-
Book Overview & Buying
-
Table Of Contents
-
Feedback & Rating

Practical Generative AI with ChatGPT
By :

With the advent of GPT-4 Vision and the following GPT-4o, we witnessed a huge acceleration in the field of multimodality, since these models are capable of processing both images and natural language. However, they were only able to produce text (including code, of course) as output. With the integration of DALL-E 3 into the ChatGPT experience, we now have an AI system that is capable of interacting with us with images and text (and, for the sake of completeness, also with audio) both in input and output.
Let’s see some concrete applications of that.
Let’s say that we work in the world of fashion, and we are asked to produce blog content around the latest trends as well as come up with new fashion ideas. We recently attended a fashion event and took some pictures as possible inspiration. Let’s see how ChatGPT can assist us in that: