Is it possible to give dall e api input as a textual prompt and an image, and receive an image back? This is doable with GPT4, but not sure if this is possible with the api.
As of now, DALL·E’s API does not support directly combining a textual prompt with an image as input to generate an image in the same way that GPT-4 with Vision can process both text and images. DALL·E is primarily designed to generate images from textual prompts alone.