Directing MiniMax Hailuo: fifteen bracketed camera commands
MiniMax Hailuo's docs cover 2 of the six points. Camera moves: commands or presets. Frames: first and last frame. Nothing on framing, cuts, negative prompt and motion amount. As of 2026-09-25.
| Model | Camera moves |
|---|---|
| Adobe Firefly | Commands or presets |
| Google Veo | Words in the prompt |
| Grok Imagine | Words in the prompt |
| Higgsfield | Commands or presets |
| HunyuanVideo 1.5 | Words in the prompt |
| Kling AI | Words in the prompt |
| Leonardo Motion 2.0 | Commands or presets |
| LTX | Words in the prompt |
| LTX Studio | Commands or presets |
| Luma Dream Machine | Commands or presets |
| Midjourney | None in the docs |
| MiniMax Hailuo | Commands or presets |
| Moonvalley Marey | Drawn or set from an image |
| Open-Sora 2.0 | None in the docs |
| Pika | Words in the prompt |
| PixVerse | Commands or presets |
| Runway | Words in the prompt |
| SceneMixer | Words in the prompt |
| Seedance | From a reference |
| SkyReels | Words in the prompt |
| Sora | Words in the prompt |
| Step-Video-TI2V | Words in the prompt |
| Vidu | None in the docs |
| Wan | Words in the prompt |
Inclusion rule. All 24 models on the register, each with the way its own docs ask for a camera move. Order. Alphabetical by model name.
- Camera moves
- Commands or presets
- Framing
- None in the docs
- Cuts
- None in the docs
- Frames
- First and last frame
- Negative prompt
- None in the docs
- Motion amount
- None in the docs
1What the docs say
MiniMax documents fifteen bracketed camera commands for its Hailuo models, such as [Truck left] or [Push in], which can be combined inside one bracket or run in sequence. Its guide adds first and last frames and, for the H3 model, camera movement taken from a reference. Shot sizes, negative prompts and a motion setting are not documented.
How a camera move is asked for: Commands or presets
Supported 15 camera commands
MiniMax, text-to-video API reference
- prompt parameterFifteen bracketed camera commands, such as [Truck left] or [Push in], combined or in sequence
- Reference generationThe H3 model can take camera movement from reference images, videos or audio
MiniMax Hailuo, camera moves in detail · How a camera move is asked for, every model
Shot sizes and angles in the docs: None in the docs
- API reference and guide read; shot sizes and angles are not listedNot described in the docs read (2026-09-25)
Shot sizes and angles in the docs, every model
Cuts inside one generation: None in the docs
- Guide read; several shots inside one generation are not describedNot described in the docs read (2026-09-25)
Cuts inside one generation, every model
Start and end frames: First and last frame
Control the starting or ending frame; bring a specific frame naturally to life
MiniMax, video generation guide
- First/last-frame image-to-videoA first-frame image, a last-frame image or both can be set
MiniMax Hailuo, frames in detail · Start and end frames, every model
A negative prompt: None in the docs
- API reference read; no negative prompt field is listedNot described in the docs read (2026-09-25)
A negative prompt, every model
A setting for how much the picture moves: None in the docs
- API reference read; no setting for the amount of motion is listedNot described in the docs read (2026-09-25)
A setting for how much the picture moves, every model
2Camera words in its docs
pan · tilt · truck · pedestal · push-in · pull-out · zoom · tracking shot · static shot
3Neighbouring models
- MiniMax Hailuo and Kling AI
- MiniMax Hailuo and Seedance
- MiniMax Hailuo and Wan
- Luma Dream Machine
- Midjourney
- Moonvalley Marey
- Open-Sora 2.0
How the docs were read: the method.
4Docs read
- MiniMax, text-to-video API reference, read 2026-09-25
- MiniMax, video generation guide, read 2026-09-25