Generates images through OpenAI, Google, DashScope, and Canghe APIs with support for text-to-image, reference images, and aspect ratios. Ships with sensible defaults (2K quality, Google provider) but you can override everything through CLI flags or EXTEND.md preferences. Reference image support is the standout feature here, working across Google's multimodal models, OpenAI's GPT Image edits, and Canghe. Runs sequential by default, which is the right call for stability, but switches to parallel generation when you actually need it. The quality presets and aspect ratio handling save you from looking up provider-specific parameters every time.
npx skills add https://github.com/freestylefly/canghe-skills --skill canghe-image-gen