Limited public betas in AI video release notes
A limited public beta opens a model to a restricted group of outside users before a wider release, so their feedback can shape it. As of 2026-09-25.
Adobe opened the Firefly Video Model this way in October 2024: text-to-video and image-to-video in a limited public beta on the Firefly website, with camera controls for angle, motion and zoom, and Generative Extend in the Premiere Pro beta. The new Firefly app with 1080p output followed in February 2025.
Other makers use preview for the same stage. Veo 3 was a preview in the Gemini API in July 2025, and LTX marked its async endpoints as a beta in May 2026.
Whatever the label, it tells a user the behaviour may change before the wider release, and that clips made during it may not be reproducible later.
| Date | Line | Version | What changed |
|---|---|---|---|
| 14 October 2024 | Adobe Firefly Video | Firefly Video Model | Text-to-video and image-to-video open in a limited public beta, with camera controls for angle, motion and zoom |
| 14 October 2024 | Adobe Firefly Video | Firefly Video Model | Generative Extend in the Premiere Pro beta lengthens clips to cover gaps and hold shots longer |
| 12 February 2025 | Adobe Firefly Video | Firefly Video Model | The model reaches 1080p output as it opens in the new Firefly app, with a faster ideation model planned |
| 17 July 2025 | Google Veo | Veo 3 | Veo 3 preview arrives in the Gemini API and generates sound with the picture |
| 3 May 2026 | LTX | Not named in the note | Async versions of every video generation endpoint, in beta |
Inclusion rule. Entries whose note uses or shows the term. Order. By date, oldest first; undated rows last.
1In the notes
With Text to Video, video editors can generate video from text prompts, access a variety of camera controls such as angle, motion and zoom to finetune videos
Adobe, news release: Firefly Video Model launch
Generative Extend allows you to extend clips to cover gaps in footage, smooth out transitions, or hold on shots longer for perfectly timed edits.
Adobe, news release: Firefly Video Model launch
The model now supports 1080p resolution for production-ready output, with a faster ideation model planned for a future release.
Adobe Blog, Meet Firefly Video Model
Launched veo-3.0-generate-preview , the latest update to Veo introducing video with audio generation.
Google, Gemini API changelog
Async API expanded to all video generation endpoints (Beta)
LTX, API changelog
- October 14Text-to-video and image-to-video open in a limited public beta, with camera controls for angle, motion and zoom2024
- October 14Generative Extend in the Premiere Pro beta lengthens clips to cover gaps and hold shots longer2024
- February 12The model reaches 1080p output as it opens in the new Firefly app, with a faster ideation model planned2025
- July 17Veo 3 preview arrives in the Gemini API and generates sound with the picture2025
- Async APIAsync versions of every video generation endpoint, in beta
2Other terms
3Notes read
- Adobe, news release: Firefly Video Model launch, read 2026-09-25
- Adobe Blog, Meet Firefly Video Model, read 2026-09-25
- Google, Gemini API changelog, read 2026-09-25
- LTX, API changelog, read 2026-09-25