跳转到主要内容
2026/7/6 14:25 (UTC+8) · Docs Update · OpenAI / Google 📚 Agent Skills docs for the image APIs are now live To make it easy to hook the APIYI image APIs into Codex, Claude Code, OpenClaw and other coding agents, the docs center now ships two ready-to-use Agent Skills — each is just two files; drop one into your agent and generate images with a single sentence. Two skill pages (pick as needed):
  • GPT-Image-2 Series Agent Skill: one script covers all three channels — gpt-image-2 (official relay) plus gpt-image-2-all / gpt-image-2-vip (official-reverse) — switchable via --model, with text-to-image, multi-image fusion and inpainting
  • Nano Banana Pro Agent Skill: wraps gemini-3-pro-image (Nano Banana Pro) in a zero-dependency script for text-to-image and image editing
More image models will get the same skill pages over time — feedback welcome.
← Back to Live Updates · 📚 Monthly Archive