open_clip and CLIP

The open_clip project is a community-maintained reimplementation and extension of the original OpenAI CLIP model, making them ecosystem siblings where open_clip serves as the more actively maintained and production-ready alternative to the original research codebase.

open_clip
86
Verified
CLIP
60
Established
Maintenance 16/25
Adoption 25/25
Maturity 25/25
Community 20/25
Maintenance 13/25
Adoption 10/25
Maturity 16/25
Community 21/25
Stars: 13,496
Forks: 1,253
Downloads: 2,903,706
Commits (30d): 1
Language: Python
License:
Stars: 32,796
Forks: 3,961
Downloads:
Commits (30d): 1
Language: Jupyter Notebook
License: MIT
No risk flags
No Package No Dependents

About open_clip

mlfoundations/open_clip

An open source implementation of CLIP.

Supports diverse Vision Transformer and ConvNet architectures trained on large-scale datasets (LAION-2B, DataComp-1B) with published scaling laws, achieving competitive zero-shot ImageNet accuracy up to 85.4%. Integrates with PyTorch, Hugging Face model hub, and timm for image encoders, enabling efficient embedding computation via the clip-retrieval library. Offers flexible model loading from local checkpoints or HuggingFace, with pre-trained weights optimized for both inference and fine-tuning workflows.

About CLIP

openai/CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Trained on 400M image-text pairs using contrastive learning, CLIP jointly encodes images and text into a shared embedding space where cosine similarity enables zero-shot classification without task-specific fine-tuning. Built on Vision Transformers and text encoders in PyTorch, it integrates seamlessly with torchvision for preprocessing and supports multiple model scales (ViT-B/32, ViT-L/14, etc.) for deployment flexibility.

Scores updated daily from GitHub, PyPI, and npm data. How scores work