Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →nvidia/paidf-anomalygen
Full PAIDF AnomalyGen pipeline — fine-tune on a new anomaly dataset, generate synthetic anomaly images (SDG), evaluate quality (nn_score), and search per-sample (guidance, crop_ratio) parameters. Three modes: full (Phase 0→7: finetune then generate), finetune_only (Phase 0→1: train only), inference_only (Phase 0, 2→7: generate from an existing checkpoint).
Passed 21 of 22 test cases with the skill, and 6 of 22 without it.
and 28 more in the full report
16 fixed6 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
After Phase 3 completes and places images in `results/exp1/original`, what command calculates sample metrics against real dataset `/data/industrial_v1` for anomaly types `TYPE_A` and `TYPE_B`?
| Checked | Without skill | With skill |
|---|---|---|
| Invokes ${ANOMALYGEN_SCRIPTS}/run_eval.sh. | Missed | Passed |
| Passes --real-path /data/industrial_v1 and --generated-path results/exp1/original to run_eval.sh. | Missed | Passed |
The instructions your model reads when the skill loads.
Multi-phase pipeline (0–7); the mode flag selects which phases run.
| Phase | What runs | Mode(s) |
|---|---|---|
| 0 | Verify / download pretrained checkpoints | all |
| 1 | Fine-tune on dataset_dir | full, finetune_only |
| 2 | Prepare inference JSONL (AMP routing) | full, inference_only |
| 3 | SDG — generate synthetic anomaly images → original/ | full, inference_only |
| 4 | Eval original/ — emit per_sample.csv + eval.log, merge nn_score into SDG_result.csv | full, inference_only |
| 5 | Per-sample (guidance, crop_ratio) search rounds → rounds/round_NN/ (each round runs SDG + eval) | full, inference_only |
| 6 | Assemble best-of-rounds into searched/ (stitch only), plus rounds/search_summary.csv | full, inference_only |
| 7 | Filter searched/ by nn_threshold (default 0.4), regen dropped samples, then canonical bucket eval → searched/{per_sample.csv, eval.log} | full, inference_only |
Run every phase through to completion without mid-run pauses. Collect all required parameters up front, and run every command from the repo root.
Shell setup. All ${ANOMALYGEN_SCRIPTS} references resolve to the packaged
helper-script directory. Inside the container this is preset (ENV ANOMALYGEN_SCRIPTS=<dir>/scripts/utilities); on the host, export it once per
shell:
export ANOMALYGEN_SCRIPTS="$(git rev-parse --show-toplevel)/scripts/utilities"
python3 -m scripts.utilities.<name> invocations work from any CWD inside the
container (PYTHONPATH is preset) and from the repo root on the host. When inside
a product container (ANOMALYGEN_PRODUCT_MODE=1), invoke anomalygen-guard
before any GPU work; if it reports BLOCKED, fix the listed issues before
continuing.
The pipeline runs inside the metropolis_sdg.paidf_anomalygen container
(declared in versions.yaml) or any host with the cosmos-predict2 conda env
active. All phase commands assume that environment, at the repo root, with
ANOMALYGEN_SCRIPTS exported.
test cases passed, vs 6 / 22 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.