baoyu-image-gen

AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedre…

jimliu ↓ 30k

Claude Code

View source ↗

What it does

Found → load, parse, apply. If defaultmodel.[provider] is null → ask model only.
"Use the person/object in the reference image(s) as the same identity. Do not redesign it or create a similar-looking new subject."
If using multiple references, state that they are the same subject and should jointly define identity.
Prefer a small curated set of existing source references (usually 2–4) over many images; large multi-megabyte refs can destabilize streaming providers.
Do not use newly generated outputs as references unless the user explicitly asks; generated refs compound drift.
In Codex runtime: use the native imagegen skill/tool.
Using [provider] / [model]

Requirements & configuration

Codex CLI (uses logged-in Codex subscription — no OPENAIAPIKEY required; requires codex on PATH)
| --n <count> | Number of images. Replicate requires --n 1 (single-output save semantics) |
| OPENAIAPIKEY | OpenAI API key |
| AZUREOPENAIAPIKEY | Azure OpenAI API key |
| OPENROUTERAPIKEY | OpenRouter API key |

Configuration: HOMEOPENAI_API_KEYAZURE_OPENAI_API_KEYOPENROUTER_API_KEYGOOGLE_API_KEYDASHSCOPE_API_KEYZAI_API_KEYBIGMODEL_API_KEY

Derived from the skill's own SKILL.md documentation · extracted 2026-07-23

Source

Repository: https://github.com/jimliu/baoyu-skills

baoyu-image-gen FAQ

What does the baoyu-image-gen skill do?

AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs. Supports text-to-image, reference images, aspect ratios, and batch generation from saved prompt files. Sequential by default; use batch parallel generation when the user already has multiple prompts or wants stable multi-image throughput. Use when user asks to generate, create, or draw images. Found → load, parse, apply. If defaultmodel.[provider] is null → ask model only. "Use the person/object in the reference image(s) as the same identity. Do not redesign it or create a similar-looking new subject."

What does baoyu-image-gen require?

Codex CLI (uses logged-in Codex subscription — no OPENAIAPIKEY required; requires codex on PATH) | --n <count> | Number of images. Replicate requires --n 1 (single-output save semantics) | | OPENAIAPIKEY | OpenAI API key | | AZUREOPENAIAPIKEY | Azure OpenAI API key | | OPENROUTERAPIKEY | OpenRouter API key | Configuration keys: HOME, OPENAI_API_KEY, AZURE_OPENAI_API_KEY, OPENROUTER_API_KEY, GOOGLE_API_KEY, DASHSCOPE_API_KEY, ZAI_API_KEY, BIGMODEL_API_KEY.

How do I install baoyu-image-gen?

Run: npx -y skills add https://github.com/jimliu/baoyu-skills --skill baoyu-image-gen --agent claude-code — the source lives at github.com/jimliu/baoyu-skills.

Maintain baoyu-image-gen?

Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.

[![baoyu-image-gen on getagentictools](https://getagentictools.com/badge/skills/jimliu-baoyu-skills-baoyu-image-gen.svg)](https://getagentictools.com/skills/jimliu-baoyu-skills-baoyu-image-gen?ref=badge)

npx agentictools info skills/jimliu-baoyu-skills-baoyu-image-gen

The second line is the CLI lookup for this page — handy in READMEs and docs.