Introduction to image generation

A practical introductory course for creatives and innovators who want to create, edit and automate their own AI-generated visuals using tools such as Midjourney & Co.
Write your awesome label here.
With Felix Leber

Video duration

70 Minutes

Study Time

2 Hours

Skill-Level

Starter

Role

All Roles

What you will learn in this course:

In this practice-oriented introductory course, you will learn how modern image generation with AI works - from the basics of diffusion models to their application in tools such as Midjourney, ComfyUI, Stable Diffusion or Replicate. You will learn how to create, edit and automate high-quality visuals - including practical exercises, tool comparisons and prompts for your own projects.
  • How image generation works with diffusion and multimodal models
  • The differences and strengths of tools such as Midjourney, ComfyUI, Replicate or Fal.ai
  • How to control image ideas with Image References, ControlNets and Upscalers
  • How to integrate image generation into creative or automated workflows
  • And how to use these tools safely, creatively and efficiently for your professional practice

Chapter in this course: