A very preliminary analysis of DALL-E 2
This is an incremental analysis of an existing AI system's performance on challenging tasks, relevant for researchers and developers in generative AI.
The researchers tested DALL-E 2's ability to generate images from complex text prompts, finding that it fully satisfied requests for 5 out of 14 prompts with at least one image, but never produced ten fully satisfactory images for any prompt.
The DALL-E 2 system generates original synthetic images corresponding to an input text as caption. We report here on the outcome of fourteen tests of this system designed to assess its common sense, reasoning and ability to understand complex texts. All of our prompts were intentionally much more challenging than the typical ones that have been showcased in recent weeks. Nevertheless, for 5 out of the 14 prompts, at least one of the ten images fully satisfied our requests. On the other hand, on no prompt did all of the ten images satisfy our requests.