AWhat changed
Trained a 12-billion-parameter autoregressive transformer over text and image tokens and demonstrated text-conditioned image synthesis and concept combinations.
Scientific scope
Trained a 12-billion-parameter autoregressive transformer over text and image tokens and demonstrated text-conditioned image synthesis and concept combinations. Scope limitation: This is the first DALL·E model, not DALL·E 2's unCLIP diffusion pipeline. Examples and reported evaluations are specific to the paper.
Evidence
The retained primary-source abstract, bibliographic record and stated review scope support this provisional assessment. No independent experimental replication by WRS is claimed. This is the first DALL·E model, not DALL·E 2's unCLIP diffusion pipeline. Examples and reported evaluations are specific to the paper.
Contributors
- The named authors listed in the linked research record · SCIENCE: Complete source byline retained in the research record; human research direction, method development and evaluation. Individual labor shares are not measured.
- Ramesh and colleagues: original DALL·E text-to-image generation — original paper
- Ramesh and colleagues: original DALL·E text-to-image generation — company research page
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction