X-AnyLabeling Model Zoo
July 19, 2026 · View on GitHub
Classification
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| pulc_person_attribute.onnx | PersonAttribute-PULC | pulc_person_attribute.yaml | 6.59MB | baidu | github |
| pulc_vehicle_attribute.onnx | VehicleAttribute-PULC | pulc_vehicle_attribute.yaml | 6.55MB | baidu | github |
| internimage_l_22kto1k_384.onnx | InternImage-Large | internimage_l_22kto1k_384.yaml | 853.16MB | Baidu | GitHub |
| yolov5s-cls.onnx | YOLOv5-Cls-ImageNet | yolov5s_cls.yaml | 20.81MB | baidu | github |
| yolov8s-cls.onnx | YOLOv8-Cls-ImageNet | yolov8s_cls.yaml | 24.28MB | baidu | github |
| yolo11s-cls.onnx | YOLO11-Cls-ImageNet | yolo11s_cls.yaml | 25.67MB | baidu | GitHub |
Keypoint Detection
- Facial Landmark Detection
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| yolov6lite_l_face.onnx | Facial Landmark Detection | yolov6lite_l_face.yaml | 4.16MB | baidu | github |
| yolov6lite_m_face.onnx | Facial Landmark Detection | yolov6lite_m_face.yaml | 3.00MB | baidu | github |
| yolov6lite_s_face.onnx | Facial Landmark Detection | yolov6lite_s_face.yaml | 2.10MB | baidu | github |
| scrfd_10g_bnkps.onnx | SCRFD-Face Detection & Landmarks | scrfd_10g_bnkps.yaml | 16.16MB | baidu | github |
- Pose Estimation
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| yolo26s-pose.onnx | YOLO26-COCO | yolo26s_pose.yaml | 39.86MB | baidu | github |
| yolo11s-pose.onnx | YOLO11-COCO | yolo11s_pose.yaml | 38.09MB | baidu | github |
| yolov8n-pose.onnx | YOLOv8-COCO | yolov8n_pose.yaml | 12.75MB | baidu | github |
| yolov8x-pose-p6.onnx | YOLOv8-COCO | yolov8x_pose_p6.yaml | 378.92MB | baidu | github |
| dw-ll_ucoco_384.onnx | DWPose(2D human whole-body pose estimation) | yolox_l_dwpose_ucoco.yaml | 128.17MB | baidu | github |
| yolox_l.onnx | YOLOX(2D human whole-body pose estimation) | yolox_l_dwpose_ucoco.yaml | 206.71MB | baidu | github |
| rtmo_m.onnx | RTMO(2D human whole-body pose estimation) | rtmdet_m_coco_person_rtmo_m.yaml | 85.13MB | baidu | github |
| rtmdet_m_640-8xb32_coco-person.onnx | RTMDet(2D human whole-body pose estimation) | rtmdet_m_640-8xb32_coco-person.onnx | 104.25MB | baidu | github |
Lane Detection
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| clrnet_tusimple_r18.onnx | CLRNet-Tusimple (CVPR2022) | clrnet_tusimple_r18.yaml | 59.04MB | baidu | github |
Multi-Object Tracking
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| yolov5s.onnx | YOLOv5s-Det-BoT-SORT | yolov5s_det_botsort.yaml | 27.98MB | baidu | github |
| yolov8s.onnx | YOLOv8s-Det-BoT-SORT | yolov8s_det_botsort.yaml | 42.75MB | baidu | github |
| yolov8n_obb_car_bus.onnx | YOLOv8n-Obb-BoT-SORT | yolov8n_obb_botsort.yaml | 12.02MB | baidu | github |
| yolov8m-seg.onnx | YOLOv8m-Seg-Bytetrack | yolov8m_seg_bytetrack.yaml | 104.23MB | baidu | github |
| yolov8x-pose-p6.onnx | YOLOv8x-Pose-P6-BoT-SORT | yolov8x_pose_p6_botsort.yaml | 378.92MB | baidu | github |
| yolo11s.onnx | YOLO11s-Det-BoT-SORT | yolo11s_det_botsort.yaml | 36.27MB | baidu | github |
| yolov11s_obb_car_bus.onnx | YOLO11s-OBB-BoT-SORT | yolo11s_obb_botsort.yaml | 37.36MB | Baidu | GitHub |
| yolo11s-seg.onnx | YOLO11s-Seg-BoT-SORT | yolo11s_seg_botsort.yaml | 38.77MB | baidu | github |
| yolo11s-pose.onnx | YOLO11s-Pose-BoT-SORT | yolo11s_pose_botsort.yaml | 38.09MB | baidu | github |
| yolo26s.onnx | YOLO26s-Det-TrackTrack | yolo26s_det_tracktrack.yaml | 36.47MB | baidu | github |
| yolo26s-seg.onnx | YOLO26s-Seg-TrackTrack | yolo26s_seg_tracktrack.yaml | 39.91MB | baidu | github |
| yolo26s-obb.onnx | YOLO26s-OBB-TrackTrack | yolo26s_obb_tracktrack.yaml | 37.56MB | baidu | github |
| yolo26s-pose.onnx | YOLO26s-Pose-TrackTrack | yolo26s_pose_tracktrack.yaml | 39.86MB | baidu | github |
Object Detection
- Horizontal Bounding Box
- Oriented Bounding Box
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| yolov5n_obb_drone_vehicle.onnx | YOLOv5-OBB-DroneVehicle | yolov5n_obb_drone_vehicle.yaml | 8.39MB | baidu | github |
| yolov5s_obb_csl_dotav10.onnx | YOLOv5-OBB-DOTA-v1.0 | yolov5s_obb_csl_dotav10.yaml | 29.77MB | baidu | github |
| yolov5m_obb_csl_dotav15.onnx | YOLOv5-OBB-DOTA-v1.5 | yolov5m_obb_csl_dotav15.yaml | 83.59MB | baidu | github |
| yolov5m_obb_csl_dotav20.onnx | YOLOv5-OBB-DOTA-v2.0 | yolov5m_obb_csl_dotav20.yaml | 83.62MB | baidu | github |
| yolov8s-obb.onnx | YOLOv8-OBB-DOTA-v1.0 | yolov8s_obb.yaml | 43.84MB | baidu | github |
| yolo11s-obb.onnx | YOLO11s-Obb-DOTA-v1.0 | yolo11s_obb.yaml | 37.36MB | baidu | github |
| yolo26s-obb.onnx | YOLO26s-Obb-DOTA-v1.0 | yolo26s_obb.yaml | 37.56MB | baidu | github |
Optical Character Recognition
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| doclayout_yolo_docstructbench_imgsz1024.onnx | DocLayout-YOLO | doclayout_yolo.yaml | 72.22MB | baidu | github |
| ppocrv5_mobile_det_infer.onnx | Ultra-lightweight PPOCR-v5 detection model | ch_chinese_cht_en_japan_ppocr_v5.yaml | 4.55MB | baidu | github |
| ppocrv5_mobile_rec_infer.onnx | Ultra-lightweight PPOCR-v5 recognition model supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese | ch_chinese_cht_en_japan_ppocr_v5.yaml | 15.76MB | baidu | github |
| ppocrv6_tiny_det_infer.onnx | PP-OCRv6 Tiny detection model | ch_chinese_cht_en_japan_ppocr_v6_tiny.yaml | 1.70MB | baidu | github |
| ppocrv6_tiny_rec_infer.onnx | PP-OCRv6 Tiny recognition model supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese | ch_chinese_cht_en_japan_ppocr_v6_tiny.yaml | 4.26MB | baidu | github |
| ppocrv6_small_det_infer.onnx | PP-OCRv6 Small detection model | ch_chinese_cht_en_japan_ppocr_v6_small.yaml | 9.42MB | baidu | github |
| ppocrv6_small_rec_infer.onnx | PP-OCRv6 Small recognition model supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese | ch_chinese_cht_en_japan_ppocr_v6_small.yaml | 20.18MB | baidu | github |
| ppocrv6_medium_det_infer.onnx | PP-OCRv6 Medium detection model | ch_chinese_cht_en_japan_ppocr_v6_medium.yaml | 59.16MB | baidu | github |
