Describe image generation capabilities of Azure OpenAI Service
In the Azure OpenAI Service realm, image generation capabilities can take several forms, such as prompts to create a new image or a customization of a base image.
DALL-E is the model family that generates images based on text prompts. The more detailed the prompt, the better the results. You can even request images in specific styles, such as a dog in the style of Salvador Dali, a pastoral scene that includes pizza in the style of Claude Monet, or a steampunk farm tractor:
Figure 11.24 – Viewing DALL-E generated images in the playground
Depending on the application code surrounding the model deployment, you can also submit edits such as add a person sitting in the tractor seat or update the dog so that it’s wearing a hat. The current models don’t allow for editing or modifying the produced images; rather, you’re generating new images with the updated prompt parameters...
