Model pair: Kling AI and Step-Video-TI2V

The docs of Kling AI and Step-Video-TI2V part on 4 of the six camera points: framing, cuts, frames and motion amount. They read alike on camera moves and negative prompt. As of 2026-09-25.

Fig. 1 Lit: the docs cover it. Dark: they do not.

Kling AI and Step-Video-TI2V, reading by field, read 2026-09-25.
Field	Kling AI	Step-Video-TI2V
How a camera move is asked for	Words in the prompt	Words in the prompt
Shot sizes and angles in the docs	Shown in examples	None in the docs
Cuts inside one generation	Several shots per clip	None in the docs
Start and end frames	First and last frame	First frame only
A negative prompt	None in the docs	None in the docs
A setting for how much the picture moves	None in the docs	A motion setting

Inclusion rule. The six points every model on the register is read on. Order. The order the points take on every model page.

1How the two differ

Kling AI reads “Several shots per clip” on cuts inside a clip, while Step-Video-TI2V's docs say nothing about cuts inside a clip. Kling AI reads “First and last frame” on start and end frames, while Step-Video-TI2V reads “First frame only” on start and end frames. Only Step-Video-TI2V documents a motion setting. Kling AI's docs use 10 of the site's camera words and Step-Video-TI2V's use 7, sharing pan, tilt, zoom and orbit or arc.

2The differing points, in the docs' words

Shot sizes and angles in the docs

Frontal medium shot, tracking backward in front of the motorcycle
Kling AI, VIDEO 3.0 model user guide

Step-Video-TI2V: the docs read do not cover this.

Cuts inside one generation

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

Step-Video-TI2V: the docs read do not cover this.

Start and end frames

Start & End Frames-to-Video
Kling AI, VIDEO 3.0 model user guide

To incorporate the image condition as the first frame of the generated video, we encode it into latent representations
StepFun, Step-Video-TI2V repository

A setting for how much the picture moves

Kling AI: the docs read do not cover this.

The default motion_score = 5 is suitable for general use.
StepFun, Step-Video-TI2V repository

Multi-shot examples
Shot size and angle open each numbered shot in the guide's examplesKling AI, VIDEO 3.0 model user guide / recorded 2026-09-25
Multi-Shot
A Multi-Shot switch plans transitions, framing and angle changes across shots in one videoKling AI, VIDEO 3.0 model user guide / recorded 2026-09-25
Capabilities table
Start and end frames to video is supported in VIDEO 2.6 and 3.0Kling AI, VIDEO 3.0 model user guide / recorded 2026-09-25
Model summary
The image condition becomes the first frame of the generated videoStepFun, Step-Video-TI2V repository / recorded 2026-09-25
Motion dynamics control
A motion_score setting, 5 by default; 2 for more stability, 10 or 20 for more intense actionStepFun, Step-Video-TI2V repository / recorded 2026-09-25

3Kling AI, Step-Video-TI2V and a third set of camera docs

On the camera points where Kling AI and Step-Video-TI2V part, what SceneMixer's guides say, read 2026-09-25.
Camera point	SceneMixer	Source
Shot sizes and angles in the docs	Each numbered shot in a segment carries a framing change, written by the storyboard step	SceneMixer, AI storyboard generator page
Cuts inside one generation	A segment holds several numbered shots and its length is the sum of them	SceneMixer, AI storyboard generator page

Inclusion rule. Points where the two models above differ and SceneMixer's guides say something; points its guides leave open are not shown. Order. The order the points take on every model page.