| ppocrv6_medium_rec_infer.onnx | PP-OCRv6 Medium recognition model supporting Simplified Chinese, Chinese Pinyin, Traditional Chinese, English, and Japanese | ch_chinese_cht_en_japan_ppocr_v6_medium.yaml | 73.01MB | baidu | github |
| ch_ppocr_mobile_v2.0_cls_infer.onnx | Classifier model, classifying the detected text line angles | ch_chinese_cht_en_japan_ppocr_v5.yaml | 569KB | baidu | github |
| ch_PP-OCRv4_det_infer.onnx | Ultra-lightweight PPOCR-v4 detection model | ch_ppocr_v4.yaml | 4.53MB | baidu | github |
| ch_PP-OCRv4_rec_infer.onnx | Ultra-lightweight PPOCR-v5 recognition model supporting Chinese, English, and digits | ch_ppocr_v4.yaml | 10.33MB | baidu | github |
| ch_ppocr_mobile_v2.0_cls_infer.onnx | Classifier model, classifying the detected text line angles | ch_ppocr_v4.yaml | 569KB | baidu | github |
| ch_PP-OCRv4_det_infer.onnx | Ultra-lightweight PPOCR-v4 detection model | japan_ppocr.yaml | 4.53MB | baidu | github |
| japan_PP-OCRv3_rec_infer.onnx | Lightweight model for Japanese recognition model | japan_ppocr.yaml | 9.62MB | baidu | github |
| ch_ppocr_mobile_v2.0_cls_infer.onnx | Classifier model, classifying the detected text line angles | japan_ppocr.yaml | 569KB | baidu | github |
Segment Anything Models
- General Scenario
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| sam3_image_encoder.onnx | SAM3 ViT-H image encoder | sam3_vit_h.yaml | 2.39MB | baidu | github |
| sam3_image_encoder.onnx.data | SAM3 ViT-H image encoder data | sam3_vit_h.yaml | 1.70GB | baidu | github |
| sam3_language_encoder.onnx | SAM3 ViT-H language encoder | sam3_vit_h.yaml | 1.33MB | baidu | github |
| sam3_language_encoder.onnx.data | SAM3 ViT-H language encoder data | sam3_vit_h.yaml | 1.50GB | baidu | github |
| sam3_decoder.onnx | SAM3 ViT-H decoder | sam3_vit_h.yaml | 123.84MB | baidu | github |
| sam3_decoder.onnx.data | SAM3 ViT-H decoder data | sam3_vit_h.yaml | 111.13MB | baidu | github |
| sam2.1_hiera_tiny.encoder.onnx | SAM2 | sam2_hiera_tiny.yaml | 128.04MB | baidu | github |
| sam2.1_hiera_tiny.decoder.onnx | SAM2 | sam2_hiera_tiny.yaml | 19.68MB | baidu | github |
| sam2.1_hiera_small.encoder.onnx | SAM2 | sam2_hiera_small.yaml | 155.17MB | baidu | github |
| sam2.1_hiera_small.decoder.onnx | SAM2 | sam2_hiera_small.yaml | 19.68MB | baidu | github |
| sam2.1_hiera_base_plus.encoder.onnx | SAM2 | sam2_hiera_base.yaml | 324.04MB | baidu | github |
| sam2.1_hiera_base_plus.decoder.onnx | SAM2 | sam2_hiera_base.yaml | 19.68MB | baidu | github |
| sam2.1_hiera_large.encoder.onnx | SAM2 | sam2_hiera_large.yaml | 848.16MB | baidu | github |
| sam2.1_hiera_large.decoder.onnx | SAM2 | sam2_hiera_large.yaml | 19.68MB | baidu | github |
| edge_sam_encoder.onnx | EdgeSAM | edge_sam.yaml | 21.02MB | baidu | github |
| edge_sam_decoder.onnx | EdgeSAM | edge_sam.yaml | 17.78MB | baidu | github |
| sam_vit_b_01ec64.encoder.onnx | SAM ViT-base encoder | segment_anything_vit_b.yaml | 342.58MB | baidu | github |
| sam_vit_b_01ec64.decoder.onnx | SAM ViT-base decoder | segment_anything_vit_b.yaml | 15.74MB | baidu | github |
| sam_vit_b_01ec64.encoder.quant.onnx | SAM ViT-base encoder(Quantized) | segment_anything_vit_b_quant.yaml | 103.78MB | baidu | github |
| sam_vit_b_01ec64.decoder.quant.onnx | SAM ViT-base decoder(Quantized) | segment_anything_vit_b_quant.yaml | 8.34MB | baidu | github |
| sam_vit_l_0b3195.encoder.onnx | SAM ViT-large encoder | segment_anything_vit_l.yaml | 1.15GB | baidu | github |
| sam_vit_l_0b3195.decoder.onnx | SAM ViT-large decoder | segment_anything_vit_l.yaml | 15.74MB | baidu | github |
| sam_vit_l_0b3195.encoder.quant.onnx | SAM ViT-large encoder(Quantized) | segment_anything_vit_l_quant.yaml | 317.18MB | baidu | github |
| sam_vit_l_0b3195.decoder.quant.onnx | SAM ViT-large decoder(Quantized) | segment_anything_vit_l_quant.yaml | 8.34MB | baidu | github |
| mobile_sam.encoder.onnx | MobileSAM encoder | mobile_sam_vit_h.yaml | 26.85MB | baidu | github |
| sam_vit_h_4b8939.decoder.quant.onnx | MobileSAM decoder | mobile_sam_vit_h.yaml | 8.34MB | baidu | github |
| sam_vit_h_4b8939.encoder.quant.onnx | SAM ViT-huge encoder(Quantized) | segment_anything_vit_h_quant.yaml | 626.40MB | baidu | github |
| sam_vit_h_4b8939.decoder.quant.onnx | SAM ViT-huge decoder(Quantized) | segment_anything_vit_h_quant.yaml | 8.34MB | baidu | github |
| efficientvit_sam_l0_vit_h.encoder.onnx | EfficientViT-SAM ViT-huge encoder | efficientvit_sam_l0_vit_h.yaml | 117.25MB | baidu | github |
| efficientvit_sam_l0_vit_h.decoder.onnx | EfficientViT-SAM ViT-huge decoder | efficientvit_sam_l0_vit_h.yaml | 15.63MB | baidu | github |
| efficientvit_sam_l1_vit_h.encoder.onnx | EfficientViT-SAM ViT-huge encoder | efficientvit_sam_l1_vit_h.yaml | 166.31MB | baidu | github |
| efficientvit_sam_l1_vit_h.decoder.onnx | EfficientViT-SAM ViT-huge decoder | efficientvit_sam_l1_vit_h.yaml | 15.63MB | baidu | github |
| sam_hq_vit_b_encoder.onnx | HQ-SAM ViT-base encoder | sam_hq_vit_b.yaml | 342.37MB | baidu | github |
| sam_hq_vit_b_decoder.onnx | HQ-SAM ViT-base decoder | sam_hq_vit_b.yaml | 19.74MB | baidu | github |
| sam_hq_vit_l_encoder.onnx | HQ-SAM ViT-large encoder | sam_hq_vit_l.yaml | 1.15GB | baidu | github |
| sam_hq_vit_l_decoder.onnx | HQ-SAM ViT-large decoder | sam_hq_vit_l.yaml | 20.74MB | baidu | github |
| sam_hq_vit_l_encoder_quant.onnx | HQ-SAM ViT-large encoder(Quantized) | sam_hq_vit_l_quant.yaml | 307.96MB | baidu | github |
| sam_hq_vit_l_decoder | HQ-SAM ViT-large decoder | sam_hq_vit_l_quant.yaml | 20.74MB | baidu | github |
| sam_hq_vit_h_encoder_quant.onnx | HQ-SAM ViT-huge encoder(Quantized) | sam_hq_vit_h_quant.yaml | 625.55MB | baidu | github |
| sam_hq_vit_h_decoder | HQ-SAM ViT-huge decoder | sam_hq_vit_h_quant.yaml | 21.74MB | baidu | github |
- Medical Scenario
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| sam-med2d_b.encoder.onnx | SAM-Med2D ViT-base encoder | sam_med2d_vit_b.yaml | 1019.49MB | baidu | github |
| sam-med2d_b.decoder.onnx | SAM-Med2D ViT-base decoder | sam_med2d_vit_b.yaml | 15.60MB | baidu | github |
See the Segment Anything 3 guide for both local ONNX and server-side usage.
