Prompt to Picture: Creating Images with AI

Lesson 0:

Assignment
Reflection Task (150–200 words):

Why are you interested in creating images with AI?
Which medium (photography, illustration, 3D, mixed media) excites you the most to explore in this course?
Upload your reflection to the course forum (Slack) or keep it in your prompt journal for later comparison.

I’m interested in:

• exploring the current capabilities of the technology
• applying editing techniques in commerical photography. Specifically for:
  • removing distractions
  • noise reduction
• generating design ideas for websites
• generating series of images for design mockup purposes in order to:
  • engage clients
  • fit better with new designs than their own old snaps
  • lead to better briefing of photo assignments

Lesson 1:

Exploration Task:

Choose two different AI image platforms (e.g., MidJourney + Stable Diffusion, or GPT-5 + Firefly).
Generate one image in each platform using the same prompt.
Compare the results in 150–200 words:
How do they differ in style, realism, or usability?
Which one would you use for your own creative projects, and why?

Chosen platforms:

1. Gemini Nano Banana
2. Z-Image Turbo (Mage.space)
3. Chat-GPT 5
4. Gemini 3 Pro
5. Google Imagen 4
6. Firefly 4 (Didn’t seem to understand the brief)

Gallery: