Composite real product photos into AI-generated scenes using Gemini.
npx skills add https://github.com/Dunc4nJ/agent-skills --skill image-refiner
Please help me install this Agent Skill. Skill: image-refiner Source: https://github.com/Dunc4nJ/agent-skills/tree/main/skills/image-refiner Command: npx skills add https://github.com/Dunc4nJ/agent-skills --skill image-refiner
Refine base scene images by compositing real product photos into AI-generated scenes, enabling photorealistic product placement for marketing, catalogs, and launches. This skill orchestrates base image input, metadata, S3 asset retrieval, and Gemini-based editing with a built-in human QC gate.
Provide a base image and its associated metadata then run the image-refiner workflow to output a refined image after QC.
High-intent search queries and answers about installing and using this skill.
Automate photorealistic product placement by compositing real product photos into AI-generated scenes using S3-stored references and Gemini-based editing with a built-in human QC gate.
Automated image refinement requires a base scene image and an associated metadata JSON file containing refiner_notes to guide the compositing process.
S3-stored reference photos support batch image refinement workflows, downloading product assets to composite into multiple base scenes with a QC gate between steps.
A human QC gate is required before saving refined images, ensuring the photorealistic product placement meets quality standards and updating metadata with approval status.
Gemini editing via agent-browser constructs a refinement prompt from downloaded S3 references and base image metadata to generate photorealistic product placement in AI scenes.
Track provenance for refined product launch visuals by updating the metadata JSON with the refined image path, reference assets used, and final approval status for auditability.
awsSecure S3 buckets with access control, encryption, logging, and monitoring.
mattmacleod16-svgInspect dimensions, retrieve metadata, convert formats, and resize images with ImageMagick.
TrimudAutomate browser tasks via CLI for navigation, form filling, and data extraction.
buda-aiGenerate multiple images from prompts with consistent styling.
