# New Release: Ultralytics v8.4.168

**URL:** <https://community.ultralytics.com/t/new-release-ultralytics-v8-4-168/2246>\
**Category:** Discussion\
**Tags:** ultralytics-official, releases, announcements\
**Created:** [September 30, 2026, 1:14pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-168/2246 "2026-09-30T13:14:15Z")\
**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:** [September 30, 2026, 1:14pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-168/2246/1 "2026-09-30T13:14:15Z")

</div>

# 🚀 Ultralytics v8.4.168: More Reliable Data Handling and Inference

**Ultralytics YOLO v8.4.168** brings practical fixes for image and semantic-mask processing, prediction outputs, video timing, and fixed-batch exported models—plus clearer training guidance. **No model architecture changes are included.**

## 🖼 Data Handling and Prediction Fixes

- **Safer masks, fresher caches, and distinct output files:** Palette PNG masks retain their class IDs, disk caches refresh when source images change, and AVIF images with EXIF orientation load upright. Predictions for same-stem files such as `bus.jpg` and `bus.png` now receive distinct output names. Fixed-batch exports also accept short batches by padding inputs and removing extra outputs. These fixes come from [@cainiao33 in PR #26443](https://github.com/ultralytics/ultralytics/pull/26443).
- **Preserved semantic-mask IDs and video timing:** 16-bit semantic masks retain their IDs and flag invalid classes, fractional video frame rates are preserved to help avoid playback drift, and CLI run-name parsing is corrected by [@Nicholas022400701 in PR #26440](https://github.com/ultralytics/ultralytics/pull/26440).
- **Working CutMix for semantic masks:** Semantic-mask regions can now be pasted even when there are no object instances, fixing skipped augmentation on PNG semantic-mask datasets through [@Nikhi00718’s PR #26439](https://github.com/ultralytics/ultralytics/pull/26439).

## ⚙ Runtime and Testing Improvements

- **Quieter ReID initialization:** Re-identification models warm up with an in-memory image, avoiding a missing-source warning and unnecessary asset-image inference thanks to [@raimbekovm in PR #26453](https://github.com/ultralytics/ultralytics/pull/26453).
- **Lighter similarity-search tests:** `SearchApp` testing reuses existing test images instead of triggering an additional 32 MB download, as updated by [@raimbekovm in PR #26452](https://github.com/ultralytics/ultralytics/pull/26452).

## 📚 Clearer Training and Deployment Guidance

- **Understand what `mask_ratio` controls:** Documentation now clarifies that it affects training masks—not predicted mask resolution—with the update from [@Y-T-G in PR #26441](https://github.com/ultralytics/ultralytics/pull/26441).
- **Set expectations for automatic optimization:** Documentation explains that `optimizer=auto` ignores `lr0` and `momentum`, clarifies deployment rename and slug behavior, and adjusts CLI examples through [@raimbekovm’s PR #26447](https://github.com/ultralytics/ultralytics/pull/26447).

## 🚀 Try It and Share Your Feedback

Upgrade to the release:

```bash
pip install --upgrade ultralytics==8.4.168

```

Explore the [v8.4.168 release notes](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.168) for the release overview, or review the [full changelog](https://github.com/ultralytics/ultralytics/compare/v8.4.167...v8.4.168) to inspect all changes.

Try it with your datasets and inference workflows, and share your results or any issues you encounter in this discussion. 🙌 Thanks to the contributors, the YOLO community, and the Ultralytics team for making this release possible!