MiniMax Hailuo and Wan: camera docs compared
The docs of MiniMax Hailuo and Wan part on 4 of the six camera points: camera moves, framing, cuts and negative prompt. They read alike on frames and motion amount. As of 2026-09-25.
| Field | MiniMax Hailuo | Wan |
|---|---|---|
| How a camera move is asked for | Commands or presets | Words in the prompt |
| Shot sizes and angles in the docs | None in the docs | Defined in a glossary |
| Cuts inside one generation | None in the docs | Several shots per clip |
| Start and end frames | First and last frame | First and last frame |
| A negative prompt | None in the docs | A negative prompt field |
| A setting for how much the picture moves | None in the docs | None in the docs |
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
MiniMax Hailuo reads “Commands or presets” on camera moves, while Wan reads “Words in the prompt” on camera moves. MiniMax Hailuo's docs say nothing about cuts inside a clip, while Wan reads “Several shots per clip” on cuts inside a clip. Only Wan documents a negative prompt field. MiniMax Hailuo's docs use 9 of the site's camera words and Wan's use 15, sharing pan, push-in, pull-out and tracking shot.
2The differing points, in the docs' words
How a camera move is asked for
Supported 15 camera commands
MiniMax, text-to-video API reference
Each camera move carries an emotional intent: a push-in creates intimacy or tension
Alibaba Cloud Model Studio, Wan prompt guide
Shot sizes and angles in the docs
MiniMax Hailuo: the docs read do not cover this.
Aesthetic control: Includes light source, lighting environment, shot size, camera angle, lens, and camera movement.
Alibaba Cloud Model Studio, Wan prompt guide
Cuts inside one generation
MiniMax Hailuo: the docs read do not cover this.
Generate coherent multi-shot narratives with control over structure, camera position, and duration.
Alibaba Cloud Model Studio, Wan prompt guide
A negative prompt
MiniMax Hailuo: the docs read do not cover this.
Use negative_prompt to exclude the "flower" element and prevent it from appearing in the video.
Alibaba Cloud Model Studio, Wan text-to-video API reference
- prompt parameterFifteen bracketed camera commands, such as [Truck left] or [Push in], combined or in sequence
- Formula elementsCamera moves are prompt words, each tied to an intent: push-in, pull-out, tracking, orbit, fixed
- Aesthetic controlA prompt dictionary covers shot size, camera angle and lens alongside light and movement
- Multi-shot formulaA multi-shot formula numbers the shots and gives each a time range inside one video
- Use a negative promptA negative_prompt field excludes elements from the video
3MiniMax Hailuo, Wan and a third set of camera docs
| 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 |
| 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.