physical-ai-defect-image-generation

Orchestrate end-to-end AI defect-image generation pipelines for AOI datasets on NVIDIA OSMO.

Updated Apr 16, 2026

Search Tags:#image-edit #pcba #defect-generation #AOI #anomalygen #usd2roi #structural-defect

Ready to run

npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill physical-ai-defect-image-generation

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: physical-ai-defect-image-generation
Source: https://github.com/sayalinvidia/sayali-skills-test/tree/main/skills/physical-ai-defect-image-generation
Command: npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill physical-ai-defect-image-generation

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and assets (resource) components.

What problem does it solve?

Orchestrates end-to-end defect image generation pipelines for AOI datasets on NVIDIA OSMO, coordinating USD asset management, dataset prep, image-edit augmentation, anomaly generation, and labeling to produce ready-to-use anomaly trees and training data.

Core Features & Use Cases

Supports Day 0 texture defects, Day 0 good-image, Day 0 structural defects, and Day 1 real alignment or manual ROI flows for PCBA, plus metal surface and glass use cases.
Handles per-board cookbooks, pretrained vs finetune modes, and outputs organized under the DIG URL root for reproducibility and traceability.
Provides preflight gates, memory rules, and monitoring hooks to ensure safe, repeatable runs in production.

Quick Start

Run a Day 0 texture defect flow using the shipped PCB dataset and in-cluster Image-Edit endpoint to produce the first anomaly-inference run.

Frequently Asked Questions about physical-ai-defect-image-generation

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I generate synthetic defect images for AOI training datasets?▼

You can generate synthetic defect images for AOI datasets by orchestrating an end-to-end AI pipeline that coordinates dataset preparation, image-edit augmentation, and anomaly generation to produce ready-to-use labeled training data.

What types of PCBA defects can AI defect image generation pipelines produce?▼

Defect image generation pipelines support Day 0 texture defects, Day 0 structural defects, Day 1 real alignment flows, and manual ROI PCBA defects, alongside metal surface and glass use cases.

How do I run a Day 0 texture defect generation flow on a PCBA dataset?▼

You run a Day 0 texture defect flow by using a shipped PCB dataset with an in-cluster Image-Edit endpoint to execute the anomaly-inference generation pipeline and produce initial anomaly tree outputs.

Does this AI defect generation pipeline support both pretrained and finetune modes?▼

Yes, the defect generation pipeline supports both pretrained and finetune pathways, utilizing per-board cookbooks to customize and standardize the anomaly generation process for different board configurations.

Can I use defect image generation for non-PCBA materials like metal and glass?▼

Yes, the AI defect image generation pipeline supports metal surface and glass use cases in addition to PCBA workflows, coordinating anomaly generation and labeling across these varied material types.

What preflight checks are required before running AOI anomaly generation?▼

AOI anomaly generation requires preflight gates, URL artifact validation, memory rules, and monitoring hooks to enforce standardized output layouts, ensuring safe, repeatable, and traceable production runs.