Who it's for
For newcomers who want to make pictures and short videos with AI, for a post, a slide or fun. You need no coding. The image lessons work on free plans, while the video lesson needs a Google AI plan and the ComfyUI lesson needs a fairly recent computer.
Lessons
- 1AI image prompts: how to get the picture you meantAI image prompts that work: say what the picture is for, name the subject, setting, style, framing and light, quote any words, then refine one change at a time.
- 2Nano Banana and ChatGPT: edit images with AIWhat Nano Banana is and how to edit images with AI in Gemini and ChatGPT: change one part of a photo, combine pictures and keep faces and logos intact.
- 3How to make AI videos with Gemini and Google FlowHow to make AI videos with Gemini Omni and Google Flow: describe one shot, set the camera and the sound, start from your own photo and know the clip lengths.
- 4ComfyUI tutorial: install Comfy Desktop and make your first imageA ComfyUI tutorial for beginners: install Comfy Desktop, open the text-to-image workflow, download its model, make a first image and learn the nodes.
Frequently asked questions
Is this AI images and video course free?
Yes. Every lesson is free to read. Some tools it covers need a paid plan, such as video in the Gemini app and Google Flow, and each lesson says which.
Which AI tools does the course use?
ChatGPT, Gemini with Nano Banana and Midjourney for pictures, the Gemini app and Google Flow for video, and ComfyUI for pictures made on your own computer. Button names and limits come from each vendor's help pages.
Why is there no Sora lesson?
OpenAI closed the Sora app in April 2026 and the Sora API in September, so the video lesson covers Google's tools instead and explains how former Sora users can export their videos.
Can I upload photos of other people?
Only with their consent and with the right to use the photo. Google and OpenAI both ask for that, and lessons 2 and 3 show where their rules apply.
What should I learn after this course?
The Design with AI course is next. It makes logos, social graphics, readable text in images and product mockups.