Image understanding models
Models for image classification, detection, segmentation, captioning, and visual feature extraction
Where it stands
Open models837 products1.03× its peers
Fastest products
1mudler/locate-anything.cpp-gguf · Open models1128×
2prithivMLmods/Gender-Classifier-Mini · Open models317×
3BVRA/MegaDescriptor-S-224 · Open models40×
4BVRA/MegaDescriptor-B-224 · Open models39×
5onnx-community/dinov3-vitb16-pretrain-lvd1689m-ONNX · Open models25×
6microsoft/beit-base-finetuned-ade-640-640 · Open models24×
7BVRA/MegaDescriptor-T-224 · Open models17×
8microsoft/resnet-34 · Open models16×
9danelcsb/sam2.1_hiera_tiny · Open models15×
10timm/vit_7b_patch16_dinov3.lvd1689m · Open models11×
11timm/ViT-B-16-SigLIP-384 · Open models10×
12microsoft/resnet-101 · Open models9.4×
13onnx-community/grounding-dino-tiny-ONNX · Open models8.7×
141aurent/vit_small_patch8_224.lunit_dino · Open models8.7×
15depth-anything/DA3-GIANT · Open models6.9×
16google/siglip2-base-patch16-256 · Open models6.8×
17timm/convnext_large.fb_in22k_ft_in1k_384 · Open models6.6×
18nomic-ai/nomic-embed-vision-v1.5 · Open models6.5×19timm/resnetv2_50x1_bit.goog_in21k_ft_in1k · Open models6.4×
20timm/mobilenetv4_conv_small_050.e3000_r224_in1k · Open models6.2×
21facebook/sapiens2-pose-5b · Open models6.2×22ibm-nasa-geospatial/Prithvi-WxC-1.0-2300M · Open models6.0×
23yainage90/fashion-object-detection · Open models6.0×
24timm/convnextv2_large.fcmae_ft_in22k_in1k_384 · Open models5.8×
25Comfy-Org/sam-3d-body · Open models5.6×948 products carry this theme. “× its peers” is the theme's median growth against the place's median.