skillfed

baoyu-imagine

baoyu-imagine generates images from text prompts across 10+ AI providers including OpenAI GPT Image 2, Google, Azure OpenAI, and others. It supports reference images for identity preservation, batch generation, custom aspect ratios, and quality presets, with flexible configuration via local or user-home settings.

baoyu-imagine generates images from text prompts using OpenAI, Google, Azure, and multiple other AI providers.

AI-generated summary based on this skill's SKILL.md

938 162 MIT updated by guanyang

Install

guanyang/open-agent-hub/baoyu-imagine · repository language: TypeScript

CLI (skillfed)coming soon
git clone https://github.com/guanyang/open-agent-hub
cp -r open-agent-hub/skills/baoyu-imagine ~/.claude/skills/baoyu-imagine

Frequently asked questions

AI-generated answers based on this skill's SKILL.md and metadata

How do I generate an image from text with baoyu-imagine?

baoyu-imagine generates images from text prompts using multiple AI providers including OpenAI GPT Image 2, Google, Azure OpenAI, and 10+ others. Simply provide your text prompt and select your preferred provider; the tool handles the API calls and returns your generated image.

Can baoyu-imagine create images with reference photos?

Yes. baoyu-imagine supports reference images to preserve identity during generation. You can provide a reference photo alongside your text prompt, and the tool will use it to guide the image generation process across supported providers.

Does baoyu-imagine support batch image generation?

baoyu-imagine creates multiple images in parallel batch mode for efficiency. This allows you to generate several images at once rather than one at a time, significantly speeding up workflows when you need multiple variations or outputs.

Which AI providers does baoyu-imagine work with?

baoyu-imagine supports 10+ AI image providers including OpenAI, Google, Azure OpenAI, Replicate, DashScope, and others. You can switch between providers based on your needs, API availability, and preferences.

Can I control image quality and aspect ratio in baoyu-imagine?

Yes. baoyu-imagine lets you control image quality, size, and aspect ratio during generation. You can set custom aspect ratios and quality presets through flexible configuration via local or user-home settings.

What license does baoyu-imagine use?

baoyu-imagine is released under the MIT license, allowing free use, modification, and distribution with minimal restrictions.

SKILL.md

rendered from the published skill — quoted content, verbatim

Image Generation (AI SDK)

Official API-based image generation. Supports OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope (阿里通义万象), Z.AI GLM-Image, MiniMax, Jimeng (即梦), Seedream (豆包) and Replicate.

User Input Tools

When this skill prompts the user, follow this tool-selection rule (priority order):

  1. Prefer built-in user-input tools exposed by the current agent runtime — e.g., AskUserQuestion, request_user_input, clarify, ask_user, or any equivalent.
  2. Fallback: if no such tool exists, emit a numbered

(truncated - see the full file via the links below)

Read as markdown · JSON record · Browse the source repository

File tree — 15 files
skills/baoyu-imagine/SKILL.md
skills/baoyu-imagine/references/codex-image2-fallback.md
skills/baoyu-imagine/references/codex-oauth-vs-openai-api-key.md
skills/baoyu-imagine/references/config/first-time-setup.md
skills/baoyu-imagine/references/config/preferences-schema.md
skills/baoyu-imagine/references/providers/dashscope.md
skills/baoyu-imagine/references/providers/minimax.md
skills/baoyu-imagine/references/providers/openrouter.md
skills/baoyu-imagine/references/providers/replicate.md
skills/baoyu-imagine/references/providers/zai.md
skills/baoyu-imagine/references/usage-examples.md
skills/baoyu-imagine/scripts/build-batch.test.ts
skills/baoyu-imagine/scripts/build-batch.ts
skills/baoyu-imagine/scripts/main.test.ts
skills/baoyu-imagine/scripts/main.ts

Related skills

Tags

api-integration multi-provider batch-processing reference-images quality-presets aspect-ratio-control concurrent-generation model-selection