# New Release: Ultralytics v8.4.147 **URL:** \ **Category:** Discussion\ **Tags:** ultralytics-official, releases, announcements\ **Created:** [September 11, 2026, 1:09pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-147/2215 "2026-09-11T13:09:39Z")\ **Posts on this page:** 1\ **Page:** 1
**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 11, 2026, 1:09pm UTC](https://community.ultralytics.com/t/new-release-ultralytics-v8-4-147/2215/1 "2026-09-11T13:09:39Z")
# ๐Ÿš€ Ultralytics v8.4.147: Grayscale Preprocessing, Better SAM Generation, and Stronger Tooling Ultralytics **v8.4.147** is now available! This release expands Albumentations preprocessing to grayscale images, improves SAM mask generation, makes downloads and CI environments more reliable, and refreshes onboarding and Ultralytics Platform automation documentation. > **Quick overview:** Better grayscale workflows, cleaner SAM results, faster YOLO26 onboarding, and more dependable development infrastructure. No new model family or weights are introduced in this release. ## ๐ŸŒŸ New Features ### ๐Ÿ–ผ Albumentations Support for Grayscale Images Albumentations preprocessing now runs on images with either **1 channel for grayscale** or **3 channels for color** , while images with unsupported channel counts continue to be skipped. This enables configured transforms for medical, industrial, document, and scientific grayscale imagery. The change was introduced in [PR #26133](https://github.com/ultralytics/ultralytics/pull/26133) by [@onuralpszr](https://github.com/onuralpszr). ### ๐ŸŽฏ Improved SAM Mask Generation SAM generation gains several useful improvements: - Added `min_mask_region_area` to remove small mask regions and holes. - Corrected crop prompt scaling to cover the complete resized crop. - Improved confidence filtering for consistent behavior between direct `generate()` calls and standard prediction. - Standardized source image shape handling across arrays and tensors. - Added documentation demonstrating `min_mask_region_area`. These updates arrived through [PR #26129](https://github.com/ultralytics/ultralytics/pull/26129) by [@raimbekovm](https://github.com/raimbekovm). ## โšก Improvements ### ๐Ÿ›ก More Reliable Downloads The `safe_download()` utility now instructs `curl` to fail on HTTP errors rather than saving an error page as though it were a valid downloaded file. Failed downloads are therefore surfaced immediately and more clearly. See [PR #26126](https://github.com/ultralytics/ultralytics/pull/26126) by [@lakshanthad](https://github.com/lakshanthad) for the implementation. ### ๐Ÿงช Stronger CI and Runner Environments This release improves automated testing and runner reliability: - Trusted GPU CI is re-enabled on CUDA 13 runners through [PR #26127](https://github.com/ultralytics/ultralytics/pull/26127) by [@glenn-jocher](https://github.com/glenn-jocher). - Transient APT installation failures are handled with retries in the isolated export job through [PR #26122](https://github.com/ultralytics/ultralytics/pull/26122) by [@raimbekovm](https://github.com/raimbekovm). - GitHub CLI, or `gh`, is installed in CPU and GPU runner images through [PR #26131](https://github.com/ultralytics/ultralytics/pull/26131) by [@glenn-jocher](https://github.com/glenn-jocher). - `jq` is installed in CPU and GPU runner images through [PR #26134](https://github.com/ultralytics/ultralytics/pull/26134) by [@glenn-jocher](https://github.com/glenn-jocher). ## ๐Ÿ“š Documentation and Onboarding ### ๐Ÿค– Expanded Ultralytics Platform Automation Guidance New documentation makes Platform automation more accessible: - The `platform-cli` agent skill and `ul cloud` workflows are documented in [PR #26136](https://github.com/ultralytics/ultralytics/pull/26136) by [@JaviChulvi](https://github.com/JaviChulvi). - Platform Agents documentation now covers visual workflows, conditions, dataset collection, Slack alerts, execution options, and run monitoring through [PR #26135](https://github.com/ultralytics/ultralytics/pull/26135) by [@glenn-jocher](https://github.com/glenn-jocher). - Ask AI Autotraining guidance now covers dataset exploration, annotation, training, model comparison, export, and deployment through [PR #26137](https://github.com/ultralytics/ultralytics/pull/26137) by [@JaviChulvi](https://github.com/JaviChulvi). ### ๐Ÿ Faster First Prediction with YOLO26 The quickstart has been rewritten around installing Ultralytics and running a first prediction with pretrained **YOLO26** , the recommended model for new projects. The updated guidance includes clearer examples for: - CLI and Python - Docker and Conda - Headless environments - Development installations - Persistent settings Explore the changes in [PR #26128](https://github.com/ultralytics/ultralytics/pull/26128) by [@raimbekovm](https://github.com/raimbekovm). ### ๐ŸŽฅ Additional Documentation Resource A new video resource was added to the documentation through [PR #26124](https://github.com/ultralytics/ultralytics/pull/26124) by [@RizwanMunawar](https://github.com/RizwanMunawar). ## ๐Ÿ“ฆ Get v8.4.147 Upgrade to the latest release with: ```bash pip install -U ultralytics ``` You can review the official [Ultralytics v8.4.147 release](https://github.com/ultralytics/ultralytics/releases/tag/v8.4.147) or inspect every change in the [full v8.4.146 to v8.4.147 changelog](https://github.com/ultralytics/ultralytics/compare/v8.4.146...v8.4.147). Give the new release a try and share your feedback, benchmarks, or any issues you encounter with the Ultralytics community. Happy building! ๐Ÿš€