Prompt Engineering for Vision Models

About

A free DeepLearning.AI short course on how to prompt computer vision models with natural language, bounding boxes, segmentation masks, coordinate points, and other images.

• Covers zero-shot and few-shot prompting for vision models.
• Includes multi-image prompting techniques.
• Hands-on with bounding box and segmentation mask generation.
• Browser-based Jupyter notebooks for practical exercises.
• Specifically focuses on Google's PaliGemma vision-language model.