Your First AI-Generated Project
Describe your vision in English. The agent builds it.
Overview
Now you're going to take a real open-source project, describe what you want in plain English, and let an AI agent transform it — generating custom illustrations with AI models hosted on Hugging Face, spoken narration with a free text-to-speech service, and a recoloured animated background.
No prior coding experience required. The agent adapts the project's own asset script to your topic, you read each diff, and you approve each command before it runs.
Make your bullet points visual. Each one will become an AI-generated image, so specific and concrete works better than abstract. 'A warehouse filled with rows of server racks' will generate a better illustration than 'technology infrastructure.'
— from the exercise
By the end of this exercise.
- ✓A forked copy of the Web Presenter project
- ✓A Hugging Face read token kept in the HF_TOKEN environment variable — never in a file or a prompt
- ✓Ten custom illustrations generated with FLUX via Hugging Face (covered by the free monthly credit)
- ✓Ten MP3 narration clips generated with edge-tts — no account or key needed
- ✓A customised Three.js animated background matching your colour palette
- ✓A complete presentation previewed locally and pushed to a branch on GitHub
Terms you'll learn.
- Hugging Face
- A platform hosting thousands of AI models — like GitHub but for machine learning
- Access token
- A secret key that proves your identity when calling the models — a read token is enough
- Environment variable
- A value that lives in your terminal session — keeps secrets out of code, Git and prompts
- Virtual environment
- A private folder of Python packages just for this project
- Text-to-image
- AI models that generate illustrations from plain English descriptions
- Text-to-speech
- Software that converts written text into spoken audio
- Diff
- The lines an edit added (+) and removed (-) — check it before anything runs
Sections in this exercise.
- 01What You'll Build
- 02What You'll Need
- 03Set Your Hugging Face Token
- 04Fork and Clone the Project
- 05Install the Python Packages
- 06Explore the Project
- 07Choose Your Topic
- 08Generate the Illustrations
- 09Generate the Narration
- 10Update the Presentation
- 11Customise the Animated Background
- 12Preview in Your Browser
- 13Commit and Push
You described a vision in plain English and an AI agent turned it into a working product — illustrations, narration, and an animated background. Just as important: you kept your token in the environment instead of the chat, read each diff before anything ran, and approved commands one at a time.