…[SNIP]… Recently DALL-E’s creators have been signaling they will soon open access to DALL-E’s API. Undeniably, this API release will produce various innovative applications. But even before that, DALL-E is already proving to be a stepping stone in AI research. Its novelty lies in the way it was trained – with both text and vision stimuli, unlocking promising new directions of research in a re-emerging field called multimodal AI . [Source]
I can’t wait to see what DALL-E can do with my GPT-3 generated magic items and monsters…
We appreciate the excitement, but I’m not sure where that article got its source from, as we haven’t announced any plans for releasing DALL-E at this time.
Author of the article here.
This piece was written a couple of months ago when OpenAI sent out a survey for early DALL-E and CLIP access, hence the “signalling about opening access”.
Although there is some work happening to create an open-source alternative, I do hope DALL-E will end up as part of OpenAI’s API.