VideoGenReview

What each AI video model's release notes say changed

The full release-note log, oldest first

All 219 entries in one table: the date each note carries, the line and version, what changed and the kinds of change it counts under. The dated entries run from 1 July 2024 to 22 September 2026; undated version rows come last. As of 2026-09-25.

Four kinds of entryMost entries quote a maker's own note; some record a platform announcing an outside model; a few are undated rows from a maker's model list or a platform's tier list.EntryMaker's noteChangelog, API log or launch post, dated.ArrivalA platform announces an outside model, dated.Model list rowA version and its specs, no date.Tier list rowA platform's tier naming an outside model, no date.
Fig. 1 The Source column on line pages says which kind each entry is.
All 219 entries, read 2026-09-25.
DateLineVersionWhat changedKinds
1 July 2024RunwayGen-3 AlphaGen-3 Alpha text-to-video, described as a step up in fidelity, consistency and motionnew model, motion
29 July 2024RunwayGen-3 AlphaGen-3 Alpha takes an image as the first frameframes
5 August 2024RunwayGen-3 AlphaThe image can be the first or the last frameframes
14 August 2024RunwayGen-3 Alpha TurboGen-3 Alpha Turbo: faster and cheaper than Gen-3 Alphanew model, tiers
4 September 2024RunwayGen-3 AlphaGen-3 Alpha clips can be extended to 40 seconds in totallength
13 September 2024RunwayGen-3 AlphaVideo to Video restyles an uploaded clipediting
16 September 2024RunwayNot named in the noteThe Runway API opensaccess
20 September 2024RunwayGen-3 Alpha TurboVertical video for everyone on Gen-3 Alpha Turboresolution
23 September 2024RunwayGen-3 Alpha TurboGen-3 Alpha Turbo clips extend to 34 secondslength
8 October 2024RunwayGen-3 Alpha TurboFirst and last frame input for Gen-3 Alpha Turboframes
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 zoomnew model, camera
14 October 2024Adobe Firefly VideoFirefly Video ModelGenerative Extend in the Premiere Pro beta lengthens clips to cover gaps and hold shots longerlength, editing
25 October 2024RunwayAct-OneAct-One drives a character from one performance video and one imagenew model, motion
1 November 2024RunwayGen-3 Alpha TurboCamera Control with direction and intensity for Gen-3 Alpha Turbocamera
15 November 2024Kling AIKling 1.5Kling 1.5 Pro opens in the API for image-to-video onlynew model, access
15 November 2024RunwayGen-3 Alpha TurboVideo to Video runs up to 20 secondslength, editing
22 November 2024RunwayGen-3 Alpha TurboExpand Video repaints a clip into a new aspect ratioediting, resolution
29 November 2024Kling AIKling 1.0Motion Brush arrives for the 1.0 model at 5 secondsmotion
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 pacingnew model
4 December 2024RunwayGen-3 Alpha TurboA static option in Camera Controlcamera
6 December 2024RunwayAct-OneAct-One puts a performance onto characters inside existing videosreferences, editing
7 December 2024RunwayGen-3 Alpha TurboHandheld shake and speed can be controlledcamera
9 December 2024Kling AIKling 1.5The standard mode of Kling 1.5 opens for image-to-videotiers
19 December 2024RunwayGen-3 Alpha TurboA middle keyframe between first and lastframes
23 December 2024Kling AINot named in the noteLip-sync for videos made with the 1.0 and 1.5 modelssound
7 January 2025Kling AIKling 1.6Kling 1.6 launches, without tail frame, motion brush or camera control at firstnew model
9 January 2025WanWan 2.1Wan 2.1 text-to-video Plus, with large movements and physical plausibility namednew model, motion
10 January 2025RunwayGen-3 AlphaUpscaling to 4K inside Gen-3 Alpharesolution
20 January 2025WanWan 2.1Wan 2.1 image-to-video Plus turns a still into a clipframes
11 February 2025MiniMax HailuoHailuo DirectorThe Director models follow camera movement instructions more closelynew model, camera
12 February 2025Adobe Firefly VideoFirefly Video ModelThe model reaches 1080p output as it opens in the new Firefly app, with a faster ideation model plannedresolution, access
12 February 2025Adobe Firefly VideoFirefly Video ModelKeyframes can be set at the start and at the end of a clipframes
27 February 2025WanWan 2.1A Turbo tier of Wan 2.1 image-to-video for faster generationtiers
27 March 2025PixVerseNot named in the noteTransition from a first to a last frameframes
31 March 2025Kling AIKling 1.6Kling 1.6 can generate from an end frameframes
31 March 2025Luma RayRay2Camera Motion Concepts give Ray2 composable camera movescamera
1 April 2025RunwayGen-4Gen-4 is released for paid plansnew model
7 April 2025Amazon Nova ReelNova Reel 1.1Nova Reel 1.1 improves quality and latency for 6-second single-shot clips over Nova Reel 1.0new model
7 April 2025Amazon Nova ReelNova Reel 1.1Multi-shot videos up to two minutes, in an automated mode from one prompt or a manual mode with a prompt per shotlength, camera
7 April 2025Amazon Nova ReelNova Reel 1.1Manual mode, also called storyboard mode, takes a separate prompt for each shotcamera
7 April 2025Amazon Nova ReelNova Reel 1.1The user guide records video generation up to two minutes longlength
7 April 2025RunwayGen-4Gen-4 Turbo, the faster tier, opens to all userstiers
7 April 2025WanWan 2.1Wan 2.1 start-and-end-frame model makes a transition between two imagesframes
9 April 2025Google VeoVeo 2Veo 2 becomes generally available in the Gemini API for text and image inputnew model, access
18 April 2025Luma RayRay2Nine Camera Angle Concepts are added for Ray2camera
29 April 2025PixVerseNot named in the notePixVerse MCP server releasedaccess
30 April 2025RunwayGen-4Gen-4 References keeps characters and locations consistentreferences
9 May 2025Luma RayNot named in the noteReframe outpaints a video or image beyond its bordersediting, resolution
13 May 2025Kling AIKling 2.0Kling 2.0 Master for text-to-video and image-to-videonew model
14 May 2025WanWan 2.1Wan 2.1 VACE combines local editing, repainting, outpainting, extension and image referencesediting, length, references
2 June 2025Luma RayNot named in the noteModify Video keeps a performance and changes the world around itediting, motion
18 June 2025MiniMax HailuoHailuo 02Hailuo 02 generates 1080p and clips of up to 10 secondsnew model, resolution, length
18 June 2025Midjourney videoMidjourney V1 videoThe V1 video model animates images, with low or high motion and extensions of about 4 secondsnew model, length, motion
19 June 2025Kling AIKling 2.1Kling 2.1 image-to-video in standard and pro modes, plus a 2.1 Masternew model, tiers
20 June 2025PixVerseNot named in the noteText-to-video and image-to-video take a camera movement fieldcamera
23 June 2025Google VeoVeo 2Veo 2 on Vertex AI takes a last frame as well as a first, or a video to extendframes, length
25 June 2025RunwayGen-4An update to Gen-4 References improves object consistencyreferences
30 June 2025Kling AINot named in the noteLip-sync videos can run 60 seconds instead of 10sound, length
14 July 2025PixVerseNot named in the noteLip-sync and extend arrivesound, length
17 July 2025Adobe Firefly VideoFirefly Video ModelMotion fidelity is improved, for smoother transitions and more natural movementmotion
17 July 2025Adobe Firefly VideoFirefly Video ModelA reference video can pass its composition to a new generationreferences
17 July 2025RunwayAct-TwoAct-Two tracks head, face, body and handsnew model, motion
17 July 2025Google VeoVeo 3Veo 3 preview arrives in the Gemini API and generates sound with the picturenew model, sound
17 July 2025Google VeoVeo 3Veo 3 preview models on Vertex AI can be upscaled to 1080presolution
25 July 2025Midjourney videoMidjourney V1 videoLooping, set start and end images, and video in the Discord botframes, access
28 July 2025ViduNot named in the noteLip-sync from text or audiosound
28 July 2025WanWan 2.2Wan 2.2 text-to-video Plus names complex movement and cinematic controlnew model, camera, motion
29 July 2025Google VeoVeo 3Veo 3 and the Veo 3 Fast tier become generally available on Vertex AIaccess, tiers
31 July 2025RunwayAlephAleph, a model for editing and transforming video, opens to paid plansnew model, editing
31 July 2025Google VeoVeo 3Image-to-video opens for the Veo 3 preview and a Veo 3 Fast preview is releasedframes, tiers
1 August 2025Kling AINot named in the noteVideo-to-audio adds sound to any Kling video, and text-to-audio arrivessound
5 August 2025PixVerseNot named in the noteSound effects and Fusion (reference to video) arrivesound, references
7 August 2025Midjourney videoMidjourney V1 videoAn HD mode renders video at native 720presolution, tiers
7 August 2025ViduNot named in the noteAn off-peak mode at lower credit costtiers
12 August 2025Kling AIKling 1.6Text-to-video on 1.6 gains the pro modetiers
12 August 2025Luma RayNot named in the noteModify with Instructions takes edits in plain languageediting
13 August 2025Midjourney videoMidjourney V1 videoHD video opens to the Standard plan and smaller batches arriveaccess, tiers
15 August 2025WanWan 2.2Wan 2.2 image-to-video Flash: faster, with shot controltiers, camera
26 August 2025ViduNot named in the noteReference video generation from one to seven imagesreferences
29 August 2025PixVersePixVerse V5The V5 model is releasednew model
5 September 2025Kling AIKling 2.1Kling 2.1 takes a start and an end frame, in pro mode onlyframes
8 September 2025Google VeoVeo 3Veo 3 on Vertex AI can make 4, 6 or 8 second clipslength
9 September 2025Google VeoVeo 3Veo 3 goes GA in the Gemini API with more aspect ratio, resolution and seed optionsaccess, resolution
11 September 2025PixVerseNot named in the noteSound effects and text-to-speech lip-sync inside generation callssound
12 September 2025WanWan 2.2A Wan 2.2 first-and-last-frame model for transitions between two imagesframes
15 September 2025Kling AINot named in the noteLip-sync handles several people on screen and a set start timesound
18 September 2025Luma RayRay3Ray3 adds reasoning, native HDR EXR output and a Draft Modenew model, resolution, tiers
23 September 2025WanWan 2.5Wan 2.5 preview generates synchronised audio and 10 second clipsnew model, sound, length
24 September 2025ViduVidu Q2Vidu Q2 Pro and Q2 Turbo for image-to-video and start-and-end framesnew model, frames, tiers
28 September 2025PixVerseNot named in the noteRestyle is releasedediting
6 October 2025SoraSora 2The API gains a videos endpoint for Sora 2 and Sora 2 Pronew model, access
15 October 2025Google VeoVeo 3.1Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame inputnew model, length, references, frames
20 October 2025Kling AIKling 2.5 TurboKling 2.5 Turbo for text-to-video and image-to-video, pro modenew model, tiers
21 October 2025ViduVidu Q2Q2 gains reference-to-video, text-to-video and extensionreferences, length
28 October 2025MiniMax HailuoHailuo 2.3Hailuo 2.3 and a 2.3 Fast tier, with body movement, faces and physics named as the gainsnew model, motion, tiers
29 October 2025LTXNot named in the noteThe LTX API opens with text-to-video and image-to-videonew model, access
9 November 2025PixVerseNot named in the noteMulti-transition and Swap generation are releasedframes, editing
10 November 2025WanWan 2.2Wan 2.2 Animate moves a character photo with the performance from a reference videomotion, references
11 November 2025Kling AIKling 2.5 TurboKling 2.5 Turbo gains the standard modetiers
13 November 2025ViduNot named in the noteAudio and video in one output for reference-to-video and image-to-videosound
17 November 2025Kling AIKling 2.5 TurboKling 2.5 Turbo pro mode takes first and last framesframes
17 November 2025Google VeoVeo 3.1Veo 3.1 and Veo 3.1 Fast become generally available on Vertex AIaccess
25 November 2025LTXNot named in the noteRetake edits a chosen section of a video from a promptediting
2 December 2025PixVersePixVerse V5.5V5.5 is releasednew model
3 December 2025WanWan 2.6Wan 2.6 text-to-video plans several shots inside one clip of up to 15 secondsnew model, camera, length
3 December 2025WanWan 2.6Wan 2.6 image-to-video handles dialogue between several speakerssound
4 December 2025Kling AIKling AvatarAvatar videos can run five minuteslength
8 December 2025Google VeoVeo 3.1Veo 3.1 video extension reaches Vertex AI in previewlength
9 December 2025LTXNot named in the noteAudio-to-video drives a clip from an audio tracksound
11 December 2025RunwayGen-4.5Gen-4.5 is released for all paid plansnew model
15 December 2025Kling AIKling 2.6Kling 2.6 launches with a switch for generating soundnew model, sound
15 December 2025Kling AIKling OmniThe Omni video model launches on a new API driven by prompt wordsnew model, references
16 December 2025Adobe Firefly VideoFirefly Video ModelA start frame can be paired with a reference video whose camera motion the generation recreatescamera, frames, references
16 December 2025Kling AIKling 2.6Kling 2.6 can speak with a chosen voicesound
16 December 2025WanWan 2.6Wan 2.6 reference-to-video keeps a person's look and voice, with several characters at oncereferences, sound
17 December 2025Kling AIKling 2.6Kling 2.6 Motion Control copies an action and expression, up to 30 seconds in one takemotion, length
18 December 2025Luma RayRay3Ray3 Modify adds keyframe and character reference controlsediting, frames, references
22 December 2025Kling AINot named in the noteMotion Control in the API takes a reference image and a reference video togethermotion, references
23 December 2025LTXNot named in the noteThe developer console opens to self-service sign-upaccess
1 January 2026LTXNot named in the noteCamera motion settings for text-to-video and image-to-videocamera
13 January 2026SoraSora 2The sora-2 name now points to a December 2025 snapshot; the October snapshot stays callablenew model
13 January 2026Google VeoNot named in the note4K output and portrait video at every resolution come to Veo in the Gemini APIresolution
13 January 2026Google VeoVeo 3.1On Vertex AI, reference-to-video takes 9:16 and 1080p or 4K outputs can be upsampledresolution, references
15 January 2026WanWan 2.6A Flash tier of Wan 2.6 image-to-video: faster and lower costtiers
21 January 2026RunwayGen-4.5Gen-4.5 takes a first frame image with the promptframes
23 January 2026Kling AINot named in the noteOther angles of an element can be filled in from its front viewreferences
26 January 2026Luma RayRay3.14Ray3.14 brings native 1080p and faster, cheaper 720p than Ray3new model, resolution, tiers
26 January 2026PixVersePixVerse V5.6V5.6 is releasednew model
28 January 2026Grok ImagineNot named in the noteVideo generation opens in the xAI APInew model, access
29 January 2026Kling AINot named in the noteCanvas Agent adds smart multi-shot and multi-angle expansioncamera
29 January 2026WanWan 2.6A Flash tier of Wan 2.6 reference-to-videotiers, references
30 January 2026Kling AINot named in the noteKeyframes pulled from a video can serve as start and end frames; .mov export addedframes
31 January 2026Kling AIKling 3.0Kling 3.0 is fully rolled out in the appnew model
12 February 2026PixVersePixVerse V5.6Fusion reference-to-video moves to V5.6references
18 February 2026LTXNot named in the noteAn extend endpoint adds frames at the start or the endlength
25 February 2026Kling AIKling 3.0Kling 3.0 and 3.0 Omni reach the API; elements can be built from videoaccess, references
28 February 2026PixVerseNot named in the noteMimic is releasedmotion
4 March 2026Kling AIKling 3.0Kling 3.0 Motion Control launchesmotion
5 March 2026LTXLTX-2.3LTX-2.3 becomes the default model in two variantsnew model, tiers
11 March 2026Kling AIKling 3.03.0 Omni can plan its own shots when shot_type is set to intelligencecamera
12 March 2026SoraSora 2Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobsreferences, length, resolution, access
12 March 2026SoraSora 2A new edits endpoint edits existing videos and takes over from remixediting
15 March 2026Grok ImagineNot named in the noteThe Batch API accepts video generation jobsaccess
23 March 2026Kling AINot named in the noteElements made from several images can be tied to a voicesound, references
29 March 2026PixVersePixVerse V6V6 covers text-to-video, image-to-video, transition and extendnew model, length, frames
31 March 2026Google VeoVeo 3.1 LiteVeo 3.1 Lite preview is released as a lower-cost tier for high-volume usenew model, tiers
