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.
| Date | Line | Version | What changed | Kinds |
|---|---|---|---|---|
| 1 July 2024 | Runway | Gen-3 Alpha | Gen-3 Alpha text-to-video, described as a step up in fidelity, consistency and motion | new model, motion |
| 29 July 2024 | Runway | Gen-3 Alpha | Gen-3 Alpha takes an image as the first frame | frames |
| 5 August 2024 | Runway | Gen-3 Alpha | The image can be the first or the last frame | frames |
| 14 August 2024 | Runway | Gen-3 Alpha Turbo | Gen-3 Alpha Turbo: faster and cheaper than Gen-3 Alpha | new model, tiers |
| 4 September 2024 | Runway | Gen-3 Alpha | Gen-3 Alpha clips can be extended to 40 seconds in total | length |
| 13 September 2024 | Runway | Gen-3 Alpha | Video to Video restyles an uploaded clip | editing |
| 16 September 2024 | Runway | Not named in the note | The Runway API opens | access |
| 20 September 2024 | Runway | Gen-3 Alpha Turbo | Vertical video for everyone on Gen-3 Alpha Turbo | resolution |
| 23 September 2024 | Runway | Gen-3 Alpha Turbo | Gen-3 Alpha Turbo clips extend to 34 seconds | length |
| 8 October 2024 | Runway | Gen-3 Alpha Turbo | First and last frame input for Gen-3 Alpha Turbo | frames |
| 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 | new model, camera |
| 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 | length, editing |
| 25 October 2024 | Runway | Act-One | Act-One drives a character from one performance video and one image | new model, motion |
| 1 November 2024 | Runway | Gen-3 Alpha Turbo | Camera Control with direction and intensity for Gen-3 Alpha Turbo | camera |
| 15 November 2024 | Kling AI | Kling 1.5 | Kling 1.5 Pro opens in the API for image-to-video only | new model, access |
| 15 November 2024 | Runway | Gen-3 Alpha Turbo | Video to Video runs up to 20 seconds | length, editing |
| 22 November 2024 | Runway | Gen-3 Alpha Turbo | Expand Video repaints a clip into a new aspect ratio | editing, resolution |
| 29 November 2024 | Kling AI | Kling 1.0 | Motion Brush arrives for the 1.0 model at 5 seconds | motion |
| 3 December 2024 | Amazon Nova Reel | Nova Reel 1.0 | Nova Reel launches in Amazon Bedrock for short videos from text and images, with control of style and pacing | new model |
| 4 December 2024 | Runway | Gen-3 Alpha Turbo | A static option in Camera Control | camera |
| 6 December 2024 | Runway | Act-One | Act-One puts a performance onto characters inside existing videos | references, editing |
| 7 December 2024 | Runway | Gen-3 Alpha Turbo | Handheld shake and speed can be controlled | camera |
| 9 December 2024 | Kling AI | Kling 1.5 | The standard mode of Kling 1.5 opens for image-to-video | tiers |
| 19 December 2024 | Runway | Gen-3 Alpha Turbo | A middle keyframe between first and last | frames |
| 23 December 2024 | Kling AI | Not named in the note | Lip-sync for videos made with the 1.0 and 1.5 models | sound |
| 7 January 2025 | Kling AI | Kling 1.6 | Kling 1.6 launches, without tail frame, motion brush or camera control at first | new model |
| 9 January 2025 | Wan | Wan 2.1 | Wan 2.1 text-to-video Plus, with large movements and physical plausibility named | new model, motion |
| 10 January 2025 | Runway | Gen-3 Alpha | Upscaling to 4K inside Gen-3 Alpha | resolution |
| 20 January 2025 | Wan | Wan 2.1 | Wan 2.1 image-to-video Plus turns a still into a clip | frames |
| 11 February 2025 | MiniMax Hailuo | Hailuo Director | The Director models follow camera movement instructions more closely | new model, camera |
| 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 | resolution, access |
| 12 February 2025 | Adobe Firefly Video | Firefly Video Model | Keyframes can be set at the start and at the end of a clip | frames |
| 27 February 2025 | Wan | Wan 2.1 | A Turbo tier of Wan 2.1 image-to-video for faster generation | tiers |
