Introduction
A new architecture substantially improves coherence and aesthetics, showing the speed of closed-model iteration.
View full image ↗Midjourney V4 output in Justus Becker’s 2023 same-prompt experiment, a retrospective test of the 2022 version.
Justus Becker / Midjourney V4 · Rights remain with the respective holders; reproduction does not imply an open licence
Source · Midjourney's evolution: the same image in all five versions — JUSTUS BECKER ↗RESEARCH ACCOUNT
Multi-object composition and image prompting become central to version comparison.
ANTI-AI ARCHIVE · Revised 2026-10-02
Release and use
Released in November 2022, V4 is described by its developer as using a new architecture. Image prompting and multiple objects become important comparisons with earlier versions. Release and default adoption are distinct dates, not a single simultaneous change for every user.
Section sources: Midjourney V4
Change in creative practice
Moving from an atmosphere toward an organised scene allows more explicit compositional requests. Better model performance is not synonymous with full compositional control. Comparing V4 with earlier versions traces how decisions are distributed among language, reference images and the platform’s internal aesthetic tendencies.
Section sources: Midjourney V4
Sources for this account
Official release scope and demonstration descriptions read; vendor performance claims are not treated as independent test results.
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 2 research preview expands.
Compare the methods, forms of control or presentation contexts of this entry and Midjourney V5.
Dates & version record
Date displayed for this node: 2022-11 · Historical date recorded for the source: 2022-11
Month or year precision follows the master; an exact release date awaits independent verification.
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.
Midjourney V4
https://docs.midjourney.com/hc/en-us/articles/33329788681101-Legacy-Features
Current cited URL
This is the archive’s bilingual research abstract. The external link is an original source, not a claim that the publisher offers full text in both languages.
Provenance, translation & verification
Timeline entry #168 · Model / service
Research materials & supplement references · 1
GenAI Visual Release Chronology Research Master · p. 9 · R043
Date as recorded: 2022-11
Midjourney V4 ↗
Midjourney V4
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. Midjourney V4. Art-history node #168. https://salondesrefuses.cn/en/art-history/152
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.