Open Skills Logo
Open Skills

baoyu-image-gen

AI image generation with OpenAI, Google and DashScope APIs. Supports text-to-image, reference images, aspect ratios. Sequential by default; parallel generation available on request. Use when user asks to generate, create, or draw images.

Author

@JimLiu

Category

Image Processing

Install

Hot:5

Download and extract to your skills directory

Copy command and send to OpenClaw for auto-install:

Download and install this skill https://openskills.cc/api/download?slug=jimliu-skills-baoyu-image-gen&locale=en&source=copy

baoyu-image-gen - Multi-Platform AI Image Generation Tool

Skill Overview


An AI image generation tool based on official APIs. It supports three major platforms: OpenAI, Google Imagen, and Alibaba Tongyi Wanxiang. With a single command, it can handle various image creation tasks such as text-to-image and reference-image-based generation.

Suitable Use Cases

  • Rapid Content Creation

    • Quickly generate cover images for blog posts, social media, and marketing materials. Supports multiple aspect ratios (16:9, 1:1, 9:16, etc.) and automatically matches different platforms’ display requirements.

  • Iterative Creative Work from Reference Images

    • Modify and recreate based on existing images. Supports using reference images to guide the AI to generate new works with similar style or content—ideal for product iterations and design variants.

  • Batch Image Production

    • When you need large numbers of images with a similar style, you can choose sequential or parallel generation modes as needed. Suitable for batch-making cover images, icon sets, or test data.

    Core Features

  • Multi-Platform API Support

    • A unified interface for calling OpenAI, Google Imagen, and Alibaba Tongyi Wanxiang. It automatically selects available API keys, or you can manually specify the provider and model.

  • Flexible Image Configuration

    • Supports custom aspect ratios (1:1, 16:9, 4:3, etc.), sizes (1K/2K/4K), and quality presets—covering needs from quick previews to high-resolution outputs.

  • Reference Image & Multimodal Generation

    • Supports uploading reference images and using Google multimodal capabilities or OpenAI Edits to generate new images. You can also read prompts from multiple files, making it easy to reuse complex copy templates.

    Frequently Asked Questions

    How do I use baoyu-image-gen to generate images?


    After configuring the corresponding API key, run the command:
    npx -y bun ${SKILL_DIR}/scripts/main.ts --prompt "描述" --image 输出.png
    to generate the image. You can also specify the provider (OpenAI, Google, or DashScope) using the --provider parameter.

    What image sizes and aspect ratios are supported?


    Supported preset aspect ratios include 1:1, 16:9, 9:16, 4:3, 3:4, and 2.35:1. You can also customize pixel dimensions using the --size parameter (e.g., 1024x1024). Quality presets are normal (1K) and 2k (2048px).

    Can I generate multiple images at once?


    By default, it uses sequential mode to generate one image at a time to ensure stability. For batch generation, use the --n parameter to specify the quantity and clearly set the parallel request mode. The system will launch multiple subtasks for concurrent processing.