| 27 March 2025 | PixVerse | Not named in the note | Transition from a first to a last frame | frames |
| 31 March 2025 | Kling AI | Kling 1.6 | Kling 1.6 can generate from an end frame | frames |
| 31 March 2025 | Luma Ray | Ray2 | Camera Motion Concepts give Ray2 composable camera moves | camera |
| 1 April 2025 | Runway | Gen-4 | Gen-4 is released for paid plans | new model |
| 7 April 2025 | Amazon Nova Reel | Nova Reel 1.1 | Nova Reel 1.1 improves quality and latency for 6-second single-shot clips over Nova Reel 1.0 | new model |
| 7 April 2025 | Amazon Nova Reel | Nova Reel 1.1 | Multi-shot videos up to two minutes, in an automated mode from one prompt or a manual mode with a prompt per shot | length, camera |
| 7 April 2025 | Amazon Nova Reel | Nova Reel 1.1 | Manual mode, also called storyboard mode, takes a separate prompt for each shot | camera |
| 7 April 2025 | Amazon Nova Reel | Nova Reel 1.1 | The user guide records video generation up to two minutes long | length |
| 7 April 2025 | Runway | Gen-4 | Gen-4 Turbo, the faster tier, opens to all users | tiers |
| 7 April 2025 | Wan | Wan 2.1 | Wan 2.1 start-and-end-frame model makes a transition between two images | frames |
| 9 April 2025 | Google Veo | Veo 2 | Veo 2 becomes generally available in the Gemini API for text and image input | new model, access |
| 18 April 2025 | Luma Ray | Ray2 | Nine Camera Angle Concepts are added for Ray2 | camera |
| 29 April 2025 | PixVerse | Not named in the note | PixVerse MCP server released | access |
| 30 April 2025 | Runway | Gen-4 | Gen-4 References keeps characters and locations consistent | references |
| 9 May 2025 | Luma Ray | Not named in the note | Reframe outpaints a video or image beyond its borders | editing, resolution |
| 13 May 2025 | Kling AI | Kling 2.0 | Kling 2.0 Master for text-to-video and image-to-video | new model |
| 14 May 2025 | Wan | Wan 2.1 | Wan 2.1 VACE combines local editing, repainting, outpainting, extension and image references | editing, length, references |
| 2 June 2025 | Luma Ray | Not named in the note | Modify Video keeps a performance and changes the world around it | editing, motion |
| 18 June 2025 | MiniMax Hailuo | Hailuo 02 | Hailuo 02 generates 1080p and clips of up to 10 seconds | new model, resolution, length |
| 18 June 2025 | Midjourney video | Midjourney V1 video | The V1 video model animates images, with low or high motion and extensions of about 4 seconds | new model, length, motion |
| 19 June 2025 | Kling AI | Kling 2.1 | Kling 2.1 image-to-video in standard and pro modes, plus a 2.1 Master | new model, tiers |
| 20 June 2025 | PixVerse | Not named in the note | Text-to-video and image-to-video take a camera movement field | camera |
| 23 June 2025 | Google Veo | Veo 2 | Veo 2 on Vertex AI takes a last frame as well as a first, or a video to extend | frames, length |
| 25 June 2025 | Runway | Gen-4 | An update to Gen-4 References improves object consistency | references |
| 30 June 2025 | Kling AI | Not named in the note | Lip-sync videos can run 60 seconds instead of 10 | sound, length |
| 14 July 2025 | PixVerse | Not named in the note | Lip-sync and extend arrive | sound, length |
| 17 July 2025 | Adobe Firefly Video | Firefly Video Model | Motion fidelity is improved, for smoother transitions and more natural movement | motion |
| 17 July 2025 | Adobe Firefly Video | Firefly Video Model | A reference video can pass its composition to a new generation | references |
| 17 July 2025 | Runway | Act-Two | Act-Two tracks head, face, body and hands | new model, motion |
| 17 July 2025 | Google Veo | Veo 3 | Veo 3 preview arrives in the Gemini API and generates sound with the picture | new model, sound |
| 17 July 2025 | Google Veo | Veo 3 | Veo 3 preview models on Vertex AI can be upscaled to 1080p | resolution |
