Agent skill · nvidia
paidf-augmentation
Use when authoring or validating PAIDF augmentation YAML configs, or running remote Cosmos Transfer/Predict, image-edit, or image-to-video inference.
What it needs
About 7k tokens when loaded.
What this skill does
PAIDF Augmentation Pipeline Skill Unified pipeline for augmenting camera data through NVIDIA generative AI models with automated captioning, generation, and quality evaluation. BYOM (bring-your-own-model): every model is reached over a remote HTTP endpoint described by one entry in the config's endpoints: list; adding a model is usually a config change, not code. Purpose Use this skill to drive the PAIDF augmentation pipeline end to end: Select the right model — Cosmos Transfer 2.5 (transform a video), Cosmos Predict 2.5 (generate/extend video), image-edit (edit an image), or image-to-video (animate a first frame: Cosmos3 or Veo 3.1). Author and validate YAML configs against the PipelineConfig Pydantic schema. Configure captioning (VLM, LLM, deterministic VLM-template, text, or file) and evaluators (hallucination check, attribute verification, VLM verification). Launch and run inference inside the paidf-augmentation:1.1.0 Docker container (remote-API only — no local model weights). Use this skill when running inference, authoring or editing configs, debugging validation or runtime errors, adding data samples, configuring captioning, tuning generation parameters, registering BYOM endpoints/adapters, or setting up evaluators. Trigger keywords: augmentation, cosmos transfer, cosmos predict, image edit, image-to-video, veo, image attribute augmentation, defect image generation, captioning, attribute verification, config validation. Do not use this skill for training or fine-tuning models, deploying clusters or NIM endpoints, or unrelated application/database development. Prerequisites Requirement Detail ------------- -------- Docker docker --version. The image is remote-API only — it bundles no Cosmos/torch weights, so plain remote inference needs no GPU and no HFTOKEN. NVIDIA GPU (conditional) Only for the dataprocessing.alignment post-processor (cupy) and H.264 decode (evaluators, dataprocessing.transcode). See Limitations. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills nvidia/paidf-augmentation