7 months ago

pypi.org: dalle-mini

DALL·E mini - Generate images from a text prompt

Homepage: https://github.com/borisdayma/dalle-mini
Documentation: https://dalle-mini.readthedocs.io/
License: Apache Software License
Latest release: 0.1.5
published over 2 years ago

Versions: 11
Dependent Packages: 0
Dependent Repositories: 9
Downloads: 683 Last month
Docker Downloads: 271

Rankings

Stargazers count: 0.1%

Forks count: 1.2%

Docker downloads count: 2.3%

Average: 4.5%

Dependent repos count: 4.9%

Downloads: 8.4%

Dependent packages count: 10.1%

Maintainers (1)

borisdayma

Last synced: 7 months ago

pypi.org: jonmalpak

This package is used for security research and demonstrations. It might contain dangerous code snippets. Do not run.

Homepage: https://github.com/borisdayma/dalle-mini
Documentation: https://jonmalpak.readthedocs.io/
License: Apache v2
Latest release: 3.2.4
published over 3 years ago

Versions: 1
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 0

Rankings

Stargazers count: 0.2%

Forks count: 1.3%

Dependent packages count: 4.8%

Dependent repos count: 6.3%

Average: 12.6%

Downloads: 50.6%

Last synced: about 1 year ago

pypi.org: fooblakebaz

This package is used for security research and demonstrations. It might contain dangerous code snippets. Do not run.

Homepage: https://github.com/borisdayma/dalle-mini
Documentation: https://fooblakebaz.readthedocs.io/
License: Apache v2
Latest release: 1.0.1
published over 3 years ago

Versions: 1
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 0

Rankings

Stargazers count: 0.2%

Forks count: 1.3%

Dependent packages count: 4.8%

Dependent repos count: 6.3%

Average: 12.7%

Downloads: 50.9%

Last synced: about 1 year ago

pypi.org: cxmaster

This package is used for security research and demonstrations. It might contain dangerous code snippets. Do not run.

Homepage: https://github.com/borisdayma/dalle-mini.git
Documentation: https://cxmaster.readthedocs.io/
License: Apache v2
Latest release: 3.2.1
published over 3 years ago

Versions: 1
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 0

Rankings

Stargazers count: 0.2%

Forks count: 1.3%

Dependent packages count: 4.8%

Dependent repos count: 6.3%

Average: 12.7%

Downloads: 50.9%

Last synced: about 1 year ago

pypi.org: hfghfgh

This package is used for security research and demonstrations. It might contain dangerous code snippets. Do not run.

Homepage: https://github.com/borisdayma/dalle-mini
Documentation: https://hfghfgh.readthedocs.io/
License: Apache v2
Latest release: 1.1.1
published over 3 years ago

Versions: 1
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 0

Rankings

Stargazers count: 0.2%

Forks count: 1.3%

Dependent packages count: 4.8%

Dependent repos count: 6.3%

Average: 12.7%

Downloads: 50.9%

Last synced: about 1 year ago

pypi.org: ffff2223433

This package is used for security research and demonstrations. It might contain dangerous code snippets. Do not run.

Homepage: https://github.com/borisdayma/dalle-mini
Documentation: https://ffff2223433.readthedocs.io/
License: Apache v2
Latest release: 1.2.3
published over 3 years ago

Versions: 1
Dependent Packages: 0
Dependent Repositories: 0
Downloads: 0

Rankings

Stargazers count: 0.2%

Forks count: 1.3%

Dependent packages count: 4.8%

Dependent repos count: 6.3%

Average: 12.7%

Downloads: 51.0%

Last synced: about 1 year ago

Dependencies

.github/workflows/check_size.yml actions

ActionsDesk/lfs-warning v2.0 composite

.github/workflows/pypi_release.yml actions

actions/checkout v3 composite
actions/setup-python v3 composite
pypa/gh-action-pypi-publish 27b31702a0e7fc50959f5ad993c78deac1bdfc29 composite

.github/workflows/style.yml actions

actions/checkout v2 composite
actions/setup-python v2 composite
jamescurtin/isort-action master composite
psf/black stable composite

.github/workflows/sync_to_hub.yml.backup actions

actions/checkout v2 composite

.github/workflows/sync_to_hub_debug.yml actions

actions/checkout v2 composite

Docker/Dockerfile docker

nvidia/cuda 11.6.2-cudnn8-devel-ubuntu20.04 build

pyproject.toml pypi

setup.py pypi

dalle-mini

Science Score: 77.0%

Repository

Basic Info

Statistics

Metadata Files

README.md

DALL·E Mini

How to use it?

How does it work?

Development

Dependencies Installation

Training of DALL·E mini

FAQ

Where to find the latest models?

Where does the logo come from?

Contributing

Acknowledgements

Authors & Contributors

Citing DALL·E mini

References

Citations

Owner

Citation (CITATION.cff)

GitHub Events

Total

Last Year

Committers

All Time

Past Year

Top Committers

Committer Domains (Top 20 + Academic)

Issues and Pull Requests

All Time

Past Year

Top Authors

Issue Authors

Pull Request Authors

Top Labels

Issue Labels

Pull Request Labels

Packages

proxy.golang.org: github.com/borisdayma/dalle-mini

Rankings

pypi.org: dalle-mini

Rankings

Maintainers (1)

pypi.org: jonmalpak

Rankings

pypi.org: fooblakebaz

Rankings

pypi.org: cxmaster

Rankings

pypi.org: hfghfgh

Rankings

pypi.org: ffff2223433

Rankings

Dependencies