| 25 July 2025 | Midjourney video | Midjourney V1 video | Looping, set start and end images, and video in the Discord bot | frames, access |
| 28 July 2025 | Vidu | Not named in the note | Lip-sync from text or audio | sound |
| 28 July 2025 | Wan | Wan 2.2 | Wan 2.2 text-to-video Plus names complex movement and cinematic control | new model, camera, motion |
| 29 July 2025 | Google Veo | Veo 3 | Veo 3 and the Veo 3 Fast tier become generally available on Vertex AI | access, tiers |
| 31 July 2025 | Runway | Aleph | Aleph, a model for editing and transforming video, opens to paid plans | new model, editing |
| 31 July 2025 | Google Veo | Veo 3 | Image-to-video opens for the Veo 3 preview and a Veo 3 Fast preview is released | frames, tiers |
| 1 August 2025 | Kling AI | Not named in the note | Video-to-audio adds sound to any Kling video, and text-to-audio arrives | sound |
| 5 August 2025 | PixVerse | Not named in the note | Sound effects and Fusion (reference to video) arrive | sound, references |
| 7 August 2025 | Midjourney video | Midjourney V1 video | An HD mode renders video at native 720p | resolution, tiers |
| 7 August 2025 | Vidu | Not named in the note | An off-peak mode at lower credit cost | tiers |
| 12 August 2025 | Kling AI | Kling 1.6 | Text-to-video on 1.6 gains the pro mode | tiers |
| 12 August 2025 | Luma Ray | Not named in the note | Modify with Instructions takes edits in plain language | editing |
| 13 August 2025 | Midjourney video | Midjourney V1 video | HD video opens to the Standard plan and smaller batches arrive | access, tiers |
| 15 August 2025 | Wan | Wan 2.2 | Wan 2.2 image-to-video Flash: faster, with shot control | tiers, camera |
| 26 August 2025 | Vidu | Not named in the note | Reference video generation from one to seven images | references |
| 29 August 2025 | PixVerse | PixVerse V5 | The V5 model is released | new model |
| 5 September 2025 | Kling AI | Kling 2.1 | Kling 2.1 takes a start and an end frame, in pro mode only | frames |
| 8 September 2025 | Google Veo | Veo 3 | Veo 3 on Vertex AI can make 4, 6 or 8 second clips | length |
| 9 September 2025 | Google Veo | Veo 3 | Veo 3 goes GA in the Gemini API with more aspect ratio, resolution and seed options | access, resolution |
| 11 September 2025 | PixVerse | Not named in the note | Sound effects and text-to-speech lip-sync inside generation calls | sound |
| 12 September 2025 | Wan | Wan 2.2 | A Wan 2.2 first-and-last-frame model for transitions between two images | frames |
| 15 September 2025 | Kling AI | Not named in the note | Lip-sync handles several people on screen and a set start time | sound |
| 18 September 2025 | Luma Ray | Ray3 | Ray3 adds reasoning, native HDR EXR output and a Draft Mode | new model, resolution, tiers |
| 23 September 2025 | Wan | Wan 2.5 | Wan 2.5 preview generates synchronised audio and 10 second clips | new model, sound, length |
| 24 September 2025 | Vidu | Vidu Q2 | Vidu Q2 Pro and Q2 Turbo for image-to-video and start-and-end frames | new model, frames, tiers |
| 28 September 2025 | PixVerse | Not named in the note | Restyle is released | editing |
| 6 October 2025 | Sora | Sora 2 | The API gains a videos endpoint for Sora 2 and Sora 2 Pro | new model, access |
| 15 October 2025 | Google Veo | Veo 3.1 | Veo 3.1 preview adds extension, up to three reference images and first-and-last-frame input | new model, length, references, frames |
| 20 October 2025 | Kling AI | Kling 2.5 Turbo | Kling 2.5 Turbo for text-to-video and image-to-video, pro mode | new model, tiers |
| 21 October 2025 | Vidu | Vidu Q2 | Q2 gains reference-to-video, text-to-video and extension | references, length |
| 28 October 2025 | MiniMax Hailuo | Hailuo 2.3 | Hailuo 2.3 and a 2.3 Fast tier, with body movement, faces and physics named as the gains | new model, motion, tiers |
| 29 October 2025 | LTX | Not named in the note | The LTX API opens with text-to-video and image-to-video | new model, access |
