hermes - 💡(How to fix) Fix Pixshelf: local-first stock photo workflow command center

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Root Cause

It should not handle direct stock agency submission or uploads. Upload/submission automation is out of scope because agency integrations are brittle, complicated, and easy to get wrong.

RAW_BUFFERClick to expand / collapse

Feature Description

Pixshelf should be positioned as a local-first stock photo command center that combines:

  • Photo Mechanic-style ingest and culling
  • Excire Foto-style local AI discovery/search/keywording
  • IMstocker Studio-style stock metadata preparation and validation

It should not handle direct stock agency submission or uploads. Upload/submission automation is out of scope because agency integrations are brittle, complicated, and easy to get wrong.

Product Positioning

Pixshelf = local-first stock photo workflow app: fast culling + AI discovery + stock-ready metadata.

Not an uploader. Not an agency submission bot. Not a full Lightroom replacement.

Core Workflow

1. Inbox

  • Open or watch a folder/card/export folder
  • Detect new shoot/folder
  • Generate previews/index
  • Show counts for RAW/JPEG, duplicates, obvious rejects, unreviewed files

2. Cull

Photo Mechanic-inspired speed layer:

  • Fast grid/contact sheet
  • Large preview
  • Keyboard-first next/previous/rate/reject flow
  • Star ratings
  • Color labels
  • Pick/reject flags
  • Compare similar frames
  • Batch rename
  • Move/copy selected files into workflow folders
  • Filter by rating, label, flag, file type, date, camera, lens

Goal: reduce a shoot to stock-worthy candidates quickly.

3. Analyze

Excire-inspired local AI layer:

  • Local image analysis
  • AI subject/object/scene/concept tags
  • Natural-language search
  • Similar image search / “find photos like this”
  • Duplicate and near-duplicate detection
  • Blur/technical quality scoring
  • Commercial usefulness signals
  • Person/release-risk detection
  • Logo/trademark/text/signage risk detection

Goal: use AI to support both discovery and stock-prep decisions.

4. Stock Prep

IMstocker-inspired metadata workbench, without uploads:

  • Title generator
  • Description generator
  • Keyword generator
  • Keyword cleanup and ranking
    • remove duplicates
    • reorder strongest keywords first
    • cap keyword count appropriately
    • flag weak/generic/hallucinated terms
  • Category suggestions
  • Editorial vs commercial flag/recommendation
  • Model/property release reminders
  • Agency-specific metadata validation for common agencies such as Adobe Stock, Shutterstock, Alamy, etc.
  • Per-image stock readiness checklist

Example warnings:

  • Possible logo/trademark detected
  • Recognizable person: model release likely required
  • Keyword count outside agency limits
  • First 10 keywords are weak or misordered
  • Title too generic
  • Description missing or too thin

5. Export

No uploads. Export prepared assets and metadata only:

  • Write XMP/IPTC metadata
  • Export CSV/JSON metadata
  • Copy final files to output folders
  • Optional agency-ready folder structure:
    • ready/adobe-stock
    • ready/shutterstock
    • ready/editorial
    • needs-release
    • rejects

MVP Scope

Build the first version around Stock Prep from Folder:

  • Open folder
  • Grid + preview
  • Rate/pick/reject
  • Local AI keyword suggestions
  • Title/description generation
  • Manual metadata editing
  • Keyword ranking/cleanup
  • Stock readiness checklist
  • XMP/IPTC/CSV export
  • No uploads
  • No agency submissions
  • No complex DAM/catalog requirement for v1

Killer Feature

A button/action like:

Prepare selected images for stock

For selected images, Pixshelf should produce:

  • suggested title
  • suggested description
  • 30–50 cleaned/ranked keywords
  • release/trademark warnings
  • stock-readiness checklist/score
  • exportable metadata

Non-Goals

Do not build these for this feature:

  • Direct uploads to stock agencies
  • Submission automation
  • Agency login/session management
  • Submission status tracking
  • Full Lightroom replacement
  • Full cloud DAM
  • Client galleries
  • Mobile app
  • Accounting/invoicing

Acceptance Criteria

  • User can open a folder of images and cull/select stock candidates.
  • User can generate and edit stock-oriented titles, descriptions, and keywords.
  • User can run stock-readiness validation before export.
  • User can export metadata to portable formats such as XMP/IPTC/CSV.
  • The app makes clear that uploads/submissions are intentionally out of scope.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING