← All genres
VIDEO
Video
Text- and image-to-video. Native audio is the current dividing line.
10 models tracked · 25 releases on record · last movement 5d from Lucy
Where the genre stands
Ordered by most recently shipped
ModelVersion
- LucyDecartCNReal-time video editing over WebRTC — restyle a live feed as it runs.6
- KlingKuaishouCNThe value pick — four entries in the current video top ten.4.0
- HailuoMiniMaxCNVideo model taking image, video and text references at once.3 Max
- VeoGoogle DeepMindUSNative 4K with synchronised audio generated in a single pass.3.2
- LTXLightricksCNOpen WeightsFast video generation with audio, in Pro and Fast tiers.2.5
- SeedanceByteDanceCNLong-form image-to-video. Currently top of the public leaderboards.2.5
- RayLuma AIUSLuma's video model, directed frame by frame with up to 16 keyframes.3.2
- SoraOpenAIUSStill the most physically convincing motion. Removed from the API on 24 September 2026.2
- Gen-4RunwayUSPinnacle cinematic video generation engine with custom motion brushes and depth control.4.5
- WanAlibaba WanxCNOpen WeightsOpen-weight video foundation model supporting 1080P text-to-video and image-to-video.2.2
Everything that shipped
- 5dVIDEOLucyDecartCNNEW DROPLucy 6 is listed on fal.ai.6
- 3wVIDEOKlingKuaishouCNNEW DROPKling 4.0 launches globally with native 4K 10-bit HDR and Omni Reference.4.0
- 3wVIDEOHailuoMiniMaxCNNEW DROPMiniMax launches H3 Max Director mode with native camera path scripting and 3D relighting.3 Max
- 1moVIDEOVeoGoogle DeepMindUSVeo 3.2 integrates Google DeepMind spatial audio and 4K visual resolution.3.2
- 3moVIDEOLTXLightricksCNLTX 2.5 is listed on fal.ai.2.5
- 3moVIDEOHailuoMiniMaxCNMiniMax H3 text-to-video lands with high frame consistency and fluid physics.3
- 3moVIDEOLTXLightricksCNLTX-2.3 ships text-, image- and audio-to-video.2.3
- 3moVIDEOLucyDecartCNLucy 2.5 edits webcam and streamed video live.2.5
- 4moVIDEOSeedanceByteDanceCNSeedance 2.5 extends clip length and shot consistency.2.5
- 5moVIDEORayLuma AIUSRay3.2 adds frame-by-frame direction and a public API.3.2
- 7moVIDEOSoraOpenAIUSSunsetSora 2 deprecated; API removal set for 24 September 2026.2
- 8moVIDEOKlingKuaishouCNKling 3.0 adds multilingual lip sync and cinematic motion controls.3.0
- 9moVIDEOSeedanceByteDanceCNSeedance 2.0 takes the #1 slot on Artificial Analysis.2.0
- 9moVIDEORayLuma AIUSRay3.14: native 1080p, 3x cheaper and 4x faster.3.14
- 11moVIDEOGen-4RunwayUSRunway Gen-4.5 tops the Artificial Analysis text-to-video leaderboard.4.5
- 1yVIDEOVeoGoogle DeepMindUSVeo 3.1 brings true 4K at up to 60fps.3.1
- 1yVIDEOSoraOpenAIUSSora 2 launches with synced audio and a social app.2
- 1yVIDEOKlingKuaishouCN2.5 Turbo cuts cost while improving motion.2.5
- 1yVIDEORayLuma AIUSLuma launches Ray3.3
- 1yVIDEOWanAlibaba WanxCNWan 2.2 releases open weights and inference code.2.2
- 1yVIDEOSeedanceByteDanceCNFirst public Seedance release.1.0
- 1yVIDEOVeoGoogle DeepMindUSVeo 3 introduces synchronised native audio.3.0
- 1yVIDEOKlingKuaishouCNKling 2.0 rebuilds the motion model.2.0
- 1yVIDEOGen-4RunwayUSRunway Gen-4 keeps characters, locations and objects consistent across scenes.4.0
- 1yVIDEOWanAlibaba WanxCNAlibaba open-sources Wan 2.1 matching commercial video generators with consumer GPU support.2.1