It is a shortcut for a paragraph you would otherwise write. Selecting a preset shifts the whole generation towards a family of grade, texture and rendering conventions that the model already knows by that name, which is both more reliable and more repeatable than an ad-hoc description.
The repeatability is the real value. Six clips that each describe their own look in prose will drift apart; six clips on one preset share a grade, which is most of what makes a set read as a set. That is why presets matter more for multi-shot pieces than for one-offs.
They are also blunt. A preset touches everything, so it will happily make a product shot cinematic in ways that hurt a product shot. When a preset is nearly right, the prompt is where you claw back the specific corrections.
In practice
- Presets are model-specific vocabulary — the same name on two models is not the same look.
- Pick the preset first, then write the prompt inside it, rather than fighting it afterwards.
- For a series, lock one preset across every shot before you worry about anything else.
Style presets in the catalog
Named looks a model will apply without you describing them in the prompt. 91 of the 296 models in the Versely catalog qualify.
| Model | Provider | Type |
|---|---|---|
| Kling 2.5 Turbo | Kling | Video |
| Grok Imagine Video | Grok | Video |
| VEO 3.1 | Video | |
| Seedream 4.0 | ByteDance | Image |
| Pixverse V4 | Pixverse | Video |
| Kling Video V2.6 Pro Text to Video | Kling | Video |
| Wan V2.6 Text to Video | Wan | Video |
| Wan 2.6 Text to Image | Wan | Image |
Browse all 36 spec pages for full settings, resolutions and credit costs.
The mistake to avoid
Stacking a preset with a prompt that describes a different style. The two average out and you get neither.
Related terms
Prompt
A prompt is the written instruction a generative model reads to decide what to make — the one input almost every model requires.
Aspect ratio
Aspect ratio is the proportion between an output's width and its height, written as two numbers — 16:9 for landscape, 9:16 for a full phone screen.
Character consistency
Character consistency is whether the same person, mascot or product still looks like itself across separate generations.
Text-to-image
Text-to-image renders a still picture from a written description, with no picture going in.
Seed
A seed is the number that decides the random starting noise for a generation, so the same seed with the same settings reproduces the same output.
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.