Prompting

Describe images (Alt-Text)

Image models can describe images. For example:

1. Model: GPT-4o-Mini
2. Upload an image
3. User message: "Describe the image for a blind person. Follow the WCAG guidelines for alt-text."

Compare images

Image models can compare the difference between images. For example:

1. Model: GPT-4o-Mini
2. Upload 2 images
3. User message: "Compare these 2 similar images. Describe both images in detail, including every word used. Then explain the difference between the two visuals (including every word) to a blind person in a structured way."