← Back to Using AI
Lesson

AI Tools for Images, Video & Websites

How to use generative AI to help make images, video, and websites — and how to do it ethically, transparently, and responsibly. AI is a power tool: helpful in the right hands, dangerous in the wrong ones.

Time: one 75-min sessionFocus: what AI is good at, what it's not, and how to use it ethically
Overview

Why this matters

Goal: learn to use generative AI to help make images, video, and websites — ethically and responsibly. AI is now part of every working designer's toolkit.

Junior designers who refuse to learn it get out-shipped. Junior designers who use it without thinking get burned by copyright, factual errors, and ethical violations. The job is to use AI like a power tool.

Learning objectives

  1. Name the major AI tools for image, video, and website generation.
  2. Write a clear prompt that produces usable output.
  3. Apply five ethical guardrails to every project: disclose, verify, attribute, respect copyright, respect privacy.
  4. Spot the common failure modes: hallucination, bias, deepfakes, copyright entanglement.
  5. Use AI as a collaborator, not a replacement — the designer is still responsible for what ships.
Step 1

What “generative AI” means in 2026

Generative AI is software that creates new content — text, images, audio, video, code — from a written prompt. It learns patterns from massive amounts of data, then produces new outputs that match those patterns.

What AI is good at

  • Drafting starter content (copy, layouts, code scaffolding) you then edit
  • Generating placeholder imagery that fits a description
  • Brainstorming variations quickly
  • Explaining unfamiliar code, errors, or concepts
  • Summarizing and rephrasing text

What AI is bad at

  • Facts — it confidently makes things up (hallucination)
  • Real people — usually a copyright / consent violation
  • Original vision — it averages what already exists
  • Math, precise counting, fine layout, hand anatomy
  • Anything where lives or money depend on exact correctness
Step 2

The tools (a 2026 snapshot)

The landscape shifts constantly — but these are the ones to know. Almost all have a free tier for class work.

Image generation

Image-generation tools
ToolStrengthNotes
DALL·E 3 (in ChatGPT)General-purpose, follows complex prompts.Best for beginners. Free tier inside ChatGPT.
MidjourneyMost artistic / cinematic style.Discord-based; paid only (~$10/mo).
Adobe FireflyTrained on licensed content; safe for commercial use.Free with Creative Cloud. Important for production work.
Stable DiffusionFree & open-source, highly customizable.Via Leonardo / Civitai. Steeper learning curve.
Canva AIIntegrated with design templates.Easiest path from prompt to a finished post.

Video generation

Video-generation tools
ToolStrengthNotes
RunwayIndustry-leading short-clip generation.Free tier; great UI; 4–10 second clips.
Pika LabsQuick stylized clips from text or image.Free tier; Discord-based.
OpenAI SoraPhotorealistic up to 60-second clips.Paid; access limited.
DescriptEdit video by editing the transcript.AI-assisted editing, not generation.
HeyGenSpokesperson avatars from a script.Deepfake risk — only use with clear consent.

Website / code generation

Website-generation and AI-coding tools
ToolStrengthNotes
v0.dev (Vercel)Production-grade HTML + Tailwind from a prompt.Best output quality. Free tier.
ChatGPT / ClaudePair-programming, debugging, explaining code.Great for “why isn't this working?”
GitHub CopilotAutocomplete inside VS Code.Free with the Student Developer Pack.
CursorAI-first code editor (a VS Code fork).Free tier; fast for refactoring.
Lovable / Bolt / Replit AgentFull-stack “build me an app” agents.Great for prototypes; treat output as a draft.
Wix ADI / Hostinger AIDrag-and-drop builders with AI prompts.For non-coders. Learn HTML/CSS anyway.
Step 3

How to write a good prompt

The same tool gives different output depending on how you ask. Three habits make every prompt better:

  1. Be specific. “A hero photo” gives garbage. “A close-up of fresh pink peonies in a clear glass vase on a sunlit kitchen counter, shallow depth of field, warm morning light, editorial style” gives something usable.
  2. Describe the style. “Editorial,” “flat illustration,” “cinematic with film grain,” “mid-century poster.” Only reference real artists when their work is public-domain or you're licensed.
  3. Say what NOT to include. “No people, no text, no logos.” Negative prompts cut 80% of bad outputs.

