HunyuanVideo 1.5: camera moves written into demo prompts
HunyuanVideo 1.5's docs cover 4 of the six points. Camera moves: words in the prompt. Framing: shown in examples. Frames: first frame only. Negative prompt: a negative prompt field. Nothing on cuts 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
- Words in the prompt
- Framing
- Shown in examples
- Cuts
- None in the docs
- Frames
- First frame only
- Negative prompt
- A negative prompt field
- Motion amount
- None in the docs
1What the docs say
Tencent's HunyuanVideo 1.5 repository is an open model whose demo prompts carry the camera in plain words: circling the subject, tilting down slowly, zooming in, handheld, a medium shot from a level angle. The inference script takes a negative prompt, and the model does both text-to-video and image-to-video. No named commands, cuts or motion setting are documented.
How a camera move is asked for: Words in the prompt
The camera circles around the subject to capture the spin from all angles.
Tencent Hunyuan, HunyuanVideo-1.5 repository
- Demo promptsCamera movement is written into the prompt; the demo prompts circle, tilt and zoom the camera
HunyuanVideo 1.5, camera moves in detail · How a camera move is asked for, every model
Shot sizes and angles in the docs: Shown in examples
slowly advancing medium shot, shot from a level angle
Tencent Hunyuan, HunyuanVideo-1.5 repository
- Demo promptsShot size and angle appear in the demo prompts, such as a medium shot from a level angle
HunyuanVideo 1.5, framing in detail · Shot sizes and angles in the docs, every model
Cuts inside one generation: None in the docs
- Repository 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 frame only
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
- AbstractText-to-video and image-to-video in one framework
HunyuanVideo 1.5, frames in detail · Start and end frames, every model
A negative prompt: A negative prompt field
Negative prompt for video generation
Tencent Hunyuan, HunyuanVideo-1.5 repository
- Command line argumentsThe inference script takes a negative prompt, empty by default
HunyuanVideo 1.5, negative prompt in detail · A negative prompt, every model
A setting for how much the picture moves: None in the docs
- Repository read; no setting for the amount of motion is describedNot described in the docs read (2026-09-25)
A setting for how much the picture moves, every model
2Camera words in its docs
tilt · zoom · handheld · static shot · close-up · medium shot · low angle
3Neighbouring models
- HunyuanVideo 1.5 and Pika
- HunyuanVideo 1.5 and PixVerse
- Grok Imagine
- Higgsfield
- Kling AI
- Leonardo Motion 2.0
How the docs were read: the method.
4Docs read
- Tencent Hunyuan, HunyuanVideo-1.5 repository, read 2026-09-25