skilld
All skills
jimliu avatar

/baoyu-image-gen

@1567581 official
by Jim Liu 宝玉jimliu/baoyu-skills26k stars
2,896

AI image generation with OpenAI GPT Image 2.5, 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.

Ask your Agent

Use this Skill: https://skilld.dev/gh/jimliu/baoyu-skills/baoyu-image-gen

This session only. Nothing lands on disk.

referencesprovidersreplicate.md

≈454 tokens on demand. Your agent reads this file only when SKILL.md points to it.

Replicate

Read when the user picks --provider replicate. Replicate support is intentionally scoped to model families baoyu-image-gen can validate locally and save without dropping outputs.

Supported Families

google/nano-banana* (default: google/nano-banana-2)

  • Supports prompt-only and reference-image generation
  • Uses Replicate aspect_ratio, resolution, and output_format
  • --size <WxH> is accepted only as a shorthand for a documented aspect_ratio plus 1K / 2K

bytedance/seedream-4.5

  • Supports prompt-only and reference-image generation
  • Uses Replicate size, aspect_ratio, and image_input
  • Local validation blocks unsupported 1K requests before the API call

bytedance/seedream-5-lite

  • Supports prompt-only and reference-image generation
  • Uses Replicate size, aspect_ratio, and image_input
  • Local validation currently accepts 2K / 3K only

wan-video/wan-2.7-image

  • Supports prompt-only and reference-image generation
  • Uses Replicate size and images
  • Max output is 2K

wan-video/wan-2.7-image-pro

  • Supports prompt-only and reference-image generation
  • Uses Replicate size and images
  • 4K is allowed only for text-to-image; local validation blocks 4K + --ref

Guardrails

  • Replicate currently supports only single-output save semantics in this tool — keep --n 1
  • If a model is outside the compatibility list above, baoyu-image-gen treats it as prompt-only and rejects advanced local options instead of guessing a nano-banana-style schema

Examples

# Default model
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate

# Explicit model
${BUN_X} {baseDir}/scripts/main.ts --prompt "A cat" --image out.png --provider replicate --model google/nano-banana

Source: SKILL.md on GitHub

Third-party checks

1 alert16d5 checks · Risk SAFE
  • Gen Agent Trust Hub16d

    The skill facilitates official API-based image generation across various known providers (OpenAI, Google, Azure, OpenRouter, DashScope, Z.AI, MiniMax, Replicate, Agnes). Analysis confirmed no malicious operations, prompt injections, or dynamic code execution flaws.

  • Socket16d

    2 alerts: gptAnomaly, gptSecurity

  • Snyk16d

    Risk: LOW · No issues

  • Runlayer6mo

    2/9 files flagged

  • ZeroLeaks5mo

    1 finding · Score: 86/100

Provenance

Signed by skilld at 1567581. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated 3 weeks ago

Capability

version
2.2.0
Other metadata
metadata
{
  "openclaw": {
    "homepage": "https://github.com/JimLiu/baoyu-skills#baoyu-image-gen",
    "requires": {
      "anyBins": [
        "bun",
        "npx"
      ]
    }
  }
}

Topics

  • API
  • image-generation
  • openai
  • google
  • azure
  • replicate
  • text-to-image
  • batch-generation
  • multimodal

README badge

README badge for jimliu/baoyu-skills/baoyu-image-gen

What it does

Generates images via OpenAI, Google, Azure OpenAI, OpenRouter, DashScope, Replicate, and 5+ other APIs. Supports text-to-image, reference images, aspect ratios, and batch generation with configurable worker concurrency. Routes through a provider-agnostic CLI that requires Bun or Node.js and API credentials per provider.

Generated from the current SKILL.md.

Frequently asked

Which image generation APIs does this skill support?
OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate, Codex CLI, and Agnes.
Does this skill support reference images?
Yes, but support varies by provider. Google multimodal, OpenAI GPT Image edits, Azure OpenAI edits, OpenRouter multimodal, Replicate, MiniMax, and Seedream 4.0+ support references. Jimeng, Seedream 3.0, and most DashScope models do not.
Can I generate multiple images at once?
Yes. Use batch mode with `--batchfile` and `--jobs` for parallel generation, or the `--n` option for single-call multi-image requests (Replicate requires `--n 1`).
Do I need an OpenAI API key to use this skill?
Only if you use the `openai` provider or have it as your default. Other providers require their own API keys. If using Codex CLI without an OpenAI key, use `--provider codex-cli` instead.
Does this skill require bun or npm?
Yes, the skill requires either `bun` or `npx` to run the TypeScript scripts.

Generated from the current SKILL.md. These answers refresh after source changes.