22 models · ranked by HuggingFace downloads
OpenAI's CLIP model using a ViT-L/14 image encoder, trained contrastively on 400 million image-text pairs from the internet. It aligns image and text in a shared embedding space, enabling zero-shot image classification by comparing image embeddings against text label embeddings. The ViT-L/14 variant offers higher accuracy than the smaller ViT-B/32 at greater compute cost.
OpenAI's CLIP model using a ViT-B/32 image encoder, the smaller of the two widely deployed CLIP variants. Trained contrastively on 400 million image-text pairs, it aligns image and text representations in a shared embedding space for zero-shot classification and retrieval. The B/32 variant sacrifices accuracy versus ViT-L/14 for faster inference.
OpenAI CLIP ViT-L/14 at 336×336px input resolution, a higher-resolution variant of the standard ViT-L/14 CLIP model. The larger input patch size reduces information loss during tokenization, improving performance on classification tasks requiring fine-grained visual detail. Otherwise shares the same contrastive training on 400M image-text pairs as the base ViT-L/14.
CLIP-ViT-B-32-laion2B-s34B-b79K is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
fashion-clip is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
siglip-so400m-patch14-384 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
siglip-base-patch16-224 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
CLIP-ViT-B-16-laion2B-s34B-b88K is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
clip-vit-base-patch16 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
marqo-fashionSigLIP is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
BiomedCLIP-PubMedBERT_256-vit_base_patch16_224 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
siglip2-so400m-patch14-384 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
CLIP-ViT-L-14-laion2B-s32B-b82K is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
siglip2-base-patch16-224 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
CLIP-convnext_base_w-laion2B-s13B-b82K-augreg is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
PE-Core-L14-336 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
siglip2-base-patch16-naflex is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
CLIP-ViT-H-14-laion2B-s32B-b79K is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
siglip2-so400m-patch16-naflex is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
vit_base_patch16_plus_clip_240.laion400m_e31 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
TinyCLIP-ViT-8M-16-Text-3M-YFCC15M is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.
siglip2-base-patch16-512 is an open-source zero-shot-image-classification model available on HuggingFace. Details are sourced from the public model registry.