VideoGenReview

What each AI video model's release notes say changed

New AI video models and snapshots, by date

70 entries on a new model or snapshot from 17 of the 17 lines, dated 1 July 2024 to 18 September 2026. The table lists each with its line and version; the chart counts them per line. As of 2026-09-25.

1Reading the notes

Every line has at least one entry here, because a new model or a new dated snapshot is the one change every maker announces. The register counts a snapshot, such as Wan 2.7's dated text-to-video builds or the newer model behind OpenAI's sora-2 name, as its own entry: the behaviour behind the same name changed on that day. Arrivals on Runway, Higgsfield and Luma are kept too, since for many users the day a model reaches the tool they already pay for is the day it launches.

Entries on new model per lineCounted from the table. Lines without an entry of this kind are left out.Entries on new model per lineKling AI1010Wan1010Runway99MiniMax Hailuo55PixVerse55Gemini Omni44Google Veo44Seedance44Grok Imagine33LTX33Luma Ray33Amazon Nova Reel22HappyHorse22Sora22Vidu22Adobe Firefly Video11Midjourney video11
Fig. 1 Counted from the table. Lines without an entry of this kind are left out.
Entries on a new model or snapshot per line, read 2026-09-25.
LineEntries
Adobe Firefly Video1
Amazon Nova Reel2
Gemini Omni4
Google Veo4
Grok Imagine3
HappyHorse2
Kling AI10
LTX3
Luma Ray3
Midjourney video1
MiniMax Hailuo5
PixVerse5
Runway9
Seedance4
Sora2
Vidu2
Wan10

Inclusion rule. Lines with at least one entry of this kind. Order. Alphabetical by line.

