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

Was this helpful?

  1. Learn
  2. Advanced
  3. Processing
  4. On-Device

Optimizing Memory

Learn about optimizing processing memory usage

PreviousOn-DeviceNextSupernet

Last updated 8 months ago

Was this helpful?

Within the processing field in the Advanced tab, you can toggle Optimize Memory Usage on and off.

When this option is enabled, Sogni loads and unloads models just-in-time to prevent memory shortages, which can increase latency by approximately 2 seconds in exchange for reducing memory usage. The Stable Diffusion pipeline will lazily load TextEncoder, Unet, Decoder, and SafetyChecker when needed and aggressively unload their resources afterward.

Optimizing memory usage can be advantageous when running resource-intensive models on systems with less than 32GB of RAM, or if the generation process is causing your Mac to run slowly.

This option is automatically enabled if your Mac has less than 16GB of RAM, and it is not recommended to disable it.


Need help? Ask in our Discord!

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