> For the complete documentation index, see [llms.txt](https://metacreate.gitbook.io/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://metacreate.gitbook.io/docs/welcome/controls-and-settings.md).
# Controls and Settings
MetaCreate gives you creative control without overwhelming complexity. These settings shape how your image, video, or audio output turns out. Each slider or toggle affects a different part of the generation flow.
***
### Steps (Inference Steps)
Controls the balance between speed and detail.
* Lower steps → fast drafts
* Higher steps → sharper, more polished results
Use fewer for experiments, more for finals.
***
### Seed
Every generation starts with a “random seed.”
* Same prompt + same seed → similar output
* Changing the seed → new variations
Useful for exploring alternate versions of the same idea.
***
### CFG Scale (Guidance Scale)
Defines how closely the output follows your prompt.
* Lower values → more creativity
* Higher values → stricter interpretation
A mid-range value works for most creators.
***
### Aspect Ratio / Image Size
Sets the shape of your output.
* 1:1 (square) for general visuals
* 9:16 (portrait) for people and social content
* 16:9 (wide) for landscapes and cinematic frames
Pick the ratio that matches your use-case.
***
### Strength (Image-to-Image / Inpainting)
Determines how strongly the model changes your original image.
* Low strength → mostly preserve the original
* High strength → significant transformation
Great for edits, style changes, or partial replacements.
***
### Negative Prompt
Tells the system what you want to avoid.\
Useful for removing unwanted elements like blur, distortions, or specific styles.
***
### Safety Tolerance / Safety Checker
Controls how strict the system is with sensitive or edgy content.
* Low tolerance → brand-safe
* Higher tolerance → more freedom
Fine-tune based on your project or audience.
***
### Style / Style Name
Quickly switch between visual flavors like:
* Realism
* Anime
* 3D
* Sketch
* Cinematic
* Artistic
Choosing a style gives your output an instant identity.
***
### Schedulers
Advanced control for shaping the generation process.\
Affects speed, consistency, and the final aesthetic.\
Most users don’t need to adjust this unless experimenting.
***
### Mask URL (Inpainting)
Marks areas of the image you want changed.\
Only the masked parts get edited — everything else stays intact.\
Ideal for removing objects, replacing backgrounds, or fixing details.
***
### Expand Prompt / Prompt Optimizer
Turns short prompts into richer, more descriptive ones.\
Helpful for beginners or for getting consistent high-quality results.
***
### Motion / Duration (Video Models)
Controls how long your generated video is and how dynamic the motion feels.\
Works for everything from subtle loops to more expressive movements.
***
### Voice / Style (TTS & Audio)
Choose how your audio output sounds.
Exmples:
* Narrator
* Conversational
* Dramatic
* Whisper
* Energetic
Perfect for voiceovers, characters, trailers, or branded audio.
---
# 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, and the optional `goal` query parameter:
```
GET https://metacreate.gitbook.io/docs/welcome/controls-and-settings.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.