Summary

In this chapter, you have learned about vision transformers and how to use them for various tasks. Semantic segmentation, object detection, and classification were a few of these tasks. You also gained knowledge about text and visual prompt models, which can take a prompt as input and provide the outputs. Models such as DETR, ViT, and CLIPSeg were described in this chapter.

In the next chapter, you will learn about multimodal models, such as Stable Diffusion, and how they work.