Optimizing Memory

Learn about optimizing processing memory usage

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 ✨