Text2Movie

The film language each AI video model's docs let you write

Kling AI: cuts

On cuts inside one generation, Kling AI reads “Several shots per clip”. A Multi-Shot switch plans transitions, framing and angle changes across shots in one video. As of 2026-09-25.

VIDEO 3.0 will automatically plan scene transitions, shot framing, and camera angle changes based on the prompts.

Kling AI, VIDEO 3.0 model user guide

Multi-shot video format: "shot n, m, words; shot n, m, words;" (separated by standard semicolons)

Kling AI, VIDEO 3.0 Omni text-to-video API

1Beside the other models

5 other models read the same way: LTX, SceneMixer, Seedance, Sora and Wan.

The reading goes no further than the quoted line.

2About the field

Cuts inside a clip matter for drama, where a conversation is a sequence of shots. Without them, each shot is a separate generation and the cut happens in an editor.

Cuts, this model markedDark marks are points the docs do not cover or could not be read.Cuts, this model markedReadingAdobe Firefly — Reading: None in the docsAdobe FireflyGoogle Veo — Reading: Editing terms onlyGoogle VeoGrok Imagine — Reading: None in the docsGrok ImagineHiggsfield — Reading: None in the docsHiggsfieldHunyuanVideo 1.5 — Reading: None in the docsHunyuanVideo 1.5Kling AI — Reading: Several shots per clipKling AILeonardo Motion 2.0 — Reading: None in the docsLeonardo Motion 2.0LTX — Reading: Several shots per clipLTXLTX Studio — Reading: None in the docsLTX StudioLuma Dream Machine — Reading: None in the docsLuma Dream MachineMidjourney — Reading: None in the docsMidjourneyMiniMax Hailuo — Reading: None in the docsMiniMax HailuoMoonvalley Marey — Reading: None in the docsMoonvalley MareyOpen-Sora 2.0 — Reading: None in the docsOpen-Sora 2.0Pika — Reading: None in the docsPikaPixVerse — Reading: None in the docsPixVerseRunway — Reading: None in the docsRunwaySceneMixer — Reading: Several shots per clipSceneMixerSeedance — Reading: Several shots per clipSeedanceSkyReels — Reading: None in the docsSkyReelsSora — Reading: Several shots per clipSoraStep-Video-TI2V — Reading: None in the docsStep-Video-TI2VVidu — Reading: None in the docsViduWan — Reading: Several shots per clipWan
Fig. 1 Dark marks are points the docs do not cover or could not be read.
Cuts inside one generation, all 24 models, read 2026-09-25.
ModelReading
Adobe FireflyNone in the docs
Google VeoEditing terms only
Grok ImagineNone in the docs
HiggsfieldNone in the docs
HunyuanVideo 1.5None in the docs
Kling AISeveral shots per clip
Leonardo Motion 2.0None in the docs
LTXSeveral shots per clip
LTX StudioNone in the docs
Luma Dream MachineNone in the docs
MidjourneyNone in the docs
MiniMax HailuoNone in the docs
Moonvalley MareyNone in the docs
Open-Sora 2.0None in the docs
PikaNone in the docs
PixVerseNone in the docs
RunwayNone in the docs
SceneMixerSeveral shots per clip
SeedanceSeveral shots per clip
SkyReelsNone in the docs
SoraSeveral shots per clip
Step-Video-TI2VNone in the docs
ViduNone in the docs
WanSeveral shots per clip

Inclusion rule. Every model on the register, whether or not it has a page of its own on this field. Order. Alphabetical by model name.

3Next on the reel