The AI Engineer PathMultimodality
The module works with images in both directions: generating them from a prompt and asking a model to describe them. Its two downloadable projects, a movie-poster generator and a vision request, run in the browser against current OpenAI image and vision models. Both need the same Vite key change and OpenAI SDK update, and both make paid requests from the browser, so the guide is careful about which key you use.
These pages accompany the Multimodality module of Scrimba's AI Engineer Path. They don't replace the lessons; they hold the setup detail that changes faster than a recorded scrim can, so it can be corrected here instead of re-recorded.
The pages
Running Multimodality locally is for when you've downloaded the image-generation or vision project from the lesson menu and want it running on your own machine. It covers what to install first, how to prepare either project, replace its retired model and run it with a temporary OpenAI key, and the errors most learners hit on the way.
More pages for this module will be added here as they're written.
Looking for a different course?
Run an AI course project locally lists every course and project that has a setup guide.