# Clip

OpenAI's model connecting vision and language.

- Repository: https://github.com/Orchestra-Research/AI-Research-SKILLs (14176 stars)
- Category: Media
- License: MIT
- Last updated: 2026-10-11
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill clip -g -a claude-code -y`
Codex: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill clip -g -a codex -y`
Cursor: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill clip -g -a cursor -y`
Gemini CLI: `npx skills add Orchestra-Research/AI-Research-SKILLs --skill clip -g -a gemini-cli -y`
Claude Code plugin marketplace: `/plugin marketplace add Orchestra-Research/AI-Research-SKILLs`

## Description

OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# 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

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

### Zero-shot classification

```python
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

```python
# 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")
```

The rest: https://github.com/Orchestra-Research/AI-Research-SKILLs/blob/HEAD/18-multimodal/clip/SKILL.md