AI Model Hub
Browse AI models for multimodal decomposition and recomposition pipelines — plug any model into your extractors.
8,900 models available
Showing 1–24 of 8,900 models
Featured Models
Benchmarked
HFVisual Embeddings
openai/clip-vit-large-patch14
Contrastive Language-Image Pre-Training for zero-shot visual understanding
28.6M
3 benchmarks
HFVisual Embeddings
google/siglip-base-patch16-224
Sigmoid Loss for Language Image Pre-Training, efficient contrastive learning
1.2M
3 benchmarks
HFVisual Embeddings
google/siglip2-giant-opt-patch16-384
Multilingual vision-language encoder with dense features and localization
1.2M
2 benchmarks
HFVisual Embeddings
facebook/dinov2-large
Self-supervised vision foundation model producing all-purpose visual features
2.8M
2 benchmarks
PyTorchVisual Embeddings
facebook/dinov3-large
Next-generation self-supervised vision model with Gram anchoring and 6.7B scaling
450K
1 benchmarks
HFVisual Embeddings
laion/CLIP-ViT-bigG-14-laion2B-39B-b160k
Open-source CLIP trained on 2B image-text pairs at giant scale
890K
2 benchmarks
Sentence Similarity
sentence-transformers/all-MiniLM-L6-v2
213.1M
4,724
sentence-transformersSentence Similarity
sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
37.8M
1,208
sentence-transformersSentence Similarity
sentence-transformers/all-mpnet-base-v2
34.8M
1,282
sentence-transformers...
1 / 371