10 actions in 8 pieces of software · ranked by words, meaning and measured trust · 655 ms

1. 1mattsays/sam3-imageverified and signedpassport

   modelrecord

   • mattsays/sam3-image

     A unified foundation model for prompt-based segmentation in images and videos

2. 2yodagg/sam3-image-segverified and signedpassport

   modelrecord

   • yodagg/sam3-image-seg

3. 3vufinder/sam3verified and signedpassport

   modelrecord

   • vufinder/sam3

     Segment Anything Model 3 - unified foundation model for promptable segmentation in images.

4. 4lucataco/sam3-videoverified and signedpassport

   modelrecord

   • lucataco/sam3-video

     A unified foundation model for prompt-based segmentation in images and videos

5. 5sam3verified and signedpassport

   modelrecord1,945,717 downloads/month

   • mask-generation

     Task: mask-generation

6. 6SAM3demo or tutorialno passport yet

   MCP serverrecord

   • sam3_image_text_inference

     Segment every instance of a concept in a single image with SAM3 using a natural-language text prompt (concept segmentation). The prompt is a concept to find (e.g. "player in white", "red car"); each matching instance becomes one detection. Returns a JSON list of detection objects, each with: "object

   • sam3_image_visual_inference

     Segment objects in a single image with SAM3 using visual prompts (bounding boxes and/or points); a drop-in match for SAM2's process_image. Provide at least one of bboxes or points. Each bounding box produces its own mask; all points together describe one object and produce a single mask. The return

7. 7LocateAnything + SAM3verified and signedpassport

   MCP serverrecord

   • locate_anything_sam3_create_image_export

     Package the PNG, full result, config, BBOX data, and raw response. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool

   • locate_anything_sam3_run_image

     Locate prompted content in an image and optionally segment it with SAM3. If a user passes a file as an input, use the upload_file_to_gradio tool, if present, to upload the file to the gradio app and create a Gradio File Input. Then use the returned path as the input to the tool

8. 8bytedance/sa2va-8b-imageverified and signedpassport

   modelrecord

   • bytedance/sa2va-8b-image

     Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos