Ai art wiki is a free online encyclopedia, created and edited by volunteers. If you see wrong or missing information, feel free to edit it. Guidelines

DALL-E

From AI art wiki
Jump to navigation Jump to search

DALL-E (stylized as DALL·E) and DALL-E 2 are deep learning models developed by OpenAI to generate digital images from natural language descriptions, called "prompts".

It can only generate 512x512 images.

Model
DALL-E
type Unknown model type
Dall-e2-examples.png
Official quote DALL·E 2 is a new AI system that can create realistic images and art from a description in natural language.
Links
License MIT
Description General-purpose model
NSFW no
Important tags

Comparisons to similar networks[edit | edit source]

Stable Diffusion[edit | edit source]

DALL-E seems to be more robust on general-purpose prompts.

DALL-E can't have higher resolution, while SD can.

SD has more extension.

Thatwilldo.jpg

Stub (unfinished article)

This article is unfinished.

Forks[edit | edit source]

RuDALL-e[edit | edit source]

RuDALL-e is fork of DALL-E that accepts prompts in Russian.