Text2Movie

The film language each AI video model's docs let you write

Which AI video models' docs advise against negative wording?

2 of the 24 models: Runway and SceneMixer. The other 22 do not, in the docs read. As of 2026-10-13.

The register, split by the questionWhich AI video models' docs advise against negative wording? 2 models match and 22 do not.RegisterMatch2 models: Runway and SceneMixerNo match22 models
Fig. 1 Counted from the models' docs on this page.
Models that answer the question, read 2026-10-13.
ModelNegative promptWhat the docs say
RunwayAdvised againstThe guide advises positive phrasing and avoiding negative prompts
SceneMixerAdvised againstNegative wording is advised against: the guide says to describe what is there, because a named absence tends to be drawn

Inclusion rule. Models whose own docs meet the condition in the question. Order. Alphabetical by model name.

1Why it matters

Several models take a negative prompt field; some guides say the opposite, that naming what should not appear tends to put it on screen. Knowing which camp a model's docs are in decides how a shot list is phrased.

2From the docs

Use positive phrasing and avoid negative prompts

Runway, Gen-4 video prompting guide

The fix is always the same: say what is there.

SceneMixer, say what is there guide

3The rest of the register

Not matching: Adobe Firefly, Google Veo, Grok Imagine, Higgsfield, HunyuanVideo 1.5, Kling AI, Leonardo Motion 2.0, LTX, LTX Studio, Luma Dream Machine, Midjourney, MiniMax Hailuo, Moonvalley Marey, Open-Sora 2.0, Pika, PixVerse, Seedance, SkyReels, Sora, Step-Video-TI2V, Vidu and Wan.

4Related questions