baoyu-image-gen
๐ฏSkillfrom jimliu/baoyu-skills
|AI SDK-based image generation skill supporting OpenAI, Google, and DashScope providers with text-to-image generation, reference images, aspect ratio control, and quality presets through a unified slash command interface.
Overview
Baoyu Image Gen is an AI SDK-based image generation skill for Claude Code that supports multiple providers including OpenAI, Google, and DashScope (Aliyun Tongyi Wanxiang). It enables text-to-image generation with features like reference images, aspect ratio control, and quality presets, all accessible through a simple slash command interface. Part of the jimliu/baoyu-skills collection, it provides a unified interface across different AI image generation backends.
Key Features
- Multi-Provider Support: Works with OpenAI, Google, and DashScope (Aliyun Tongyi Wanxiang) APIs with automatic provider detection based on available API keys
- Flexible Image Options: Supports custom aspect ratios (e.g., 16:9, 1:1, 4:3), quality presets (normal and 2k), and specific output sizes
- Reference Image Support: Google multimodal mode allows using reference images to guide generation (e.g., "Make it blue" with a source image)
- Prompt File Input: Can read prompts from files using --promptfiles, enabling complex multi-file prompt compositions
- Customizable Endpoints: Supports custom base URLs for each provider, allowing use with compatible API proxies
Who is this for?
- Developers who want to generate images directly from Claude Code without switching to external tools or web interfaces
- Content creators and designers who need quick image generation with fine-grained control over providers, aspect ratios, and quality levels
- Teams working with Chinese AI platforms (DashScope/Tongyi Wanxiang) who need a unified interface alongside OpenAI and Google providers
Same repository
jimliu/baoyu-skills(23 items)
Installation
npx vibeindex add jimliu/baoyu-skills --skill baoyu-image-gennpx skills add jimliu/baoyu-skills --skill baoyu-image-gen~/.claude/skills/baoyu-image-gen/SKILL.mdSKILL.md
More from this repository10
A Claude Code skill for publishing content to WeChat Official Accounts, supporting article posting via API/browser and image-text posting with up to 9 images, with configurable preferences and a structured 7-step publishing workflow.
A Claude Code skill that analyzes articles, identifies optimal illustration positions, and generates images using a Type x Style two-dimensional system with 6 types and multiple visual styles.
A Claude Code skill that generates article cover images using a 5-dimensional system (Type, Palette, Rendering, Text, Mood) with 9 color palettes and 6 rendering styles for 54 unique combinations.
A Claude Code skill that transforms written content into professional slide deck images with 16 visual style presets, smart content scaling, and multi-language support.
A Claude Code skill that generates Xiaohongshu (RedNote) infographic card series from content using a Style x Layout 2D system with 9 visual styles and 6 layout types.
A collection of Claude Code skills for content generation including Xiaohongshu infographics, slide decks, comics, cover images, and social media publishing to X and WeChat.
A Claude Code skill that converts X (Twitter) tweets, threads, and articles into Markdown with YAML front matter, supporting media downloads, customizable output paths, and consent-based access to a reverse-engineered X API.
Agent skill for posting text, images, and long-form Markdown articles to X (Twitter) directly from Claude Code using Chrome CDP, part of Baoyu's cross-platform content publishing suite.
Generates professional infographics by combining 20 layout types (bento-grid, funnel, timeline, etc.) with 17 visual styles (craft-handmade, cyberpunk, pixel-art, etc.), with auto-recommended combinations based on content analysis.
Interacts with Gemini Web to generate text and images directly from Claude Code. Supports text prompts, prompt files, and image output as PNG files.