Model Integration

Connect to and invoke image and video generation models across providers (Gemini / Nano Banana, fal.ai, Replicate, OpenAI GPT Image, xAI Grok Imagine) from an agent. Use this skill whenever a task needs to actually generate or edit an image or video and it is unclear which capability is available or how to call it — setting up API keys, detecting configured providers or MCP image tools, choosing the right model for a job (especially reference-following for style/character consistency), or writing the call. This is the execution layer the consistency skills delegate to when they say "invoke whatever image capability is available".

genielabsopensource Updated
Style drift: original character vs. off-model generations from two frontier image models, with the failures annotated — wrong art style, bad proportions, outlin

File contents

genielabsopensource/style-consistency-ai commit f4ba0bfeae

Frequently asked questions

npx get-skill add genielabsopensource/model-integration