From the course: Azure OpenAI: Generative AI Models and How to Use Them
Join today to access over 24,100 courses taught by industry experts.
How it works - Azure OpenAI Tutorial
From the course: Azure OpenAI: Generative AI Models and How to Use Them
How it works
- [Instructor] Converting text into images, it's not an easy process. So let's have a look how it's actually done and we're going to start back to embeddings. The first step that needs to be done is converting our prompt into a text embedding. The second step is sending that text embedding to the prior which is a process that will convert the text embedding into an image embedding. And once we have the image embedding we can send it to an image decoder which will generate the image we requested. Now, the text embedding that is used is not the classic text embedding that also is available in the Azure OpenAI service. The one that is used is called CLIP Contrastive Language Image Pre-training, which actually does the opposite of generating an image. It describes the image. Now CLIP is a clever AI model that can understand both images and text. It is trained in two parts, an image part, and a text part. In a training…
Practice while you learn with exercise files
Download the files the instructor uses to teach the course. Follow along and learn by watching, listening and practicing.
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.