2 April 2026Google VeoVeo 3.1 LiteVeo 3.1 Lite reaches Vertex AI in public previewaccess
3 April 2026WanWan 2.7Wan 2.7 text-to-video and image-to-video, with rhythmic cuts namednew model, camera
3 April 2026WanWan 2.7Wan 2.7 reference-to-video mixes up to five image or video references and clones a voice timbrereferences, sound
3 April 2026WanWan 2.7Wan 2.7 video edit makes local or whole-clip edits from a promptediting
7 April 2026PixVersePixVerse C1The C1 model covers text, image, transition and reference-to-videonew model, references
7 April 2026SeedanceSeedance 2.0Seedance 2.0 reaches Runway on Unlimited and Enterprise plans outside the USnew model
15 April 2026PixVerseNot named in the noteModify is releasedediting
22 April 2026HappyHorseHappyHorse 1.0HappyHorse 1.0 text-to-video and image-to-video are listednew model
23 April 2026Kling AINot named in the noteNative 4K output in the APIresolution
23 April 2026Kling AINot named in the noteNative 4K reaches the Kling appresolution
23 April 2026LTXNot named in the noteAn HDR conversion endpoint turns SDR clips into HDR framesresolution
26 April 2026HappyHorseHappyHorse 1.0HappyHorse 1.0 reference-to-video takes up to nine reference imagesreferences
26 April 2026HappyHorseHappyHorse 1.0HappyHorse 1.0 video edit changes parts of a clip from instructions and up to five imagesediting, references
26 April 2026WanWan 2.7A dated Wan 2.7 text-to-video snapshot from 25 April 2026new model
3 May 2026LTXNot named in the noteAsync versions of every video generation endpoint, in betaaccess
7 May 2026Kling AINot named in the noteMulti-shot videos can have set first and last framesframes, camera
21 May 2026PixVersePixVerse V6V6 Fusion makes reference names and types optionalreferences
21 May 2026RunwayAleph 2.0Aleph 2.0 edits a whole clip to match one edited framenew model, editing
9 June 2026Luma RayRay3.2Ray3.2 adds frame-level control over how action movesnew model, frames
16 June 2026HappyHorseHappyHorse 1.1HappyHorse 1.1 text-to-video names shot control and motion renderingnew model, camera, motion
16 June 2026HappyHorseHappyHorse 1.1HappyHorse 1.1 reference-to-video keeps subject and scene style steadierreferences
16 June 2026HappyHorseHappyHorse 1.1HappyHorse 1.1 image-to-video names consistency across clipsframes
16 June 2026PixVerseNot named in the noteUpscale is releasedresolution
17 June 2026Kling AIKling 3.0 TurboKling 3.0 Turbo for text-to-video and image-to-video at 720p and 1080pnew model, tiers, resolution
17 June 2026Kling AIKling 3.0Video editing in 3.0 Omni is upgraded alongside the Turbo launchediting
21 June 2026SeedanceSeedance 2.0Seedance 2.0 generates in 4K on Higgsfieldresolution
21 June 2026SeedanceSeedance 2.0 MiniSeedance 2.0 Mini arrives on Higgsfield as a lighter, faster modeltiers
29 June 2026Gemini OmniGemini Omni FlashGemini Omni Flash arrives on Higgsfieldnew model
30 June 2026Gemini OmniGemini Omni FlashGemini Omni Flash preview makes 3 to 10 second clips at 720p and edits them in conversationnew model, length, resolution, editing
30 June 2026Gemini OmniGemini Omni FlashGemini Omni Flash arrives in Runwaynew model, editing
1 July 2026WanWan 2.7A second dated Wan 2.7 snapshot, from 12 June 2026new model
7 July 2026LTXNot named in the noteReframe fills in missing areas to fit a new resolutionediting, resolution
15 July 2026Kling AINot named in the noteMore video models move to the simpler API introduced with 3.0 Turboaccess
21 July 2026SeedanceSeedance 2.0 MiniSeedance 2.0 Mini and Fast reach Runway through its MCPtiers
22 July 2026PixVerseNot named in the noteVoice cloning for image avatar and lip-syncsound
22 July 2026SeedanceSeedance 2.0Seedance 2.0 in 4K through Runway's MCPresolution
26 July 2026PixVersePixVerse V6V6 reference-to-video takes video references in an omni modereferences
31 July 2026Grok ImagineGrok Imagine 1.5Grok Imagine video 1.5 adds reference-to-video with preset voices and native 1080pnew model, references, resolution, sound
31 July 2026MiniMax HailuoMiniMax H3MiniMax H3 reads text, image, video and audio together as creative contextnew model, references
