HunyuanVideo 1.5: negative prompt
Reading for HunyuanVideo 1.5 on a negative prompt: “A negative prompt field”. The inference script takes a negative prompt, empty by default. As of 2026-09-25.
Negative prompt for video generation
Tencent Hunyuan, HunyuanVideo-1.5 repository
- Command line argumentsThe inference script takes a negative prompt, empty by default
1Beside the other models
3 other models read the same way: Google Veo, Leonardo Motion 2.0 and Wan.
The reading goes no further than the quoted line.
2About the field
A negative prompt names what should not appear. Some makers prefer positive phrasing because a model that reads a word may draw it, even after a no.
| Model | Reading |
|---|---|
| Adobe Firefly | None in the docs |
| Google Veo | A negative prompt field |
| Grok Imagine | None in the docs |
| Higgsfield | None in the docs |
| HunyuanVideo 1.5 | A negative prompt field |
| Kling AI | None in the docs |
| Leonardo Motion 2.0 | A negative prompt field |
| LTX | None in the docs |
| LTX Studio | None in the docs |
| Luma Dream Machine | None in the docs |
| Midjourney | None in the docs |
| MiniMax Hailuo | None in the docs |
| Moonvalley Marey | None in the docs |
| Open-Sora 2.0 | None in the docs |
| Pika | None in the docs |
| PixVerse | None in the docs |
| Runway | Advised against |
| SceneMixer | Advised against |
| Seedance | N/A, docs unreadable |
| SkyReels | None in the docs |
| Sora | None in the docs |
| Step-Video-TI2V | None in the docs |
| Vidu | None in the docs |
| Wan | A negative prompt field |
Inclusion rule. Every model on the register, whether or not it has a page of its own on this field. Order. Alphabetical by model name.