Introduction
BigGAN scales GAN training for class-conditioned ImageNet generation and improves image fidelity. It reinforces an observation that recurs in the foundation-model period: model size, data and computational scale can themselves contribute to generative quality. The historical argument concerns this scaling relationship, not an automatic equation of scale with artistic value.
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.
Brock, Donahue & Simonyan · original paper · Image rights remain with their respective holders; no open licence is asserted
Source · BigGAN ↗RESEARCH ACCOUNT
Fidelity and variety do not always increase together
ANTI-AI ARCHIVE · Revised 2026-10-02
Method and contribution
BigGAN investigates large-scale adversarial training and its instabilities. Orthogonal regularisation supports a truncation technique that changes the balance between sample fidelity and variety by restricting input variation. ImageNet results evaluate class-conditional synthesis, not open-ended artistic production.
Section sources: BigGAN
Art-historical interpretation
Editorial interpretation: higher quality may mean sharper, more typical or more varied outputs, and these need not coincide. An artist exploring unusual outputs may have different aims from a benchmark. Selection practices and evaluative criteria therefore belong in the historical record.
Section sources: BigGAN
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 Generative Adversarial Nets.
Compare the methods, forms of control or presentation contexts of this entry and Disco Diffusion notebook/system.
Dates & version record
Date displayed for this node: 2018 · Historical date recorded for the source: 2018
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.
Provenance, translation & verification
Timeline entry #097 · Historical node
Research materials & supplement references · 1
AI Art Genealogy Research Master · p. 19 · 060
Date as recorded: 2018
BigGAN ↗
BigGAN
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. BigGAN. Art-history node #097. https://salondesrefuses.cn/en/art-history/060
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.