| 9 November 2025 | PixVerse | Not named in the note | Multi-transition and Swap generation are released | frames, editing |
| 10 November 2025 | Wan | Wan 2.2 | Wan 2.2 Animate moves a character photo with the performance from a reference video | motion, references |
| 11 November 2025 | Kling AI | Kling 2.5 Turbo | Kling 2.5 Turbo gains the standard mode | tiers |
| 13 November 2025 | Vidu | Not named in the note | Audio and video in one output for reference-to-video and image-to-video | sound |
| 17 November 2025 | Kling AI | Kling 2.5 Turbo | Kling 2.5 Turbo pro mode takes first and last frames | frames |
| 17 November 2025 | Google Veo | Veo 3.1 | Veo 3.1 and Veo 3.1 Fast become generally available on Vertex AI | access |
| 25 November 2025 | LTX | Not named in the note | Retake edits a chosen section of a video from a prompt | editing |
| 2 December 2025 | PixVerse | PixVerse V5.5 | V5.5 is released | new model |
| 3 December 2025 | Wan | Wan 2.6 | Wan 2.6 text-to-video plans several shots inside one clip of up to 15 seconds | new model, camera, length |
| 3 December 2025 | Wan | Wan 2.6 | Wan 2.6 image-to-video handles dialogue between several speakers | sound |
| 4 December 2025 | Kling AI | Kling Avatar | Avatar videos can run five minutes | length |
| 8 December 2025 | Google Veo | Veo 3.1 | Veo 3.1 video extension reaches Vertex AI in preview | length |
| 9 December 2025 | LTX | Not named in the note | Audio-to-video drives a clip from an audio track | sound |
| 11 December 2025 | Runway | Gen-4.5 | Gen-4.5 is released for all paid plans | new model |
| 15 December 2025 | Kling AI | Kling 2.6 | Kling 2.6 launches with a switch for generating sound | new model, sound |
| 15 December 2025 | Kling AI | Kling Omni | The Omni video model launches on a new API driven by prompt words | new model, references |
| 16 December 2025 | Adobe Firefly Video | Firefly Video Model | A start frame can be paired with a reference video whose camera motion the generation recreates | camera, frames, references |
| 16 December 2025 | Kling AI | Kling 2.6 | Kling 2.6 can speak with a chosen voice | sound |
| 16 December 2025 | Wan | Wan 2.6 | Wan 2.6 reference-to-video keeps a person's look and voice, with several characters at once | references, sound |
| 17 December 2025 | Kling AI | Kling 2.6 | Kling 2.6 Motion Control copies an action and expression, up to 30 seconds in one take | motion, length |
| 18 December 2025 | Luma Ray | Ray3 | Ray3 Modify adds keyframe and character reference controls | editing, frames, references |
| 22 December 2025 | Kling AI | Not named in the note | Motion Control in the API takes a reference image and a reference video together | motion, references |
| 23 December 2025 | LTX | Not named in the note | The developer console opens to self-service sign-up | access |
| 1 January 2026 | LTX | Not named in the note | Camera motion settings for text-to-video and image-to-video | camera |
| 13 January 2026 | Sora | Sora 2 | The sora-2 name now points to a December 2025 snapshot; the October snapshot stays callable | new model |
| 13 January 2026 | Google Veo | Not named in the note | 4K output and portrait video at every resolution come to Veo in the Gemini API | resolution |
| 13 January 2026 | Google Veo | Veo 3.1 | On Vertex AI, reference-to-video takes 9:16 and 1080p or 4K outputs can be upsampled | resolution, references |
| 15 January 2026 | Wan | Wan 2.6 | A Flash tier of Wan 2.6 image-to-video: faster and lower cost | tiers |
| 21 January 2026 | Runway | Gen-4.5 | Gen-4.5 takes a first frame image with the prompt | frames |
| 23 January 2026 | Kling AI | Not named in the note | Other angles of an element can be filled in from its front view | references |
| 26 January 2026 | Luma Ray | Ray3.14 | Ray3.14 brings native 1080p and faster, cheaper 720p than Ray3 | new model, resolution, tiers |
