Any solution to create new images from seed image

[zhangligao]

I find that in chat page I could create a new image base on uploaded seed image:

I am wondering if we could do same thing by calling a API?
I checked Dall·E documents, seems it not supports my use case:

1. Creating images from scratch based on a text prompt (DALL·E 3 and DALL·E 2)
2. Creating edited versions of images by having the model replace some areas of a pre-existing image, based on a new text prompt (DALL·E 2 only)
3. Creating variations of an existing image (DALL·E 2 only)

[matcha72]

You can probably ask GPT-4-Vision api to generate a description of the image and feed that description to generate an image