OpenCLIP
LAIONOpenCLIP is the open reimplementation of CLIP: a full contrastive pretraining pipeline plus a family of image-text checkpoints trained on LAION's published corpora rather than on a private crawl. Because both halves are in the open, it is the line that made CLIP-style scaling reproducible - the ViT-bigG/14 checkpoint reaches 80.1% zero-shot ImageNet, above anything OpenAI released - and it is the reference implementation almost every later CLIP variant is trained and evaluated with.
Two organizations in one product: the open_clip training code is maintained under mlfoundations, the checkpoints and the LAION corpora are published by LAION. The corpus history is not clean - laion/laion2B-en no longer resolves under its own name and now redirects to the re-filtered laion/relaion2B-en-research-safe, which sits behind an auto-accept gate.
Openness
5 high confidence- weights
- open(56 ungated laion/CLIP-* checkpoints on the Hub - 50 MIT, 4 Apache-2.0 and 2 declaring none)
- data
- open(the DataComp-1B corpus behind the DataComp.XL checkpoints is published ungated under CC-BY-4.0
- code
- open(open_clip ships the full contrastive pretraining pipeline - data loading, training loop, distributed launch scripts and ImageNet zero-shot evaluation)
- license
- MIT(OSI)
OpenCLIP publishes the training corpus, the pipeline that consumed it and an OSI license over the weights, which is the fullest release case in this category. The original LAION-2B corpus these checkpoints were trained on no longer resolves under its own name; it now points to the re-filtered ReLAION release behind a click-through gate, which counts as released rather than merely documented.
- https://huggingface.co/api/datasets/laion/relaion2B-en-research-safe recorded 2026-09-11
`id: laion/relaion2B-en-research-safe`, `gated: auto`, `private: false`, `disabled: false` - and the request for laion/laion2B-en redirects here.
- https://huggingface.co/api/datasets/mlfoundations/datacomp_1b recorded 2026-09-11
gated: false; license cc-by-4.0 - DataComp-1B, the corpus behind the DataComp.XL checkpoints, is published and ungated. This is the firmer footing for data:open than the LAION-2B path, whose original name now redirects to a re-filtered successor behind a gate.
- https://huggingface.co/laion/CLIP-ViT-H-14-laion2B-s32B-b79K/raw/main/README.md recorded 2026-09-11
`license: mit`; 'A CLIP ViT-H/14 model trained with the LAION-2B English subset of LAION-5B ... using OpenCLIP'; a Training Data section naming the 2-billion-sample English subset.
- https://raw.githubusercontent.com/mlfoundations/open_clip/main/LICENSE recorded 2026-09-11
the MIT permission grant verbatim - 'to deal in the Software without restriction' - over a 2012-2021 copyright by the open_clip authors.
- https://raw.githubusercontent.com/mlfoundations/open_clip/main/README.md recorded 2026-09-11
'This repository is focused on training CLIP models'; documents `python -m open_clip_train.main` with train-data, epochs and imagenet-val arguments, plus single-node and SLURM multi-node launch recipes.
Adoption
5 medium confidenceAdoption is measured as Hugging Face downloads summed across the 56 laion/CLIP-* repositories in the LAION account. That total sits close to the top adoption threshold and moves week to week, which keeps confidence at medium rather than high, and third-party re-hosts on the timm and apple accounts are excluded as mirrors, so the reading is, if anything, an undercount.
- https://huggingface.co/api/models?author=laion&search=CLIP&limit=100&sort=downloads&direction=-1 recorded 2026-09-11
56 laion CLIP repos with `downloads` (trailing 30 days) summing to 10,909,706.
Capability
3 high confidenceOpenCLIP posts real, published zero-shot ImageNet numbers and beats the original CLIP it reproduced, but the LAION-2B checkpoints are from an earlier generation, and SigLIP 2 leads them by five points on the same benchmark.
- https://raw.githubusercontent.com/mlfoundations/open_clip/main/README.md recorded 2026-09-11
model table, ImageNet zero-shot acc.: ViT-H-14 LAION-2B 32B samples 78.0%; ViT-bigG-14 LAION-2B 34B samples 80.1%; ViT-L-14-quickgelu (Original CLIP) WIT 13B 75.5%.
Verified 2026-09-11