The correct answers are A. Create images and D. Modify images.
The Azure OpenAI DALL-E model is a text-to-image generative AI model that can create original images and modify existing ones based on text prompts. According to Microsoft Learn and Azure OpenAI documentation, DALL-E interprets natural language descriptions to produce unique and creative visual content, making it useful for design, illustration, marketing, and educational applications.
* Create images (A) - DALL-E can generate new images entirely from textual input. For example, the prompt "a futuristic city skyline at sunrise" would result in a custom-generated artwork that visually represents that description.
* Modify images (D) - DALL-E also supports inpainting and outpainting, allowing users to edit or expand existing images. You can replace parts of an image (for example, changing a background or object) or add new elements consistent with the visual style of the original.
The remaining options are incorrect:
* B. OCR is performed by Azure AI Vision, not DALL-E.
* C. Detect objects in images is also an Azure AI Vision (Image Analysis) feature.
* E. Generate captions for images is handled by Azure AI Vision, not DALL-E, since DALL-E generates-not interprets-visuals.