Revision History
Text-to-Image Models · 11 revisions
Sizes are character counts of the article source. The signed number is the change from the previous revision.
Recent edit summaries
Detailed summaries recorded by editors. Generic maintenance summaries are omitted here; every recorded revision remains below. Dates describe the edit, not necessarily the event it covers.
- Correction: Corrected the energy figures from Luccioni et al., the HPSv2 author list, DALL-E's token count, Kolors' architecture, the release dates of HiDream-I1, Reve Image, Flux.1 Kontext and Midjourney V8.1, the Getty v. Stability AI trial date, a nonexistent 2025 Allen v. Perlmutter ruling, the length of Google's Gemini people-image pause, the claim that Qwen-Image 2.0 shipped open weights, the gpt-image-1 naming, Midjourney pricing, and Nano Banana user figures and app-store rankings that the cited source did not contain (plus 30 minor fixes)
Version 11 · Nov 2, 2026, 07:01 AM
- Update: added a video.
Version 10 · Nov 1, 2026, 08:00 AM
- References: renumbered 45 hidden references so they show and link
Version 9 · Oct 30, 2026, 09:45 AM
- Improve internal links (2026-10-13)
Version 8 · Oct 13, 2026, 10:06 AM
- Added 6 contextual internal links
Version 7 · Jul 23, 2026, 03:03 PM