2 August 2026LTXLTX-2.3A 720p output tier for LTX 2.3resolution, tiers
5 August 2026MiniMax HailuoHailuo 3.0Runway's developer API adds a model it names MiniMax Hailuo 3.0new model, references
6 August 2026SeedanceSeedance 2.5Seedance 2.5 arrives on Higgsfield with clips up to 30 secondsnew model, length
6 August 2026SeedanceSeedance 2.5Seedance 2.5 arrives on Luma with 30-second single-pass generationnew model, length
6 August 2026WanWan 3.0Wan 3.0 folds reference, editing, replication and driving into one model, with clips up to 30 secondsnew model, length, references, editing
10 August 2026LTXLTX-2.5The fast LTX-2.5 model can choose the clip length from the promptlength
10 August 2026RunwayGen-4.5Gen-4.5 and Aleph 2 outputs export as ProRes 4444 or PNG sequencesresolution, access
11 August 2026LTXLTX-2.5LTX-2.5 models in portrait and landscape, with the fast one up to 4Knew model, resolution
11 August 2026SeedanceSeedance 2.5Seedance 2.5 reaches Runway through its MCP, up to 30 secondsnew model, length
13 August 2026Grok ImagineGrok Imagine 1.5Grok Imagine 1.5 reaches Runway's MCP, 1 to 15 seconds with audionew model, sound
14 August 2026SeedanceSeedance 2.5Seedance 2.5 at 1080p on Higgsfield, in early accessresolution
15 August 2026SeedanceSeedance 2.5Seedance 2.5 at 1080p across Runwayresolution
18 August 2026LTXLTX-2.5Audio-to-video gets the same resolution tiers as the other modessound, resolution
19 August 2026LTXNot named in the noteAudio-to-video takes a frame rate, a last frame and camera motionsound, frames, camera
20 August 2026RunwayRunway RubyRuby converts SDR video to HDRnew model, resolution
20 August 2026WanWan 3.0Wan 3.0 Prime, a faster version with the same capabilitiestiers
24 August 2026WanWan 3.0Wan 3.0 and Wan 3.0 Prime arrive on Higgsfield, up to 30 secondsnew model, length
24 August 2026WanWan 3.0Wan 3.0 arrives in Runway at 480p, 720p or 1080pnew model, resolution
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 outputnew model, access, length, frames, resolution
28 August 2026Gemini OmniGemini Omni 1.1 FlashGemini Omni 1.1 Flash on Higgsfield, up to 10 seconds and 4Kframes, resolution, length
31 August 2026MiniMax HailuoMiniMax H3 MaxMiniMax H3 Max, a variant tuned for prompt adherence, on Higgsfieldtiers, frames
2 September 2026LTXLTX-2.5LTX-2.5 Pro renders 1440p and 4K in both orientations and takes 48 fpsresolution
14 September 2026ViduVidu Q3Vidu Q3 reference-to-video models for drama and for ads are listed on Model Studionew model, references
17 September 2026RunwayNot named in the noteFrame-rate conversion up to 120 fps, 4K and five minutesresolution
18 September 2026Kling AIKling 3.0Kling 3.0 and O3 models, including 4K, reach Runway's MCPnew model
22 September 2026SeedanceSeedance 2.5A 480p Draft Mode for Seedance 2.5 on Higgsfield, before the 1080p finaltiers
Undated tier rowMiniMax HailuoMiniMax H3SceneMixer's tier list carries MiniMax H3 and an H3 Fast tier, each up to 15 seconds a cliptiers, length
Undated version rowSeedanceSeedance 1.0 ProSeedance 1.0 Pro: 2 to 12 seconds, up to 1080p, first and last frameslength, resolution, frames
Undated version rowSeedanceSeedance 1.5 ProSeedance 1.5 Pro: 4 to 12 seconds, up to 1080p, now marked retiredlength
Undated version rowSeedanceSeedance 2.0Seedance 2.0: 4 to 15 seconds, up to 4K, multimodal references, editing and extensionlength, resolution, references, editing
Undated version rowSeedanceSeedance 2.0 MiniSeedance 2.0 Mini: 480p and 720p, 4 to 15 secondstiers
Undated version rowSeedanceSeedance 2.5Seedance 2.5: 4 to 30 seconds, 1080p in 10-bitlength, resolution
Undated tier rowWanWan 3.0SceneMixer's tier list carries Wan 3.0 at 480p, its default, and at 720p and 1080p, each up to 30 seconds a cliptiers, resolution, length
Undated tier rowWanWan 3.0Wan 3.0 is one of SceneMixer's two video paths, with its 720p tier marked recommendedtiers, access

Inclusion rule. Every entry on the register. Order. By date, oldest first; undated rows last.

The same rows, with quotes and sources, are in the data file.