Text2Movie

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

LTX Studio: frames

On start and end frames, LTX Studio reads “First frame only”. Presets are applied to a clip made from a first-frame image on the LTXV model. As of 2026-09-25.

Upload your image for the first frame only, and ensure you’re using the LTXV model

LTX Studio blog, camera motion in the Gen Space

1Beside the other models

6 other models read the same way: Grok Imagine, HunyuanVideo 1.5, Leonardo Motion 2.0, Open-Sora 2.0, Sora and others.

Nothing past the docs is assumed about how the model behaves.

2About the field

A last frame pins where a shot ends, which is what lets it hand over cleanly to the next one.

Frames, this model markedDark marks are points the docs do not cover or could not be read.Frames, this model markedReadingAdobe Firefly — Reading: First and last frameAdobe FireflyGoogle Veo — Reading: First and last frameGoogle VeoGrok Imagine — Reading: First frame onlyGrok ImagineHiggsfield — Reading: None in the docsHiggsfieldHunyuanVideo 1.5 — Reading: First frame onlyHunyuanVideo 1.5Kling AI — Reading: First and last frameKling AILeonardo Motion 2.0 — Reading: First frame onlyLeonardo Motion 2.0LTX — Reading: Several keyframesLTXLTX Studio — Reading: First frame onlyLTX StudioLuma Dream Machine — Reading: First and last frameLuma Dream MachineMidjourney — Reading: First and last frameMidjourneyMiniMax Hailuo — Reading: First and last frameMiniMax HailuoMoonvalley Marey — Reading: Several keyframesMoonvalley MareyOpen-Sora 2.0 — Reading: First frame onlyOpen-Sora 2.0Pika — Reading: First and last framePikaPixVerse — Reading: First and last framePixVerseRunway — Reading: Several keyframesRunwaySceneMixer — Reading: None in the docsSceneMixerSeedance — Reading: N/A, docs unreadableSeedanceSkyReels — Reading: First and last frameSkyReelsSora — Reading: First frame onlySoraStep-Video-TI2V — Reading: First frame onlyStep-Video-TI2VVidu — Reading: First and last frameViduWan — Reading: First and last frameWan
Fig. 1 Dark marks are points the docs do not cover or could not be read.
Start and end frames, all 24 models, read 2026-09-25.
ModelReading
Adobe FireflyFirst and last frame
Google VeoFirst and last frame
Grok ImagineFirst frame only
HiggsfieldNone in the docs
HunyuanVideo 1.5First frame only
Kling AIFirst and last frame
Leonardo Motion 2.0First frame only
LTXSeveral keyframes
LTX StudioFirst frame only
Luma Dream MachineFirst and last frame
MidjourneyFirst and last frame
MiniMax HailuoFirst and last frame
Moonvalley MareySeveral keyframes
Open-Sora 2.0First frame only
PikaFirst and last frame
PixVerseFirst and last frame
RunwaySeveral keyframes
SceneMixerNone in the docs
SeedanceN/A, docs unreadable
SkyReelsFirst and last frame
SoraFirst frame only
Step-Video-TI2VFirst frame only
ViduFirst and last frame
WanFirst and last frame

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