Image generation is the sub-type of genAI that creates visual outputs, with popular tools including Midjourney, Stable Diffusion and DALL-E. Image genAI tools are also now integrated into common design softwares, such as Adobe and Canva. The video below from Google provides a great introduction to how image generation works:
Google Cloud Tech’s 9 min video on specifically on GenAI for images
Google Cloud Tech’s 9 min video on specifically on GenAI for images
While various image generations have similar capabilities and strategies for prompting, there are variations across the board. This project primarily uses Midjourney for the following reasons:
Ready to see image generation in action? Check out the following page, which includes generated images, sample prompts, and a screen recording of using Midjourney to create a fantasy map.
Artefact 1: Map & Life in Those Places
Created with Midjourney (core image), Adobe Express (added a color filter), and Adobe Firefly- AI Beta (to inpaint- aka change one section of the photo).
<aside> 🗞️ Favorite Learning Resources
Graphic from https://www.craiyon.com/blog/how-to-write-the-best-prompts-for-ai-art-generators
Chart of popular Midjourney styles, compiled by **@robomar.ai.art* and found on https://weirdwonderfulai.art/resources/midjourney-style-chart-by-robomar-ai-art/*
<aside> 🧭 Notebook Navigation 🔊Listen in for an explanation (audio file) 🤖 Working with GenAI tools 💡 World ideation points 🎙️ Notes from interviews with experts ✍🏼 📹 🎭 Sample snippet of potential content in different forms
</aside>
Following this link to the next recommended page:
<aside> Create Your Own Work
</aside>
<aside> Learn about GenAI
</aside>
<aside> GenAI in Action
Artefact 2: Magical Knitted “Armor”
Artefact 3: Folk Song Turned Musical Theatre Concept
</aside>