| 26 January 2026 | PixVerse | PixVerse V5.6 | V5.6 is released | new model |
| 28 January 2026 | Grok Imagine | Not named in the note | Video generation opens in the xAI API | new model, access |
| 29 January 2026 | Kling AI | Not named in the note | Canvas Agent adds smart multi-shot and multi-angle expansion | camera |
| 29 January 2026 | Wan | Wan 2.6 | A Flash tier of Wan 2.6 reference-to-video | tiers, references |
| 30 January 2026 | Kling AI | Not named in the note | Keyframes pulled from a video can serve as start and end frames; .mov export added | frames |
| 31 January 2026 | Kling AI | Kling 3.0 | Kling 3.0 is fully rolled out in the app | new model |
| 12 February 2026 | PixVerse | PixVerse V5.6 | Fusion reference-to-video moves to V5.6 | references |
| 18 February 2026 | LTX | Not named in the note | An extend endpoint adds frames at the start or the end | length |
| 25 February 2026 | Kling AI | Kling 3.0 | Kling 3.0 and 3.0 Omni reach the API; elements can be built from video | access, references |
| 28 February 2026 | PixVerse | Not named in the note | Mimic is released | motion |
| 4 March 2026 | Kling AI | Kling 3.0 | Kling 3.0 Motion Control launches | motion |
| 5 March 2026 | LTX | LTX-2.3 | LTX-2.3 becomes the default model in two variants | new model, tiers |
| 11 March 2026 | Kling AI | Kling 3.0 | 3.0 Omni can plan its own shots when shot_type is set to intelligence | camera |
| 12 March 2026 | Sora | Sora 2 | Character references, clips up to 20 seconds, 1080p on Sora 2 Pro, extensions and batch jobs | references, length, resolution, access |
| 12 March 2026 | Sora | Sora 2 | A new edits endpoint edits existing videos and takes over from remix | editing |
| 15 March 2026 | Grok Imagine | Not named in the note | The Batch API accepts video generation jobs | access |
| 23 March 2026 | Kling AI | Not named in the note | Elements made from several images can be tied to a voice | sound, references |
| 29 March 2026 | PixVerse | PixVerse V6 | V6 covers text-to-video, image-to-video, transition and extend | new model, length, frames |
| 31 March 2026 | Google Veo | Veo 3.1 Lite | Veo 3.1 Lite preview is released as a lower-cost tier for high-volume use | new model, tiers |
| 2 April 2026 | Google Veo | Veo 3.1 Lite | Veo 3.1 Lite reaches Vertex AI in public preview | access |
| 3 April 2026 | Wan | Wan 2.7 | Wan 2.7 text-to-video and image-to-video, with rhythmic cuts named | new model, camera |
| 3 April 2026 | Wan | Wan 2.7 | Wan 2.7 reference-to-video mixes up to five image or video references and clones a voice timbre | references, sound |
| 3 April 2026 | Wan | Wan 2.7 | Wan 2.7 video edit makes local or whole-clip edits from a prompt | editing |
| 7 April 2026 | PixVerse | PixVerse C1 | The C1 model covers text, image, transition and reference-to-video | new model, references |
| 7 April 2026 | Seedance | Seedance 2.0 | Seedance 2.0 reaches Runway on Unlimited and Enterprise plans outside the US | new model |
| 15 April 2026 | PixVerse | Not named in the note | Modify is released | editing |
| 22 April 2026 | HappyHorse | HappyHorse 1.0 | HappyHorse 1.0 text-to-video and image-to-video are listed | new model |
| 23 April 2026 | Kling AI | Not named in the note | Native 4K output in the API | resolution |
| 23 April 2026 | Kling AI | Not named in the note | Native 4K reaches the Kling app | resolution |
| 23 April 2026 | LTX | Not named in the note | An HDR conversion endpoint turns SDR clips into HDR frames | resolution |
| 26 April 2026 | HappyHorse | HappyHorse 1.0 | HappyHorse 1.0 reference-to-video takes up to nine reference images | references |
| 26 April 2026 | HappyHorse | HappyHorse 1.0 | HappyHorse 1.0 video edit changes parts of a clip from instructions and up to five images | editing, references |
