🎨
AI Art Tutorials - Web Version
  • Artroom Basics
    • Overview
    • Link to Local Version Tutorial
  • Resources
    • Settings Tutorials
      • Starter Settings
        • Video tutorial
      • Image Scale
      • Steps
      • Prompt Strength (CFG)
      • Base Image (img2img)
      • Variation Strength
      • Sampler
      • Clip Skip
      • Seed
      • VAE
      • SD Settings (Importing settings)
    • Prompting Tutorials
      • Basic Prompt Structure
      • Prompt order
      • Negative Prompts
      • Weights
      • Example Prompts
        • Art Styles
        • Art Medium
        • Attributes
          • Camera Specific Attributes
          • Effects
        • Artists
          • Asian
          • Glamour Style
          • Renaissance
          • Splash
          • Misc
        • Prompt Repositories
        • Prompt Generators
          • Clip Interrogator
          • Deep Danbooru
      • Prompt Pitfalls
      • Prompt Myths
    • Models
      • Recommended Models
        • Realistic
        • Anime/Drawn
        • Artistic
        • Tabletop Gaming
      • How to test your models?
    • Extra Features Tutorials
      • The Paint Tab
        • Tools and Functions
          • The Workspace
          • The Tools - in depth
          • Canvas Settings
        • Inpaint
        • Outpaint
        • Image Editor (GIMP/Photoshop) Assist
        • Palette Fix
        • Paint Tab Video Tutorials
      • Loras
      • ControlNet
        • Using ControlNet
        • Pose kits and Saved Preprocessed Images
      • Removing Backgrounds
      • Upscaling
        • Standard Upscalers
        • Highres Fix
      • Model Merging
      • Image Viewer
      • Settings Tab
  • Glossary
  • Guides By AI Artists
    • About this Category
    • Generating Characters for Tabletop Games
    • Turning Your Scribble Into an Image
Powered by GitBook
On this page
  1. Resources
  2. Settings Tutorials

Starter Settings

PreviousSettings TutorialsNextVideo tutorial

Last updated 1 year ago

All of these settings can be rather subjective, so don't be afraid to play around with them. I´m going top to bottom.

Height / Width. No less than 384x512 No larger than 768x768 -> Larger images can cause multiple people to appear. Use upscaler to make your images larger. Image Scale

Model: Pick one of the UMI models from here. (They should already have been downloaded with Artroom) Models

  • Umi Aphrodite for Realistic images

  • Umi Olympus for Anime images

Image Variation Strength: This is only used when you are using a starting image. Variation Strength

Number of Steps: 30 Steps

Prompt Strength: 7 Prompt Strength (CFG)

Sampler: Euler Ancestral Sampler

Clip Skip: 1 Clip Skip

Seed: Random Seed

VAE: The VAE the model recommends. Usually listed on the model page. VAE

Logo[Umi AI] Mythology and Babes by DutchAlex | Stable Diffusion Checkpoint | Civitai
Example of weird results. I did not cut this image, thats how it was genned.