LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs

Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis +4 more
11/3/2021
cs.CVcs.CLcs.LG

Official code: mlfoundations/open_clip (14,013 stars, PyTorch, last commit 2026-04-30).

Abstract

Multi-modal language-vision models trained on hundreds of millions of image-text pairs (e.g. CLIP, DALL-E) gained a recent surge, showing remarkable capability to perform zero- or few-shot learning and transfer even in absence of per-sample labels on target image data. Despite this trend, to date there has been no publicly available datasets of sufficient scale for training such models from scratch. To address this issue, in a community effort we build and release for public LAION-400M, a dataset with CLIP-filtered 400 million image-text pairs, their CLIP embeddings and kNN indices that allow efficient similarity search.

View on arXivView PDF

Code Implementations(1)

mlfoundations/open_clipOfficial100%
PyTorch

An open source implementation of CLIP.

14,0131,296Shell, PythonJul 28, 20215 months agoNOASSERTION
computer-visioncontrastive-lossdeep-learninglanguage-modelmulti-modal-learning+3 more

Similar Papers

LAION-5B: An open large-scale dataset for training next generation image-text models

88% match1 repo14.0k2022

Intern VL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks

85% match1 repo10.1k2023

Long-VITA: Scaling Large Multi-modal Models to 1 Million Tokens with Leading Short-Context Accuracy

85% match1 repo3062025

PiTL: Cross-modal Retrieval with Weakly-supervised Vision-language Pre-training via Prompting

85% match2023

ViT-Lens: Initiating Omni-Modal Exploration through 3D Insights

85% match1 repo1892023

Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data

85% match1 repo62023

Cite this paper

@article{schuhmann2021laionm,
  title  = {LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs},
  author = {Christoph Schuhmann and Richard Vencu and Romain Beaumont and Robert Kaczmarczyk and Clayton Mullis and Aarush Katta and Theo Coombes and Jenia Jitsev and Aran Komatsuzaki},
  year   = {2021},
  eprint = {2111.02114},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/2111.02114}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2111.02114.svg)](https://codeofpaper.com/paper/2111.02114)

Discussion