It doesn’t merge images. It generates them from scratch. Sure it’s trained on a corpus of existing images, but I don’t think it „merges“ them any more than human artists do with images they have seen in their lifetime.
> While our model can render a wide variety of text prompts zero-shot, it can can have difficulty producing realistic im ages for complex prompts. Therefore, we provide our model with editing capabilities in addition to zero-shot generation, which allows humans to iteratively improve model samples until they match more complex prompts. Specifically, we fine-tune our model to perform image inpainting, finding that it is capable of making realistic edits to existing images using natural language prompts.
Unless that only applies to GLIDE and not to DAL-E?
More like 'averaging them' and finding variations from vast inputs.
Which is more a long the lines of what I mean.