Darktable 4.8 Pulls AI Feature After Discovering It Doesn't Work Well

Written by Michael Larabel in Free Software on 21 June 2024 at 12:56 PM EDT. 12 Comments
FREE SOFTWARE
While more software piles on AI features these days, today's release of the Darktable 4.8 RAW photography software has removed one of its AI features after realizing it only delivers mediocre quality.

Darktable is a wonderful open-source, multi-platform photography software package. With today's Darktable 4.8 release there is a new color equalizer module for controlling hue/lightness/saturation based on colors, new "enlarge canvas" and "overlay" modules, a toggle switch for the darkroom mode, performance improvements, and a variety of other smaller enhancements.

But it's also done away with an "AI" feature in realizing the current implementation doesn't work particularly well. The AI options within Darktable's color calibration module have been removed on the basis of being only "mediocre quality" according to the release notes.

This merge removed the AI detection options for detecting image surfaces and image edges. The removal stems from this bug report from January 2023 with the AI detection of image surfaces not detecting anything. Others have experienced similar bad behavior as well. The issue was further discussed toward the end of last year in this bug report.

For Darktable 4.8 these AI detection features are hidden but the code remains. That code may be dropped though in a future release if new implementations don't materialize.

More details on the Darktable 4.8 changes and downloads via GitHub.
Related News
About The Author
Michael Larabel

Michael Larabel is the principal author of Phoronix.com and founded the site in 2004 with a focus on enriching the Linux hardware experience. Michael has written more than 20,000 articles covering the state of Linux hardware support, Linux performance, graphics drivers, and other topics. Michael is also the lead developer of the Phoronix Test Suite, Phoromatic, and OpenBenchmarking.org automated benchmarking software. He can be followed via Twitter, LinkedIn, or contacted via MichaelLarabel.com.

Popular News This Week