Skip to content
SPECIFICTION
Get listed

PixCull

github.com

Free plan WindowsmacOSLinuxiOSAPISelf-hosted
Visit github.com
Spec score 7.8 #18 of 29 in AI Photo Culling Software

What it is

PixCull is an open-source photo and video culling tool that sorts shoots into keep, maybe, and cull groups. It scores each frame from 1–5 stars on technical quality, subject, composition, light, moment, and aesthetic, with a written rationale for each area. The product describes nine photography verticals, from weddings and wildlife to journalism and still life. For photo workflows, it exports XMP sidecars for Lightroom and Capture One, IPTC captions, and HTML galleries; it can also watch tether destinations and sync folders through iCloud, Dropbox, or NAS. Video tools score clips, identify reel candidates, transcribe audio, and export EDL files for Premiere or Resolve. RAW decoding, scoring, face analysis, and GPS analysis can run locally. The maker says photos are sent to MiniMax for judging by default since v2.50 after recorded consent; cloud judging can be disabled with `--vlm-mode off`. PixCull states it has no telemetry, and cached models plus disabled cloud judging can allow runs without a network connection. The plan is free; optional cloud model calls may incur API costs.

Spec sheet

Intended users
The maker identifies wedding and event photographers, sports and action shooters, photojournalists, studios, wildlife and landscape photographers, and self-taught photographers as target users.Read 7 Oct 2026 · github.com
License
PixCull is released under the MIT license, which the maker says allows commercial use and forking.Read 7 Oct 2026 · github.com
Founded
2025Read 28 Sep 2026 · github.com
Exports and integrations
PixCull exports XMP sidecars for Lightroom and Capture One, IPTC captions, and standalone HTML galleries.Read 7 Oct 2026 · github.com
Genre support
The product describes nine photography verticals, including wedding, wildlife, sports, landscape, portrait, event, journalism, commercial, and still life.Read 7 Oct 2026 · github.com
Local processing
RAW decoding, scoring, face analysis, and GPS analysis run locally, and photos can stay on the user's machine.Read 7 Oct 2026 · github.com
Mobile companion
An iOS swipe companion is provided as a Swift package to build in Xcode and is not available on the App Store.Read 7 Oct 2026 · github.com
Optional cloud processing
The maker's security policy says photos are sent to MiniMax for judging by default since v2.50 after recorded consent, and the feature can be disabled with --vlm-mode off.Read 7 Oct 2026 · github.com
Photo culling
PixCull sorts shoots into keep, maybe, and cull, scores frames across six axes, and gives a written reason for each decision.Read 7 Oct 2026 · github.com
Privacy and network behavior
The maker states there is no telemetry; with cached models and cloud judging disabled, a run can operate without network connections.Read 7 Oct 2026 · github.com
Scoring
Each frame receives 1–5 star scores for technical quality, subject, composition, light, moment, and aesthetic, with a rationale for each axis.Read 7 Oct 2026 · github.com
Server security
The local server binds to 127.0.0.1 by default, and optional LAN deployment can be gated by an API key header.Read 7 Oct 2026 · github.com
Support and limits
The security policy says only the latest main branch is supported, older commits do not receive backported patches, and vulnerability reports should be emailed to the maintainer.Read 7 Oct 2026 · github.com
Tethering and sync
It can watch a Lightroom or Capture One tether destination and supports folder-based syncing through iCloud, Dropbox, or NAS.Read 7 Oct 2026 · github.com
Video tools
PixCull can score video clips, find reel candidates, transcribe audio, and export an EDL for Premiere or Resolve.Read 7 Oct 2026 · github.com

Plans and prices

PixCull Free MIT-licensed open source; optional paid licence; optional cloud model calls may incur API costs Read 7 Oct 2026 · github.com

Every PixCull plan and price →

Strong points and limits

Strong points

  • Scores six image qualities with written rationales
  • Exports XMP sidecars for Lightroom and Capture One
  • Supports video scoring and EDL export
  • MIT license permits commercial use and forking

Limits

  • iOS companion must be built in Xcode
  • Cloud judging is enabled by default after consent
  • Only the latest main branch is supported
  • Optional cloud model calls may incur API costs

Who it suits

PixCull suits photographers managing large shoots, including wedding, event, sports, wildlife, and landscape photographers. It may also fit users who want local processing options and exports for Lightroom or Capture One.

Verdict

PixCull combines detailed photo selection with video tools and several export paths. Readers should note the default cloud-judging behavior, optional API costs, and limited support for older commits.

Where Specifiction places it

Alternatives to PixCullAll alternatives →