Sogni: Learn
Visit Sogni.ai
  • 👋Welcome to Sogni
  • Learn
    • ❓FAQs
    • 😍Basics
      • Prompts
        • Dynamic Prompts
        • Prompt Length Token Limits
      • Switching Processing
      • Generating Batches
      • Generation Seed
      • Inference Steps
      • Guidance Scale
      • RealTime Generation (MacOS)
      • Guide Image
      • ControlNet
        • Preprocessors
        • ControlNet Models
      • Canvas
      • Masks
      • Creating Animations & Videos
    • 🤓Advanced
      • Preview Count
      • Upscaling Images
      • Schedulers
      • Processing
        • On-Device
          • Optimizing Memory
        • Supernet
      • Safe Content Filter
    • 🤖Models
      • About AI Models
      • Model Types
      • Available Models
      • Importing Stable Diffusion Models
      • Model Storage & Deleting Models
      • About Switching Models on Supernet
    • Telegram AI Sticker Bot
  • Tutorials
    • 🎥Video Tutorials
    • 🎓Guides
      • Controlling the Output
      • How to Transfer a Face From One Image to Another
      • How to generate Photorealistic Faces
      • How to Transform a Simple Sketch into Stunning Images
      • How to Create Subject-Steady Animations with Dynamic Backgrounds
      • How to use multiple ControlNets to generate a Single Image
      • How to generate larger batches of images (more than 16 at a time)
      • ▶️How to use Mask Tool
      • ▶️How to Mix Images
      • ▶️How to Extend Images with Canvas
  • Testnet
    • 💫About the Sogni Testnet
      • 💫Joining the Sogni Testnet
      • ⭐Spark Points
    • About Sogni Supernet
  • Sogni Studio Pro
    • Sogni Studio vs Sogni Studio Pro
    • ⬇️Installing Sogni Studio Pro
    • 🔒Why It's Safe to Download Sogni Studio Pro
    • ✅Updating Sogni Studio Pro
    • Account & Wallet
      • Supernet Generation Costs
    • 🐝Worker Mode
    • 🚧How to Recover Your Password
    • 🦊How to Add Your Sogni Wallet to MetaMask
  • Sogni Pocket
    • 📲Downloading Sogni Pocket
  • SOGNI FAST WORKER
    • 🐝About Sogni Fast Worker
    • ⬇️Running Sogni Fast Worker Locally
    • ⬇️Running Sogni Fast Worker Remotely
    • ❓Fast Worker FAQ
    • 🧠Sogni Fast Worker Advanced Configuration
  • Rewards
    • 🙋Account Creation & Verification Reward
    • 🌟Daily Boost Reward
    • 🌟Referral Reward
Powered by GitBook
On this page
  • About Schedulers
  • Available Schedulers & Time Step Spacing Algorithms Schedulers

Was this helpful?

  1. Learn
  2. Advanced

Schedulers

Learn about using schedulers within Sogni

About Schedulers

Schedulers are crucial in the denoising process, executing multiple iterative steps to transform a noisy image into a clean one. They manage the diffusion process, introducing random noise and gradually removing it to generate new data samples.

These components define a trade-off between denoising speed and quality. Choosing the right scheduler can be complex, with no clear quantitative measure for optimal performance. It's recommended to experiment and find the scheduler that works best for your specific creative project and system.


Available Schedulers & Time Step Spacing Algorithms Schedulers

DPM Solver Multistep: Default selection, employing the DPM-Solver++ algorithm.

PNDM (Pseudo-linear multi-step): Utilizes the pseudo linear multi-step (PLMS) method, excluding pseudo Runge-Kutta (PRK) steps.

LCM (Latent Consistency Models): Designed for LCM models and SDXL-Turbo, requiring only 1 to 8 steps compared to the 20-50 steps required by regular models.LCM models typically yield better results with 2 to 8 steps and a low Guidance Scale of 1-2. When you select the LCM scheduler, the Steps and Guidance Controls' value scale is automatically adjusted to allow for a more fine-grained value setup. On macOS, you also get the option to enable "Real-Time Generation".

Time Spacing: Time Spacing determines how time steps are spaced and offers three options: Linear, Leading, and Karras.

‍Note: The Time Spacing setting has no effect when the LCM Scheduler is selected.

‍Tip: When utilizing SDXL models, the default Time Spacing option is Karras. However, when generating animations with the use of a Guide Image, it is advisable to switch to Linear or Leading to prevent image degradation.

You can make changes to your Scheduler within the Advanced Tab in Sogni


Need help? Ask in our Discord!

PreviousUpscaling ImagesNextProcessing

Last updated 8 months ago

Was this helpful?

For any questions regarding the use of Sogni, tips, suggestions, bugs, sharing art, discussing AI and life, or simply hanging out... Join our Discord community! ✨

🤓
Join Sogni Discord