A very preliminary analysis of DALL-E 2

By Gary F. Marcus, Ernest Davis, Scott Aaronson. 2022

177 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Computational Theory and Mathematics, Computer Vision and Pattern Recognition, Generative Models, Multimodal Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

In Computer Vision and Pattern Recognition

In Generative Models

In Multimodal Learning

Citations in the corpus

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding (2022, background): “[38] Set of challenging prompts “A pear cut into seven pieces arranged in a ring.”
Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models (2023, methodology): “However, even when employing this technique, extensive prompt engineering is often required to achieve the expected result [32,33,48,49].”
ChatGPT and a new academic reality: Artificial Intelligence‐written research papers and the ethics of the large language models in scholarly publishing (2023, background): “DALL-E is an ML technology that generates images based on user inputs and was made widely available to the public, preceding ChatGPT in its availability (Marcus et al., 2022).”
Unleashing the Power of Edge-Cloud Generative AI in Mobile Networks: A Survey of AIGC Services (2023, unknown): “For example, ChatGPT [10] allows conversational services that employ text as input and output, DALL-E 2 [40] can create original, realistic images from a text description, and AIGC services with”
Compositional Visual Generation with Composable Diffusion Models (2022, background): “However, such systems are not fully compositional in nature and generate incorrect images when given more complex descriptions [25, 41].”