Text2Movie

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

Open-Sora 2.0: motion amount

On a setting for how much the picture moves, Open-Sora 2.0 reads “A motion setting”. A motion score, 4 by default, fed into the prompt; a dynamic setting lets a scorer choose it. As of 2026-09-25.

During inference, you can use the following command to generate videos with motion score (the default score is 4)

HPC-AI Tech, Open-Sora repository

1Beside the other models

5 other models read the same way: Leonardo Motion 2.0, Midjourney, PixVerse, Step-Video-TI2V and Vidu.

The reading goes no further than the quoted line.

2About the field

A motion setting is the blunt instrument beside camera words: it changes how much happens rather than what happens.

Motion amount, this model markedDark marks are points the docs do not cover or could not be read.Motion amount, this model markedReadingAdobe Firefly — Reading: None in the docsAdobe FireflyGoogle Veo — Reading: None in the docsGoogle VeoGrok Imagine — Reading: None in the docsGrok ImagineHiggsfield — Reading: None in the docsHiggsfieldHunyuanVideo 1.5 — Reading: None in the docsHunyuanVideo 1.5Kling AI — Reading: None in the docsKling AILeonardo Motion 2.0 — Reading: A motion settingLeonardo Motion 2.0LTX — Reading: None in the docsLTXLTX Studio — Reading: None in the docsLTX StudioLuma Dream Machine — Reading: None in the docsLuma Dream MachineMidjourney — Reading: A motion settingMidjourneyMiniMax Hailuo — Reading: None in the docsMiniMax HailuoMoonvalley Marey — Reading: None in the docsMoonvalley MareyOpen-Sora 2.0 — Reading: A motion settingOpen-Sora 2.0Pika — Reading: None in the docsPikaPixVerse — Reading: A motion settingPixVerseRunway — Reading: None in the docsRunwaySceneMixer — Reading: None in the docsSceneMixerSeedance — Reading: N/A, docs unreadableSeedanceSkyReels — Reading: None in the docsSkyReelsSora — Reading: None in the docsSoraStep-Video-TI2V — Reading: A motion settingStep-Video-TI2VVidu — Reading: A motion settingViduWan — Reading: None in the docsWan
Fig. 1 Dark marks are points the docs do not cover or could not be read.
A setting for how much the picture moves, all 24 models, read 2026-09-25.
ModelReading
Adobe FireflyNone in the docs
Google VeoNone in the docs
Grok ImagineNone in the docs
HiggsfieldNone in the docs
HunyuanVideo 1.5None in the docs
Kling AINone in the docs
Leonardo Motion 2.0A motion setting
LTXNone in the docs
LTX StudioNone in the docs
Luma Dream MachineNone in the docs
MidjourneyA motion setting
MiniMax HailuoNone in the docs
Moonvalley MareyNone in the docs
Open-Sora 2.0A motion setting
PikaNone in the docs
PixVerseA motion setting
RunwayNone in the docs
SceneMixerNone in the docs
SeedanceN/A, docs unreadable
SkyReelsNone in the docs
SoraNone in the docs
Step-Video-TI2VA motion setting
ViduA motion setting
WanNone in the docs

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