2Every entry

Every entry on a new model or snapshot, oldest first.
DateLineVersionWhat changed
1 July 2024RunwayGen-3 AlphaGen-3 Alpha text-to-video, described as a step up in fidelity, consistency and motion
14 August 2024RunwayGen-3 Alpha TurboGen-3 Alpha Turbo: faster and cheaper than Gen-3 Alpha
14 October 2024Adobe Firefly VideoFirefly Video ModelText-to-video and image-to-video open in a limited public beta, with camera controls for angle, motion and zoom
25 October 2024RunwayAct-OneAct-One drives a character from one performance video and one image
15 November 2024Kling AIKling 1.5Kling 1.5 Pro opens in the API for image-to-video only
3 December 2024Amazon Nova ReelNova Reel 1.0Nova Reel launches in Amazon Bedrock for short videos from text and images, with control of style and pacing
7 January 2025Kling AIKling 1.6Kling 1.6 launches, without tail frame, motion brush or camera control at first
9 January 2025WanWan 2.1Wan 2.1 text-to-video Plus, with large movements and physical plausibility named
11 February 2025MiniMax HailuoHailuo DirectorThe Director models follow camera movement instructions more closely
1 April 2025RunwayGen-4Gen-4 is released for paid plans
7 April 2025Amazon Nova ReelNova Reel 1.1Nova Reel 1.1 improves quality and latency for 6-second single-shot clips over Nova Reel 1.0
9 April 2025Google VeoVeo 2Veo 2 becomes generally available in the Gemini API for text and image input
13 May 2025Kling AIKling 2.0Kling 2.0 Master for text-to-video and image-to-video
18 June 2025MiniMax HailuoHailuo 02Hailuo 02 generates 1080p and clips of up to 10 seconds
18 June 2025Midjourney videoMidjourney V1 videoThe V1 video model animates images, with low or high motion and extensions of about 4 seconds
19 June 2025Kling AIKling 2.1Kling 2.1 image-to-video in standard and pro modes, plus a 2.1 Master
17 July 2025RunwayAct-TwoAct-Two tracks head, face, body and hands
17 July 2025Google VeoVeo 3Veo 3 preview arrives in the Gemini API and generates sound with the picture
28 July 2025WanWan 2.2Wan 2.2 text-to-video Plus names complex movement and cinematic control
31 July 2025RunwayAlephAleph, a model for editing and transforming video, opens to paid plans
29 August 2025PixVersePixVerse V5The V5 model is released
18 September 2025Luma RayRay3Ray3 adds reasoning, native HDR EXR output and a Draft Mode
23 September 2025WanWan 2.5Wan 2.5 preview generates synchronised audio and 10 second clips
24 September 2025ViduVidu Q2Vidu Q2 Pro and Q2 Turbo for image-to-video and start-and-end frames
6 October 2025SoraSora 2The API gains a videos endpoint for Sora 2 and Sora 2 Pro
15 October 2025Google VeoVeo 3.1Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input
20 October 2025Kling AIKling 2.5 TurboKling 2.5 Turbo for text-to-video and image-to-video, pro mode
28 October 2025MiniMax HailuoHailuo 2.3Hailuo 2.3 and a 2.3 Fast tier, with body movement, faces and physics named as the gains
29 October 2025LTXNot named in the noteThe LTX API opens with text-to-video and image-to-video
2 December 2025PixVersePixVerse V5.5V5.5 is released
3 December 2025WanWan 2.6Wan 2.6 text-to-video plans several shots inside one clip of up to 15 seconds
11 December 2025RunwayGen-4.5Gen-4.5 is released for all paid plans
15 December 2025Kling AIKling 2.6Kling 2.6 launches with a switch for generating sound
15 December 2025Kling AIKling OmniThe Omni video model launches on a new API driven by prompt words
13 January 2026SoraSora 2The sora-2 name now points to a December 2025 snapshot; the October snapshot stays callable
26 January 2026Luma RayRay3.14Ray3.14 brings native 1080p and faster, cheaper 720p than Ray3
26 January 2026PixVersePixVerse V5.6V5.6 is released
28 January 2026Grok ImagineNot named in the noteVideo generation opens in the xAI API
31 January 2026Kling AIKling 3.0Kling 3.0 is fully rolled out in the app
5 March 2026LTXLTX-2.3LTX-2.3 becomes the default model in two variants
29 March 2026PixVersePixVerse V6V6 covers text-to-video, image-to-video, transition and extend
31 March 2026Google VeoVeo 3.1 LiteVeo 3.1 Lite preview is released as a lower-cost tier for high-volume use
3 April 2026WanWan 2.7Wan 2.7 text-to-video and image-to-video, with rhythmic cuts named
7 April 2026PixVersePixVerse C1The C1 model covers text, image, transition and reference-to-video
7 April 2026SeedanceSeedance 2.0Seedance 2.0 reaches Runway on Unlimited and Enterprise plans outside the US
22 April 2026HappyHorseHappyHorse 1.0HappyHorse 1.0 text-to-video and image-to-video are listed
26 April 2026WanWan 2.7A dated Wan 2.7 text-to-video snapshot from 25 April 2026
21 May 2026RunwayAleph 2.0Aleph 2.0 edits a whole clip to match one edited frame
9 June 2026Luma RayRay3.2Ray3.2 adds frame-level control over how action moves
16 June 2026HappyHorseHappyHorse 1.1HappyHorse 1.1 text-to-video names shot control and motion rendering
17 June 2026Kling AIKling 3.0 TurboKling 3.0 Turbo for text-to-video and image-to-video at 720p and 1080p
29 June 2026Gemini OmniGemini Omni FlashGemini Omni Flash arrives on Higgsfield
30 June 2026Gemini OmniGemini Omni FlashGemini Omni Flash preview makes 3 to 10 second clips at 720p and edits them in conversation
30 June 2026Gemini OmniGemini Omni FlashGemini Omni Flash arrives in Runway
1 July 2026WanWan 2.7A second dated Wan 2.7 snapshot, from 12 June 2026
31 July 2026Grok ImagineGrok Imagine 1.5Grok Imagine video 1.5 adds reference-to-video with preset voices and native 1080p
31 July 2026MiniMax HailuoMiniMax H3MiniMax H3 reads text, image, video and audio together as creative context
5 August 2026MiniMax HailuoHailuo 3.0Runway's developer API adds a model it names MiniMax Hailuo 3.0
6 August 2026SeedanceSeedance 2.5Seedance 2.5 arrives on Higgsfield with clips up to 30 seconds
6 August 2026SeedanceSeedance 2.5Seedance 2.5 arrives on Luma with 30-second single-pass generation
6 August 2026WanWan 3.0Wan 3.0 folds reference, editing, replication and driving into one model, with clips up to 30 seconds
11 August 2026LTXLTX-2.5LTX-2.5 models in portrait and landscape, with the fast one up to 4K
11 August 2026SeedanceSeedance 2.5Seedance 2.5 reaches Runway through its MCP, up to 30 seconds
13 August 2026Grok ImagineGrok Imagine 1.5Grok Imagine 1.5 reaches Runway's MCP, 1 to 15 seconds with audio
20 August 2026RunwayRunway RubyRuby converts SDR video to HDR
24 August 2026WanWan 3.0Wan 3.0 and Wan 3.0 Prime arrive on Higgsfield, up to 30 seconds
24 August 2026WanWan 3.0Wan 3.0 arrives in Runway at 480p, 720p or 1080p
27 August 2026Gemini OmniGemini Omni 1.1 FlashGemini Omni 1.1 Flash goes GA with extension, first-and-last-frame input and 360p to 4K output
14 September 2026ViduVidu Q3Vidu Q3 reference-to-video models for drama and for ads are listed on Model Studio
18 September 2026Kling AIKling 3.0Kling 3.0 and O3 models, including 4K, reach Runway's MCP

Inclusion rule. All entries tagged with this kind of change, including platform arrivals and undated rows. Order. By date, oldest first; undated rows last.

3One line at a time

4Other kinds of change