> For the complete documentation index, see [llms.txt](https://docs.motorica.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.motorica.com/learn/concepts/styles.md). # Styles
An orange man doing various animated walking movements.
## Overview In Motorica, the virtual actor's performance are always generated based on the model's selected Styles. ## What are Styles? Styles shape the expression, emotion, and character behind an Motorica's animations. They do not impact the root motion selected for animations. Styles are trained using our proprietary ML models grounded in Motorica's Motion Synthesis research. Motorica uses real mocap data, recorded in our in-house mocap studio, to train Style Clones, ensuring that every generated animation comes from a real, human performance. ## Customization The Styles Control tab for both Motion Stage and Motion Factory allows you to select the virtual actor's model, the Styles that shape the model's performance, and the model's scale within its digital space. ### Model Free trial users have access to the provided Public Tango model. For enterprise customers, there are Private Tango models that provide more up-to-date motion capture data for generated animations and additional Styles. ### Style Styles are categorized by their expression, personality, and character. There are currently 7 Style categories: 1. **Basic:** traditional human motions. 2. **Creatures:** non-human characters like zombies and goblins. 3. **Warrior:** characters wielding medieval and fantasy props. 4. **Personalities**: characters based on their status and identity. 5. **Expressions**: emotion-based performances. 6. **Soldier**: modern warfare characters weilding guns and similar props. 7. **Miscellaneous**: unique and varied use-cases. ### Style Mixing The best way to generate unique animations is to combine two styles together. In both Motion Stage and Motion Factory, two styles can be mixed and customized based on each Styles' mix percentage. For example, if you want to mix the `Zombie` Style with the `Normal (M)` Style, you can give the `Zombie` Style a `70%` mix and the `Normal (M)` Style a `30%` mix. With this configuration, the `Zombie` will be more prevalent in generated animations. ### Scale Character Models are scaled based on their hip bone height. The default hip bone height value is `97.1` centimeters for both Motion Stage and Motion Factory. Larger and smaller values will adjust the motion of the animation to correctly fit the values determined in the Motion Controls. For example, increasing the hip bone height will cause the model to take less steps and general movements in their animation, whereas decreasing the hip bone height causes the character to take more steps and increase the movements required to reach the end of an animation. Adjust this value accordingly so your generated animations fit perfectly within your gameplay system and existing character models. ### Seed Animations are deterministically generated based on the Style's seed. Every time an animation is generated, the Style's seed is randomized so you get entirely new animations even when using the same Style and Motion Control values. This also means that generating an animation with the exact same seed value will create an identical animation, as long as the Style and Motion Control values remain the same. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the current page URL with the `ask` query parameter: ``` GET https://docs.motorica.com/learn/concepts/styles.md?ask= ``` The question should be specific, self-contained, and written in natural language. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.