Model pair: HunyuanVideo 1.5 and PixVerse

The docs of HunyuanVideo 1.5 and PixVerse part on 5 of the six camera points: camera moves, framing, frames, negative prompt and motion amount. They read alike on cuts. As of 2026-09-25.

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

HunyuanVideo 1.5 and PixVerse, reading by field, read 2026-09-25.
Field	HunyuanVideo 1.5	PixVerse
How a camera move is asked for	Words in the prompt	Commands or presets
Shot sizes and angles in the docs	Shown in examples	None in the docs
Cuts inside one generation	None in the docs	None in the docs
Start and end frames	First frame only	First and last frame
A negative prompt	A negative prompt field	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

HunyuanVideo 1.5 reads “Words in the prompt” on camera moves, while PixVerse reads “Commands or presets” on camera moves. HunyuanVideo 1.5 reads “First frame only” on start and end frames, while PixVerse reads “First and last frame” on start and end frames. Only HunyuanVideo 1.5 documents a negative prompt field. Only PixVerse documents a motion setting. HunyuanVideo 1.5's docs use 7 of the site's camera words and PixVerse's use 0, with none in common.

2The differing points, in the docs' words

4 of the 5 differing points are quoted below; the others are in the table above.

How a camera move is asked for

The camera circles around the subject to capture the spin from all angles.
Tencent Hunyuan, HunyuanVideo-1.5 repository

Use this field to apply camera movement if needed.
PixVerse, platform text-to-video API

Start and end frames

we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions.
Tencent Hunyuan, HunyuanVideo-1.5 repository

Transition(First-last frame) generation
PixVerse, platform text-to-video API

A negative prompt

Negative prompt for video generation
Tencent Hunyuan, HunyuanVideo-1.5 repository

PixVerse: the docs read do not cover this.

A setting for how much the picture moves

HunyuanVideo 1.5: the docs read do not cover this.

"motion_mode": "normal"
PixVerse, platform text-to-video API

Demo prompts
Camera movement is written into the prompt; the demo prompts circle, tilt and zoom the cameraTencent Hunyuan, HunyuanVideo-1.5 repository / recorded 2026-09-25
Request example
A camera_movement field applies a named move such as zoom_inPixVerse, platform text-to-video API / recorded 2026-09-25
Abstract
Text-to-video and image-to-video in one frameworkTencent Hunyuan, HunyuanVideo-1.5 repository / recorded 2026-09-25
API contents
A Transition endpoint generates video between a first and a last framePixVerse, platform text-to-video API / recorded 2026-09-25
Command line arguments
The inference script takes a negative prompt, empty by defaultTencent Hunyuan, HunyuanVideo-1.5 repository / recorded 2026-09-25
Request example
A motion_mode field sits in the request, set to normal in the examplePixVerse, platform text-to-video API / recorded 2026-09-25

3HunyuanVideo 1.5, PixVerse and a third set of camera docs

On the camera points where HunyuanVideo 1.5 and PixVerse part, what SceneMixer's guides say, read 2026-10-13.
Camera point	SceneMixer	Source
How a camera move is asked for	Camera moves are written into each shot's text: fixed, handheld, tracking or a slow push in	SceneMixer, how to write one shot
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
A negative prompt	Negative wording is advised against: the guide says to describe what is there, because a named absence tends to be drawn	SceneMixer, say what is there guide

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.