Baoyu Image Gen

One CLI for AI image generation across a dozen providers (OpenAI, Google, DashScope, Replicate and more) with reference images and batch mode.

Image & VideoIntermediate★ 25,754⑂ 2,855AI score 10/10Last updated: Jul 4, 2026

What it does

Detects requests to generate, create, or draw images and runs the right provider CLI for you.
Supports OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate, Agnes and Codex CLI.
Controls aspect ratio (16:9, 1:1, 2.35:1...), quality presets (normal/2k), explicit pixel sizes, and image count.
Ships concrete identity-preservation prompting rules for reference images (--ref), including anti-beautification guidance and pitfalls that make models invent a new lookalike person.
Batch mode assembles saved prompt files into a JSON payload, runs them in parallel with per-provider throttling, retries each image up to 3 times, and reports successes/failures.
First run creates an EXTEND.md preference file storing your default provider, model, quality, and save location.

Who it's for

Content creators and marketers who switch between multiple image APIs.
Writers who need many article illustrations generated in one pass.
Anyone producing image series that must keep the same person, character, or product.
Developers comfortable with CLI flags and environment variables.

Examples

"Make a 16:9 high-quality cat illustration" → the skill runs with --ar 16:9 --quality 2k and reports the saved file path.
You already have outline.md plus a prompts/ folder from an article-illustration workflow → build-batch.ts builds the batch file and 4 workers generate all images in parallel.
You supply 2–4 portrait references and ask for "same person, winter coat, city street" → identity-preservation prompt rules keep the face intact instead of synthesizing a new subject.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/JimLiu/baoyu-skills/HEAD/skills/baoyu-image-gen/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)

Download the ZIP with the button below.
In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.

↓ Download ZIP

Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/baoyu-image-gen folder from the GitHub repo JimLiu/baoyu-skills into my ~/.claude/skills/baoyu-image-gen/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/JimLiu/baoyu-skills.git && mkdir -p ~/.claude/skills && cp -r baoyu-skills/skills/baoyu-image-gen ~/.claude/skills/

⚠ This is a third-party skill. Check the source repository before installing.

Install Bun: run curl -fsSL https://bun.sh/install | bash (or brew install oven-sh/bun/bun on macOS). If you already have Node, npx -y bun works too.
Clone the repository: git clone https://github.com/JimLiu/baoyu-skills.git
Copy the skill into your Claude skills folder: mkdir -p ~/.claude/skills && cp -r baoyu-skills/skills/baoyu-image-gen ~/.claude/skills/
Export an API key for at least one provider, e.g. export OPENAI_API_KEY=sk-... or export GOOGLE_API_KEY=... (you can also store them in ~/.baoyu-skills/.env).
Restart Claude Code and ask it to generate an image. The first run walks through a setup prompt for default provider, model, quality, and output folder, then writes EXTEND.md.
To change defaults later, edit ~/.baoyu-skills/baoyu-image-gen/EXTEND.md.

View source on GitHub ↗License: MIT