Which AI video models document a negative prompt?
4 of the 24 models: Google Veo, HunyuanVideo 1.5, Leonardo Motion 2.0 and Wan. The other 20 do not, in the docs read. As of 2026-09-25.
| Model | Negative prompt | What the docs say |
|---|---|---|
| Google Veo | A negative prompt field | Negative prompts list elements that should not appear in the video |
| HunyuanVideo 1.5 | A negative prompt field | The inference script takes a negative prompt, empty by default |
| Leonardo Motion 2.0 | A negative prompt field | A negative prompt, switched on under Advanced Settings; the help advises writing what to avoid without no or without |
| Wan | A negative prompt field | A negative_prompt field excludes elements from the video |
Inclusion rule. Models whose own docs meet the condition in the question. Order. Alphabetical by model name.
1Why it matters
A negative prompt names what should stay out of the frame. Few makers document one for video.
2From the docs
Negative prompts are a tool that helps specify the elements that you don't want generated in your video.
Google Cloud, Veo video prompt guide
Negative prompt for video generation
Tencent Hunyuan, HunyuanVideo-1.5 repository
3The rest of the register
Not matching: Adobe Firefly, Grok Imagine, Higgsfield, Kling AI, LTX, LTX Studio, Luma Dream Machine, Midjourney, MiniMax Hailuo, Moonvalley Marey, Open-Sora 2.0, Pika, PixVerse, Runway, SceneMixer, Seedance, SkyReels, Sora, Step-Video-TI2V and Vidu.
- Negative promptsNegative prompts list elements that should not appear in the video
- Command line argumentsThe inference script takes a negative prompt, empty by default
- Negative PromptingA negative prompt, switched on under Advanced Settings; the help advises writing what to avoid without no or without
- Use a negative promptA negative_prompt field excludes elements from the video