Example — image prompt

A flat illustration of a coffee cup on a saucer, top-down view,
warm orange and cream palette, simple shapes, no text, no people,
soft drop shadow, mid-century editorial style. Aspect ratio 4:3.

Example — website-section prompt (v0 or Claude)

Generate an HTML + Tailwind hero section for a coffee shop called
"Wren & Pine." Include: brand name, 6-word tagline, one CTA button,
warm cream + dark green palette, mobile-first responsive, accessible
(semantic header, single h1, focus-visible ring). No JavaScript.
Output one HTML file only.
Iterate. Almost never accept the first output — tweak one thing and re-prompt. Two or three rounds usually gets to usable. Practice this on the Prompt Generator.
Step 4

The five ethical guardrails

Every project, every time.

1
Disclose

If AI helped make something you publish, say so — a line in your README, footer, or project notes (“Hero image generated with Adobe Firefly”). Hiding AI use is the fastest way to lose trust.

2
Verify

AI hallucinates. Every factual claim — a statistic, quote, library, citation — must be checked against a real source before you ship it.

3
Respect copyright

Use Adobe Firefly for commercial images (licensed training + indemnity). Don't prompt “in the style of [living artist].” Don't generate real, identifiable people.

4
Respect privacy & consent

Never feed an AI tool data that isn't yours to share — client contracts, medical info, private chats, photos of people who haven't consented. Most free tools keep your prompts.

5
Take responsibility

You're the designer. “The AI made that” is not a defense for a broken page, a biased image, a misquoted fact, or a copyright violation. Review everything.

Step 5

The failure modes to watch for

Common ways AI output goes wrong
FailureWhat it looks likeHow to defend
HallucinationConfident false facts, fake citations, made-up libraries.Verify everything against an authoritative source.
BiasDoctor = man, nurse = woman, “person” = white, stereotyped emotions.Read output critically; re-prompt for diversity.
Copyright entanglementOutput resembling a specific work or artist.Use Firefly for commercial work; never prompt by living artist.
DeepfakesRealistic video/audio of someone who didn't say it.Never depict real people without consent; watermark synthetic media.
Energy / water costLarge models have a real environmental footprint.Use the smallest model that works; don't regenerate 50 times.
Accessibility regressionsAI HTML often skips alt text, uses div soup, drops focus rings.Run AI code through your own accessibility checklist before shipping.
Step 6

A responsible workflow

Same for AI-assisted images, video, and code:

1 Plan first
2 Pick the right tool
3 Write a specific prompt
4 Iterate 2–3×
5 Edit by hand
6 Verify facts
7 Check accessibility
8 Disclose
9 Ship
Step 7

AI use in this class

AI is allowed, with one rule:

Disclose every AI-assisted asset on every assignment. A one-line note in your submission comments is enough (“Hero image generated with Adobe Firefly. Code reviewed by Claude.”). Undisclosed AI use is treated as a violation of academic integrity.

You may NOT use AI to

  • Generate the whole HTML/CSS for an assignment and submit it as your own
  • Write your reflection paragraphs
  • Generate images of real people without consent

You MAY use AI to

  • Generate placeholder images for your project
  • Help debug code you wrote yourself
  • Brainstorm palettes, copy, or layout ideas
  • Explain a concept you don't understand
  • Generate short illustrative clips (with disclosure)
Step 8

Resources

Accessibility

AI output is not automatically accessible

AI-generated images need your own alt text — the AI doesn't write it (and when it does, it's usually wrong). AI video needs captions and a transcript you verify by hand. AI-generated code routinely skips semantic HTML, paired form labels, and visible focus rings — you must add them. The Accessibility checklist applies to AI output just like anything else you ship.

Summary: use AI as a collaborator, not a replacement — plan first, write specific prompts, iterate, edit by hand, verify facts, fix accessibility, and disclose. Five guardrails: disclose, verify, respect copyright, respect privacy, take responsibility. In this class, AI is allowed; undisclosed AI use is not.

Created by Dr. G · Web Page Design I.
AI Disclosure: portions developed with assistance from Claude, then reviewed and edited for accuracy.

Where next

Keep going