# New Release: Ultralytics v8.4.213

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-213/2310>\
**Category:** Discussion\
**Tags:** releases, announcements, ultralytics-official\
**Created:** [November 15, 2026, 8:10am UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-213/2310 "2026-11-15T08:10:54Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![glenn-jocher](https://sea1.discourse-cdn.com/flex001/user_avatar/community.ultralytics.com/glenn-jocher/32/83_2.png) [@glenn-jocher](https://community.ultralytics.com/u/glenn-jocher)\
**Post date:** [November 15, 2026, 8:10am UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-213/2310/1 "2026-11-15T08:10:55Z")

</div>

# 🚀 Ultralytics v8.4.213: Leaner Segmentation, More Reliable Predictions

**Ultralytics v8.4.213 makes large segmentation predictions more memory- and compute-efficient** , improves tiled inference and dataset conversion, and adds better Ultralytics Platform training previews and deployment guidance.

This release focuses on practical improvements across your workflow— **no model architecture changes are included**.

## ⚡ Highlight: More Efficient Segmentation Masks

With [PR #27197 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/27197), large segmentation mask stacks are now decoded **inside each detection box** , rather than across the full image.

- **Less unnecessary processing:** Outlines and exports can use box-local masks directly.
- **Dense masks on demand:** Accessing `masks.data` still produces the familiar full-size tensor.
- **Unchanged behavior for smaller stacks:** These continue using the existing path.

If you work with large images or many detections, this can reduce mask-processing costs—especially when you only need outlines or exports. 🎯

## 🛠 Inference, Dataset, and Visualization Fixes

- **More reliable tiled predictions:** In [PR #27188 by @AhmetMert01](https://github.com/ultralytics/ultralytics/pull/27188), class-aware NMS no longer suppresses tile-seam detections because they overlap an object of a different class.
- **Safer COCO conversion:** With [PR #27187 by @AhmetMert01](https://github.com/ultralytics/ultralytics/pull/27187), conversion now raises an error when different images map to the same label file, instead of mixing their labels.
- **Correct SAM class alignment:** Through [PR #27193 by @Yannis-A-D](https://github.com/ultralytics/ultralytics/pull/27193), `yolo_bbox2segment` keeps class IDs aligned with masks that survive confidence filtering.
- **Accurate confusion-matrix percentages:** In [PR #27183 by @laodouya](https://github.com/ultralytics/ultralytics/pull/27183), Platform results now display correct percentages for models with more than 100 classes.
- **Correct red and blue channels:** With [PR #27196 by @AhmetMert01](https://github.com/ultralytics/ultralytics/pull/27196), color handling is corrected for Annotator PIL images and SAM3 tensor results.

## ☁ Platform and OCR Improvements

- **Initial training previews:** With [PR #27173 by @Laughing-q](https://github.com/ultralytics/ultralytics/pull/27173), training can upload epoch-0 batch previews to Ultralytics Platform.
- **Cleaner project names:** In [PR #27191 by @glenn-jocher](https://github.com/ultralytics/ultralytics/pull/27191), Platform project naming uses the last folder of a local save directory.
- **Consistent OCR runtime setup:** Through [PR #27189 by @Laughing-q](https://github.com/ultralytics/ultralytics/pull/27189), OCR now shares the ONNX Runtime setup used by Ultralytics YOLO models.

## 📚 Clearer Documentation

- **Expanded deployment guidance:** In [PR #27190 by @raimbekovm](https://github.com/ultralytics/ultralytics/pull/27190), the ONNX and TensorRT integration pages were reorganized with output formats, deployment details, and refreshed benchmarks.
- **Broader workflow coverage:** With [PR #27194 by @pderrenger](https://github.com/ultralytics/ultralytics/pull/27194), documentation now covers per-class validation exports and updates guidance for Gemini 4 Hydrogen, OCR languages, and Platform search and import.

## 🙌 Welcome and Thanks

A special welcome to **@Yannis-A-D** , whose [first contribution in PR #27193](https://github.com/ultralytics/ultralytics/pull/27193) fixes SAM mask/class alignment. Thanks to everyone who contributed!

## 📦 Try v8.4.213

Install this release with:

```bash
pip install --upgrade ultralytics==8.4.213

```

Explore the [v8.4.213 release notes](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.213) for details, or review the [full changelog](https://github.com/ultralytics/ultralytics/compare/v8.4.212...v8.4.213) to see every change.

**Give it a try and share your feedback below!** We’d especially love to hear how the segmentation improvements perform on your large-image and high-detection workloads. 💬