Segmentation
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| rf-detr-seg-preview.onnx | RF-DETR Seg-Preview | rfdetr_seg_preview.yaml | 122.18MB | baidu | github |
| yolov5s-seg.onnx | YOLOv5-COCO | yolov5s_seg.yaml | 29.45MB | baidu | github |
| yolov8x-seg.onnx | YOLOv8-COCO | yolov8x_seg.yaml | 274.10MB | baidu | github |
| yolov8l-seg.onnx | YOLOv8-COCO | yolov8l_seg.yaml | 175.59MB | baidu | github |
| yolov8m-seg.onnx | YOLOv8-COCO | yolov8m_seg.yaml | 104.23MB | baidu | github |
| yolov8s-seg.onnx | YOLOv8-COCO | yolov8s_seg.yaml | 45.25MB | baidu | github |
| yolov8n-seg.onnx | YOLOv8-COCO | yolov8n_seg.yaml | 13.18MB | baidu | github |
| yolo11s-seg.onnx | YOLO11-COCO | yolo11s_seg.yaml | 38.77MB | baidu | github |
| hyper-yolon-seg.onnx | Hpyer-YOLO-COCO | hyper-yolon-seg.yaml | 16.77MB | baidu | github |
| hyper-yolos-seg.onnx | Hpyer-YOLO-COCO | hyper-yolos-seg.yaml | 59.34MB | baidu | github |
| hyper-yolom-seg.onnx | Hpyer-YOLO-COCO | hyper-yolom-seg.yaml | 132.85MB | baidu | github |
| yolo26s-seg.onnx | YOLO26s-Seg-COCO | yolo26s_seg.yaml | 39.91MB | Baidu | GitHub |
Image Matting
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| bria-rmbg-2.0.onnx | RMBG v2.0 (BRIA AI) | rmbg_v20.yaml | 976.88MB | baidu | github |
| bria-rmbg-2.0-quant.onnx | RMBG v2.0 Quantized (BRIA AI) | rmbg_v20_quant.yaml | 349.13MB | baidu | github |
| bria-rmbg-1.4.onnx | RMBG v1.4 (BRIA AI) | rmbg_v14.yaml | 167.99MB | baidu | github |
Combined Models
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| yolov8s.onnx | YOLOv8-SAM2.1 | yolov8s_sam2_hiera_base.yaml | 42.75MB | baidu | github |
| sam2.1_hiera_base_plus.encoder.onnx | YOLOv8-SAM2.1 | yolov8s_sam2_hiera_base.yaml | 324.04MB | baidu | github |
| sam2.1_hiera_base_plus.decoder.onnx | YOLOv8-SAM2.1 | yolov8s_sam2_hiera_base.yaml | 19.68MB | baidu | github |
| resnet50.onnx | ResNet50-ImageNet | yolov5s_resnet50.yaml | 97.42MB | baidu | github |
| yolov5s.onnx | YOLOv5-COCO | yolov5s_resnet50.yaml | 27.98MB | baidu | github |
| mobile_sam.encoder.onnx | MobileSAM encoder(YOLOv5-SAM) | yolov5s_mobile_sam_vit_h.yaml | 26.85MB | baidu | github |
| sam_vit_h_4b8939.decoder.quant.onnx | MobileSAM decoder(YOLOv5-SAM) | yolov5s_mobile_sam_vit_h.yaml | 8.34MB | baidu | github |
| yolov5s.onnx | YOLOv5-COCO(YOLOv5-SAM) | yolov5s_mobile_sam_vit_h.yaml | 27.98MB | baidu | github |
| yolov5m.onnx | YOLOv5-RAM | yolov5m_ram.yaml | 81.19MB | baidu | github |
| ram_swin_large_14m.onnx | YOLOv5-RAM | yolov5m_ram.yaml | 865.66MB | baidu | github |
| edge_sam_encoder.onnx | EdgeSAM-CN-CLIP ViT-B-16 | edge_sam_with_chinese_clip.yaml | 21.02MB | baidu | github |
| edge_sam_decoder.onnx | EdgeSAM-CN-CLIP ViT-B-16 | edge_sam_with_chinese_clip.yaml | 17.78MB | baidu | github |
| vit-b-16.img.fp16.onnx | EdgeSAM-CN-CLIP ViT-B-16 | edge_sam_with_chinese_clip.yaml | 3.51MB | baidu | github |
| vit-b-16.txt.fp16.onnx | EdgeSAM-CN-CLIP ViT-B-16 | edge_sam_with_chinese_clip.yaml | 2.15MB | baidu | github |
