VideoGenReview

What each AI video model's release notes say changed

What a missing note does and does not mean

No note is not the same as no change. A maker can ship a feature without writing it down, or write it on a page not read here. The register covers the notes read; its gaps are gaps in the notes. As of 2026-09-25.

Where this note's examples come fromThe examples in this note come from 3 entries across 2 model lines.ExamplesMidjourney video2 entriesSeedance1 entry
Fig. 1 Each example links to its line page.

Midjourney's update blog shows four video posts in the summer of 2025 and none with video in the title after that. That says the blog stopped writing about video, not that the model stopped changing. Likewise, Seedance's lack of dated maker notes is a fact about where ByteDance publishes, not about the model.

When a feature matters to a project, the safer reading is the maker's current documentation for what exists today, and the notes for when it arrived.

The entries this note draws on, read 2026-09-25.
DateLineVersionWhat changed
18 June 2025Midjourney videoMidjourney V1 videoThe V1 video model animates images, with low or high motion and extensions of about 4 seconds
13 August 2025Midjourney videoMidjourney V1 videoHD video opens to the Standard plan and smaller batches arrive
Undated version rowSeedanceSeedance 1.0 ProSeedance 1.0 Pro: 2 to 12 seconds, up to 1080p, first and last frames

Inclusion rule. Entries used as examples in this note. Order. By date, oldest first; undated rows last.

1In the notes

Once you have a video you like you can “extend” them - roughly 4 seconds at a time - four times total.

Midjourney, V1 video model announcement

HD video generation is now available for Standard Plan users

Midjourney, new video options announcement

Duration: 2–12 s

BytePlus ModelArk, model list

2Other reading notes

3Notes read