Three-piece workflow that imports a self-hosted Immich library and emits
new facesets without disturbing existing identity numbering:
- work/immich_stage.py (WSL): pages /search/metadata, parallel-fetches
/faces?id= per asset, prefilters by face_short>=90 against bbox scaled
to original-image coords, downloads originals, sha256-dedups against
nl_full.npz and same-run staged files. 8-worker ThreadPoolExecutor
doing the full /faces->filter->/original chain per asset; resumable
via state.json. API URL + key come from IMMICH_URL / IMMICH_API_KEY
env vars, label->UUID map from work/immich/users.json (gitignored).
- work/embed_worker.py (Windows venv at C:\face_embed_venv): runs
insightface.FaceAnalysis(buffalo_l) with the DmlExecutionProvider on
AMD Radeon Vega via onnxruntime-directml. Produces a cache file in
the same .npz schema as sort_faces.cmd_embed (loadable via
load_cache). ~7.5x speedup over CPU end-to-end; embeddings bit-
identical to CPU (cosine similarity 1.0000 across 8 sample faces).
- work/cluster_immich.py (WSL): mirrors cluster_osrc.py against an
immich_<user>.npz. Builds existing identity centroids from canonical
faceset_NNN/ in facesets_swap_ready/, drops matches at <=0.45,
clusters the rest at 0.55, applies refine gates, hands off to
cmd_export_swap. Numbers new facesets past the existing maximum.
- work/finalize_immich.sh: chains queue->Windows embed->cache copy->
cluster_immich, with logging.
The 2026-04-26 run on https://fotos.computerliebe.org (Immich v2.7.2)
processed 53,842 admin-accessible assets, staged 10,261, embedded
19,462 face records on Vega DML in 64.6 min, matched 8,103 (42%) to
existing identities, and emitted 185 new facesets (faceset_026..264
with gaps). facesets_swap_ready/ went from 31 to 216 substantive
facesets.
Important caveat surfaced: /search/metadata's userIds filter is
silently ignored when the API key is bound to a different user, so
this run can't enumerate other users' libraries from the admin key.
A per-user API key would be required for nic.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
work/cluster_osrc.py mirrors build_folders.py's shape (synthesize a
refine_manifest, hand off to cmd_export_swap, relocate, merge top-level
manifest) but discovers identities by clustering rather than asserting
them by folder. Drops faces already covered by existing identity
centroids, clusters the rest at 0.55, applies refine-equivalent gates
with min_faces=6, numbers new facesets past the existing maximum so
faceset_001..NNN are never disturbed.
The 2026-04-26 run on /mnt/x/src/osrc produced faceset_020..025 (sizes
4-26 exported PNGs); analysis writeup in docs/analysis/.
README also notes the refine-renumbers caveat in passing — extend +
orchestration script is the safe pattern; cmd_refine is for fresh
clusters only.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Documents the 2026-04-26 split of faceset_001 (707 curated faces) into
6 substantive era buckets + 68 thin fragments, including the readiness
probe evidence, the anchor-based assignment rationale (replaces
transitive union-find that caused year-drift), and the re-run / apply-
to-other-identity workflow.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
- enrich: re-detects each cached face with buffalo_l (detection +
landmark_2d_106 + landmark_3d_68, recognition module skipped for speed)
and persists landmarks + pose into the cache so per-face frontality and
landmark-symmetry quality signals become available.
- compute_quality: composite score combining det_score, face short-edge,
blur, frontality (from pose pitch/yaw), and 2D-landmark symmetry with
tunable weights. Default weighting 0.30/0.20/0.20/0.15/0.15.
- export-swap: builds facesets_swap_ready/ from an existing refine
manifest. Per identity: tighter outlier gate (default 0.45), visual-
near-dupe collapse (keep best representative per group), multi-face-
per-source-image collapse (keep best bbox), rank by composite score,
single-face-per-PNG crops at 512x512 with 0.5 bbox padding, ready-to-
drop .fsz bundles (top-N + full), per-faceset manifest.json, NAME.txt
placeholder for the operator. The multi-face-per-PNG collapse is the
critical fix: roop-unleashed's .fsz loader appends every detected face
in each PNG to the FaceSet, so any multi-face crop would contaminate
the averaged embedding.
- Optional --candidates rescues raw_full singletons: matches against the
final per-faceset centroids and routes to _candidates/to_<faceset>/
for manual review; orphaned singletons that still cluster among
themselves land in _candidates/new_<NNN>/.
- docs/analysis/: evaluation document captures the evidence, downstream
requirements (FaceSet averaging, inswapper_128), opportunity matrix
(R1-R14), and the recommended target state this export implements.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
