DALL·E
DALL·E generates images from text.
Why it matters
It illustrated text-conditioned image generation with a Transformer-based model.
The announcement demonstrates examples; it is not an independent quality benchmark.
Announcement · January 2021
Event record
- Event date
- January 2021
- Timeline date
- Event date
- Verification
- Sources gathered automatically · September 11, 2026
- Lines
- ID
- evt-0016
Sources
- primary DALL·E
OpenAI · Published January 2021
Related events
- Related Diffusion models
Both records concern generative image models; that paper is earlier work in the field, not the basis of this particular model.
Records that link to this one
- Contrasts Stable Diffusion
The same task, but with the weights released openly.
High-Resolution Image Synthesis with Latent Diffusion Models - Builds on DALL·E 2 opens in a paid beta
OpenAI presents DALL·E 2 as the successor to the DALL·E of January 2021, at four times the resolution.
DALL·E 2