image

Generate images from text prompts via OpenAI DALL-E 3, Google Imagen 3, and xAI Aurora.

24|26|Updated Feb 14, 2026
One-click install
npx skills add https://github.com/hasna/skills --skill image-hasna
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image
Source: https://github.com/hasna/skills/tree/main/skills/skill-image
Command: npx skills add https://github.com/hasna/skills --skill image-hasna

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill allows users to generate images from text prompts using various AI providers, eliminating the need to learn complex image editing software or manage multiple APIs.

Core Features & Use Cases

  • Multi-Provider Support: Generate images using OpenAI DALL-E 3, Google Imagen 3, and xAI Aurora.
  • Customization: Specify models and sizes for tailored image generation.
  • Use Case: A marketer needs a unique image for a social media campaign. They can use this Skill to generate several options based on a descriptive prompt, choosing the best one.

Quick Start

Use the image skill to generate an image of a cat with the prompt 'a fluffy cat sitting on a windowsill' and save it to './cat.png'.

Frequently Asked Questions about image

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate images from text prompts using multiple AI providers?

You generate text-to-image outputs by providing a descriptive prompt to this Skill, which routes the request through OpenAI DALL-E 3, Google Imagen 3, or xAI Aurora. It processes the text and returns the generated image file for your creative applications.

Can I use DALL-E 3 and Google Imagen 3 in the same image generation workflow?

Yes, you can use DALL-E 3 and Google Imagen 3 within the same workflow through multi-provider support. This allows you to specify different models for text-to-image generation, enabling diverse creative outputs from a single interface.

Do I need API keys to generate AI art with this text-to-image tool?

Yes, you need specific API keys for each provider to generate AI art. The text-to-image generation process requires authenticating with OpenAI, Google, or xAI APIs to authorize the rendering requests and return the final images.

How do I configure custom sizes and aspect ratios for AI image generation?

You configure custom sizes and aspect ratios during the text-to-image generation process by specifying your desired dimensions in the prompt request. This allows tailored image outputs suitable for diverse practical formats like social media campaigns.

What is the best way to create marketing images from text descriptions without image editing software?

The best way to create marketing images without image editing software is using text-to-image generation. You input a descriptive prompt, the AI processes the text, and you receive unique visual assets ready for immediate download and use.

Does this image generation skill run natively using Bun APIs?

Yes, the image generation skill runs natively using Bun APIs for efficient execution. This ensures the text-to-image process handles API requests to providers like xAI Aurora and OpenAI DALL-E 3 with optimized performance.