| vit-b-16.img.fp16.onnx.extra_file | EdgeSAM-CN-CLIP ViT-B-16 | edge_sam_with_chinese_clip.yaml | 164.40MB | baidu | github |
| vit-b-16.txt.fp16.onnx.extra_file | EdgeSAM-CN-CLIP ViT-B-16 | edge_sam_with_chinese_clip.yaml | 194.68MB | baidu | github |
| groundingdino_swint_ogc_quant.onnx | GroundingSAM-SwinB with HQ-SAM-VitL-QInt8 | groundingdino_swinb_attn_fuse_sam_hq_vit_l_quant.yaml | 964.04MB | baidu | github |
| sam_hq_vit_l_encoder_quant.onnx | GroundingSAM-SwinB with HQ-SAM-VitL-QInt8 | groundingdino_swinb_attn_fuse_sam_hq_vit_l_quant.yaml | 307.96MB | baidu | github |
| sam_hq_vit_l_decoder | GroundingSAM-SwinB with HQ-SAM-VitL-QInt8 | groundingdino_swinb_attn_fuse_sam_hq_vit_l_quant.yaml | 20.74MB | baidu | github |
| sam2.1_hiera_large.encoder.onnx | GroundingSAM2 | groundingdino_swint_sam2_large.yaml | 848.16MB | baidu | github |
| sam2.1_hiera_large.decoder.onnx | GroundingSAM2 | groundingdino_swint_sam2_large.yaml | 19.68MB | baidu | github |
| groundingdino_swint_ogc_quant.onnx | GroundingSAM2 | groundingdino_swint_sam2_large.yaml | 171.28MB | baidu | github |
Open-Vocabulary Grounding
Depth Estimation
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| depth_anything_vits14.onnx | DepthAnything | depth_anything_vit_s.yaml | 94.48MB | baidu | github |
| depth_anything_vitb14.onnx | DepthAnything | depth_anything_vit_b.yaml | 370.91MB | baidu | github |
| depth_anything_vitl14.onnx | DepthAnything | depth_anything_vit_l.yaml | 1.25GB | baidu | github |
| depth_anything_v2_vits.onnx | DepthAnythingV2 | depth_anything_v2_vit_s.yaml | 94.77MB | baidu | github |
| depth_anything_v2_vitb.onnx | DepthAnythingV2 | depth_anything_v2_vit_b.yaml | 371.20MB | baidu | github |
| depth_anything_v2_vitl.onnx | DepthAnythingV2 | depth_anything_v2_vit_l.yaml | 1.25GB | baidu | github |
Interactive Video Object Segmentation
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| sam2_hiera_tiny.pt | SAM 2 | sam2_hiera_tiny_video.yaml | 148.68MB | baidu | github |
| sam2_hiera_small.pt | SAM 2 | sam2_hiera_small_video.yaml | 175.77MB | baidu | github |
| sam2_hiera_base_plus.pt | SAM 2 | sam2_hiera_base_video.yaml | 308.51MB | baidu | github |
| sam2_hiera_large.pt | SAM 2 | sam2_hiera_large_video.yaml | 856.35MB | baidu | github |
For server-side SAM 3 video tracking, see the Segment Anything 3 Video guide.
Zero-Shot Counting by Detection and Segmentation
| Name | Description | Configuration | Size | Link |
|---|---|---|---|---|
| GeCo_encoder_data.bin | GeCo | geco_sam_hq_vit_h.yaml | 2.38GB | Baidu |
| GeCo_encoder.onnx | GeCo | geco_sam_hq_vit_h.yaml | 16.78MB | baidu | github |
| GeCo_decoder.onnx | GeCo | geco_sam_hq_vit_h.yaml | 16.83MB | baidu | github |
| GeCo_encoder_quant.onnx | GeCo | geco_sam_hq_vit_h.yaml | 646.48MB | Baidu |
Extended Models and Services
This section lists models that require additional runtimes, standalone inference services, or cloud APIs. See the linked documentation for setup and usage.