Revision History
Flow Matching · 8 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: Patrick Esser added to the Black Forest Labs founders
Version 8 · Nov 4, 2026, 09:09 PM
- Correction: Corrected the authors of the Google DeepMind 'Diffusion Meets Flow Matching' post, the description of Lipman et al.'s ImageNet results and of FM-diffusion equivalence, SD3's announcement date and formulation-study results (61 formulations, not eight), FLUX.1 [schnell]'s distillation method, Movie Gen's separate 13B audio model, and the false claim that Stable Audio Open is trained with flow matching (plus 7 minor fixes)
Version 7 · Nov 2, 2026, 07:01 AM
- Update: added a video.
Version 6 · Nov 1, 2026, 08:01 AM
- Improve internal links (2026-10-13)
Version 5 · Oct 13, 2026, 10:04 AM
- Added 6 contextual internal links
Version 4 · Jul 23, 2026, 03:33 PM