| 26 April 2026 | Wan | Wan 2.7 | A dated Wan 2.7 text-to-video snapshot from 25 April 2026 | new model |
| 3 May 2026 | LTX | Not named in the note | Async versions of every video generation endpoint, in beta | access |
| 7 May 2026 | Kling AI | Not named in the note | Multi-shot videos can have set first and last frames | frames, camera |
| 21 May 2026 | PixVerse | PixVerse V6 | V6 Fusion makes reference names and types optional | references |
| 21 May 2026 | Runway | Aleph 2.0 | Aleph 2.0 edits a whole clip to match one edited frame | new model, editing |
| 9 June 2026 | Luma Ray | Ray3.2 | Ray3.2 adds frame-level control over how action moves | new model, frames |
| 16 June 2026 | HappyHorse | HappyHorse 1.1 | HappyHorse 1.1 text-to-video names shot control and motion rendering | new model, camera, motion |
| 16 June 2026 | HappyHorse | HappyHorse 1.1 | HappyHorse 1.1 reference-to-video keeps subject and scene style steadier | references |
| 16 June 2026 | HappyHorse | HappyHorse 1.1 | HappyHorse 1.1 image-to-video names consistency across clips | frames |
| 16 June 2026 | PixVerse | Not named in the note | Upscale is released | resolution |
| 17 June 2026 | Kling AI | Kling 3.0 Turbo | Kling 3.0 Turbo for text-to-video and image-to-video at 720p and 1080p | new model, tiers, resolution |
| 17 June 2026 | Kling AI | Kling 3.0 | Video editing in 3.0 Omni is upgraded alongside the Turbo launch | editing |
| 21 June 2026 | Seedance | Seedance 2.0 | Seedance 2.0 generates in 4K on Higgsfield | resolution |
| 21 June 2026 | Seedance | Seedance 2.0 Mini | Seedance 2.0 Mini arrives on Higgsfield as a lighter, faster model | tiers |
| 29 June 2026 | Gemini Omni | Gemini Omni Flash | Gemini Omni Flash arrives on Higgsfield | new model |
| 30 June 2026 | Gemini Omni | Gemini Omni Flash | Gemini Omni Flash preview makes 3 to 10 second clips at 720p and edits them in conversation | new model, length, resolution, editing |
| 30 June 2026 | Gemini Omni | Gemini Omni Flash | Gemini Omni Flash arrives in Runway | new model, editing |
| 1 July 2026 | Wan | Wan 2.7 | A second dated Wan 2.7 snapshot, from 12 June 2026 | new model |
| 7 July 2026 | LTX | Not named in the note | Reframe fills in missing areas to fit a new resolution | editing, resolution |
| 15 July 2026 | Kling AI | Not named in the note | More video models move to the simpler API introduced with 3.0 Turbo | access |
| 21 July 2026 | Seedance | Seedance 2.0 Mini | Seedance 2.0 Mini and Fast reach Runway through its MCP | tiers |
| 22 July 2026 | PixVerse | Not named in the note | Voice cloning for image avatar and lip-sync | sound |
| 22 July 2026 | Seedance | Seedance 2.0 | Seedance 2.0 in 4K through Runway's MCP | resolution |
| 26 July 2026 | PixVerse | PixVerse V6 | V6 reference-to-video takes video references in an omni mode | references |
| 31 July 2026 | Grok Imagine | Grok Imagine 1.5 | Grok Imagine video 1.5 adds reference-to-video with preset voices and native 1080p | new model, references, resolution, sound |
| 31 July 2026 | MiniMax Hailuo | MiniMax H3 | MiniMax H3 reads text, image, video and audio together as creative context | new model, references |
| 2 August 2026 | LTX | LTX-2.3 | A 720p output tier for LTX 2.3 | resolution, tiers |
| 5 August 2026 | MiniMax Hailuo | Hailuo 3.0 | Runway's developer API adds a model it names MiniMax Hailuo 3.0 | new model, references |
| 6 August 2026 | Seedance | Seedance 2.5 | Seedance 2.5 arrives on Higgsfield with clips up to 30 seconds | new model, length |
| 6 August 2026 | Seedance | Seedance 2.5 | Seedance 2.5 arrives on Luma with 30-second single-pass generation | new model, length |
| 6 August 2026 | Wan | Wan 3.0 | Wan 3.0 folds reference, editing, replication and driving into one model, with clips up to 30 seconds | new model, length, references, editing |
