clip

CLIP - Contrastive Language-Image Pre-Training

OpenAI's model that understands images from natural language.

When to use CLIP

Use when:

• Zero-shot image classification (no training data needed)
• Image-text similarity/matching
• Semantic image search
• Content moderation (detect NSFW, violence)
• Visual question answering
• Cross-modal retrieval (image→text, text→image)

Metrics:

• 25,300+ GitHub stars
• Trained on 400M image-text pairs
• Matches ResNet-50 on ImageNet (zero-shot)
• MIT License

Use alternatives instead:

• BLIP-2: Better captioning
• LLaVA: Vision-language chat
• Segment Anything: Image segmentation

Quick start

Installation

pip install git+https://github.com/openai/CLIP.git
pip install torch torchvision ftfy regex tqdm

Zero-shot classification

import torch
import clip
from PIL import Image

# Load model
device = "cuda" if torch.cuda.is_available() else "cpu"
model, preprocess = clip.load("ViT-B/32", device=device)

# Load image
image = preprocess(Image.open("photo.jpg")).unsqueeze(0).to(device)

# Define possible labels
text = clip.tokenize(["a dog", "a cat", "a bird", "a car"]).to(device)

# Compute similarity
with torch.no_grad():
    image_features = model.encode_image(image)
    text_features = model.encode_text(text)

    # Cosine similarity
    logits_per_image, logits_per_text = model(image, text)
    probs = logits_per_image.softmax(dim=-1).cpu().numpy()

# Print results
labels = ["a dog", "a cat", "a bird", "a car"]
for label, prob in zip(labels, probs[0]):
    print(f"{label}: {prob:.2%}")

Available models

# Models (sorted by size)
models = [
    "RN50",           # ResNet-50
    "RN101",          # ResNet-101
    "ViT-B/32",       # Vision Transformer (recommended)
    "ViT-B/16",       # Better quality, slower
    "ViT-L/14",       # Best quality, slowest
]

model, preprocess = clip.load("ViT-B/32")

Model	Parameters	Speed	Quality
RN50	102M	Fast	Good
ViT-B/32	151M	Medium	Better
ViT-L/14	428M	Slow	Best