Introduction
DALL·E uses an autoregressive Transformer to model text and image tokens together, demonstrating broad compositional capabilities without task-specific examples. It makes the idea of producing a new image from a sentence publicly legible as a generative paradigm, connecting research in token modelling with a new interface to images.
View full image ↗Page 1 of the linked paper PDF, preserving its original figures and language. The source file identifies the edition; later revision or reprint dates do not replace the node’s historical date.
Aditya Ramesh; Mikhail Pavlov; Gabriel Goh; Scott Gray; Chelsea Voss et al. / OpenAI · original paper · Image rights remain with their respective holders; no open licence is asserted
Source · Zero-Shot Text-to-Image Generation ↗RESEARCH ACCOUNT
Modelling text and image tokens as one generative sequence.
ANTI-AI ARCHIVE · Revised 2026-10-02
Method and contribution
The DALL·E research paper combines text and image tokens into a single stream modelled autoregressively by a transformer. It studies zero-shot generation through scale rather than building a separate specialist system for each subject. Its publication follows the January 2021 announcement, so the two nodes represent different kinds of event.
Section sources: Zero-Shot Text-to-Image Generation
Art-historical interpretation
A joint sequence makes verbal description a generation condition, while outputs remain dependent on learned associations. Demonstrations of concept combination should be distinguished from documented artistic use, and announcements, papers and public services from one another.
Section sources: Zero-Shot Text-to-Image Generation
Sources for this account
Author or conference abstract and version record read; full proofs and experiments were not independently reproduced.
This account expands the archive within the cited scope. Historical interpretation is not presented as the original author’s statement or as a proven causal influence. The account and translation are AI-assisted, pending independent human review. Section references identify evidence without claiming independent verification of every historical statement.
Continue with a comparative question
Compare the methods, forms of control or presentation contexts of this entry and DALL·E announced.
Compare the methods, forms of control or presentation contexts of this entry and Hierarchical Text-Conditional Image Generation with CLIP Latents / DALL·E 2 product.
Dates & version record
Date displayed for this node: 2021-02 · Historical date recorded for the source: 2021-02
These dates refer to the historical event or recorded version, not this page’s publication date. The original date precision and unresolved questions are retained.
Original sources & further reading
These links lead to the cited paper, article, institution or conference page. External texts retain their source languages.
Zero-Shot Text-to-Image Generation
https://arxiv.org/abs/2102.12092
Current cited URL
Provenance, translation & verification
Timeline entry #120 · Historical node
Research materials & supplement references · 2
AI Art Genealogy Research Master · p. 23 · 075
Date as recorded: 2021-02
Zero-Shot Text-to-Image Generation ↗
Zero-Shot Text-to-Image Generation
GenAI Visual Release Chronology Research Master · p. 2 · R003
Date as recorded: 2021-02
Zero-Shot Text-to-Image Generation ↗
DALL·E — Zero-Shot Text-to-Image Generation
Archive account based on the listed research materials, not a full translation of the linked work. AI-assisted translation; independent human review pending.
The master’s research claims and dates await independent verification.
Cite this node
ANTI-AI ARCHIVE. Zero-Shot Text-to-Image Generation. Art-history node #120. https://salondesrefuses.cn/en/art-history/075
For specific historical claims, also cite the original sources above and include your access date. This account is not a full translation of the linked work.
Adjacent nodes follow chronological order; adjacency does not establish direct influence or causation.