| 10 August 2026 | LTX | LTX-2.5 | The fast LTX-2.5 model can choose the clip length from the prompt | length |
| 10 August 2026 | Runway | Gen-4.5 | Gen-4.5 and Aleph 2 outputs export as ProRes 4444 or PNG sequences | resolution, access |
| 11 August 2026 | LTX | LTX-2.5 | LTX-2.5 models in portrait and landscape, with the fast one up to 4K | new model, resolution |
| 11 August 2026 | Seedance | Seedance 2.5 | Seedance 2.5 reaches Runway through its MCP, up to 30 seconds | new model, length |
| 13 August 2026 | Grok Imagine | Grok Imagine 1.5 | Grok Imagine 1.5 reaches Runway's MCP, 1 to 15 seconds with audio | new model, sound |
| 14 August 2026 | Seedance | Seedance 2.5 | Seedance 2.5 at 1080p on Higgsfield, in early access | resolution |
| 15 August 2026 | Seedance | Seedance 2.5 | Seedance 2.5 at 1080p across Runway | resolution |
| 18 August 2026 | LTX | LTX-2.5 | Audio-to-video gets the same resolution tiers as the other modes | sound, resolution |
| 19 August 2026 | LTX | Not named in the note | Audio-to-video takes a frame rate, a last frame and camera motion | sound, frames, camera |
| 20 August 2026 | Runway | Runway Ruby | Ruby converts SDR video to HDR | new model, resolution |
| 20 August 2026 | Wan | Wan 3.0 | Wan 3.0 Prime, a faster version with the same capabilities | tiers |
| 24 August 2026 | Wan | Wan 3.0 | Wan 3.0 and Wan 3.0 Prime arrive on Higgsfield, up to 30 seconds | new model, length |
| 24 August 2026 | Wan | Wan 3.0 | Wan 3.0 arrives in Runway at 480p, 720p or 1080p | new model, resolution |
| 27 August 2026 | Gemini Omni | Gemini Omni 1.1 Flash | Gemini Omni 1.1 Flash goes GA with extension, first-and-last-frame input and 360p to 4K output | new model, access, length, frames, resolution |
| 28 August 2026 | Gemini Omni | Gemini Omni 1.1 Flash | Gemini Omni 1.1 Flash on Higgsfield, up to 10 seconds and 4K | frames, resolution, length |
| 31 August 2026 | MiniMax Hailuo | MiniMax H3 Max | MiniMax H3 Max, a variant tuned for prompt adherence, on Higgsfield | tiers, frames |
| 2 September 2026 | LTX | LTX-2.5 | LTX-2.5 Pro renders 1440p and 4K in both orientations and takes 48 fps | resolution |
| 14 September 2026 | Vidu | Vidu Q3 | Vidu Q3 reference-to-video models for drama and for ads are listed on Model Studio | new model, references |
| 17 September 2026 | Runway | Not named in the note | Frame-rate conversion up to 120 fps, 4K and five minutes | resolution |
| 18 September 2026 | Kling AI | Kling 3.0 | Kling 3.0 and O3 models, including 4K, reach Runway's MCP | new model |
| 22 September 2026 | Seedance | Seedance 2.5 | A 480p Draft Mode for Seedance 2.5 on Higgsfield, before the 1080p final | tiers |
| Undated tier row | MiniMax Hailuo | MiniMax H3 | SceneMixer's tier list carries MiniMax H3 and an H3 Fast tier, each up to 15 seconds a clip | tiers, length |
| Undated version row | Seedance | Seedance 1.0 Pro | Seedance 1.0 Pro: 2 to 12 seconds, up to 1080p, first and last frames | length, resolution, frames |
| Undated version row | Seedance | Seedance 1.5 Pro | Seedance 1.5 Pro: 4 to 12 seconds, up to 1080p, now marked retired | length |
| Undated version row | Seedance | Seedance 2.0 | Seedance 2.0: 4 to 15 seconds, up to 4K, multimodal references, editing and extension | length, resolution, references, editing |
| Undated version row | Seedance | Seedance 2.0 Mini | Seedance 2.0 Mini: 480p and 720p, 4 to 15 seconds | tiers |
| Undated version row | Seedance | Seedance 2.5 | Seedance 2.5: 4 to 30 seconds, 1080p in 10-bit | length, resolution |
| Undated tier row | Wan | Wan 3.0 | SceneMixer's tier list carries Wan 3.0 at 480p, its default, and at 720p and 1080p, each up to 30 seconds a clip | tiers, resolution, length |
| Undated tier row | Wan | Wan 3.0 | Wan 3.0 is one of SceneMixer's two video paths, with its 720p tier marked recommended | tiers, 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.