Skip to main content
Back to module
Lesson 1 of 2

AI Image Generation

How Text-to-Image AI Works

1. Your text prompt is converted to numbers (embeddings)

2. AI starts with random noise

3. Gradually refines it into an image (50+ steps)

4. Guided by understanding of your text

The Prompt Formula

[Subject] + [Action/Pose] + [Environment] + [Style] + [Lighting] + [Quality] + [Mood]

Example:

"A young Ethiopian woman in traditional Tigray dress, pouring coffee from a jebena, in a rustic stone café with warm lantern light, oil painting style, soft focus, golden hour"

Ethiopian Prompt Ideas

  • "Lalibela churches in a futuristic Ethiopia, holographic prayers, cinematic"
  • "Ethiopian farmers using AI-powered drones over green teff fields, documentary style"
  • "Addis Ababa skyline in 2050, sustainable green architecture, utopian concept art"
Exercise10 points0 attempts

Which of the following is the most important factor for getting good results from AI image generators?