All Contributors have signed the CLA. ✅
_{Posted by the CLA Assistant Lite bot.}

👋 Hello @ShuaiLYU, thank you for submitting an ultralytics/ultralytics 🚀 PR! To ensure a seamless integration of your work, please review the following checklist:

• ✅ Define a Purpose: Please confirm your PR description clearly explains the purpose and scope of your contribution. If possible, link to any relevant issues for added context. Ensure your commit messages are clear and concise.
• ✅ Synchronize with Source: Make sure your PR is up to date with the main branch of ultralytics/ultralytics. If your branch is behind, use the 'Update branch' button or run git pull and git merge main locally.
• ✅ Ensure CI Checks Pass: Check that all Ultralytics Continuous Integration (CI) checks have passed. If there are any failures, please resolve them.
• ✅ Update Documentation: If your PR introduces new features or changes existing functionality, update the relevant documentation accordingly.
• ✅ Add Tests: Where applicable, include or update tests to ensure your changes are covered and passing.
• ✅ Sign the CLA: If this is your first Ultralytics contribution, please sign our Contributor License Agreement (CLA) by commenting "I have read the CLA Document and I sign the CLA" in this PR.
• ✅ Minimize Changes: Please limit your changes to only what's necessary for your addition or bug fix. "It is not daily increase but daily decrease, hack away the unessential. The closer to the source, the less wastage there is." — Bruce Lee

For further details, you can refer to our Contributing Guide. If your PR addresses a bug and you haven't already, please provide a minimum reproducible example (MRE) so we can verify the fix.

This is an automated response 🛠️—an Ultralytics engineer will review your contribution and assist you soon. Thank you for helping improve Ultralytics! 🚀✨

Codecov Report

❌ Patch coverage is 16.94915% with 98 lines in your changes missing coverage. Please review.

📢 Thoughts on this report? Let us know!

Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.

I have read the CLA Document and I sign the CLA

You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.

I have read the CLA Document and I sign the CLA

I have read the CLA Document and I sign the CLA

Absolutely thrilled to see this merged — huge thanks @ShuaiLYU, @Laughing-q, and @glenn-jocher! “Great things are done by a series of small things brought together.” — Vincent van Gogh. Your collective effort delivers a training-free, dynamic SAM 2 experience that makes interactive segmentation and cross-image tracking faster, cleaner, and more intuitive for real-world annotation, editing, and surveillance workflows.

Quick start:

from ultralytics.models.sam import SAM2DynamicInteractivePredictor

overrides = dict(model="sam2_t.pt", imgsz=1024, task="segment", mode="predict", conf=0.01)
predictor = SAM2DynamicInteractivePredictor(overrides=overrides, max_obj_num=10)

# Add an object via box prompt and update memory
predictor.inference(img="image1.jpg", bboxes=[[100, 100, 200, 200]], obj_ids=[1], update_memory=True)

# Track it in a new image
results = predictor(source="image2.jpg")

See the Ultralytics Docs for details: https://docs.ultralytics.com

Brilliant work pushing the boundaries of dynamic, interactive segmentation — this will be a game-changer for our users. 🚀

@glenn-jocher too fast haha I just found a typo

EDIT: fixed in https://github.com/ultralytics/ultralytics/pull/21835/files