Basics
Generation Steps
Learn about using the steps parameter within your creations
What are steps within Sogni generations?
Steps are the number of steps in the diffusion process determines how many iterations the image goes through.
Each additional step introduces small, incremental changes to the image, allowing for further refinement. You can generate images with up to 150 steps, providing a high level of control over the final result.
Sogni uses the super efficient DPM Solver scheduler by default, which achieves impressive results in just 20 or 25 steps, ensuring both efficiency and quality. You can select other Schedulers and Time Spacing algorithms in the Advanced tab of the Control Bar.
Tip: To expedite the generation process, start with a smaller number of steps, typically between 15 and 30. During this stage, you can type or edit your prompt, adjust other settings, and more. Once you achieve a satisfactory image, you can lock the seed and increase the number of steps to regenerate the image with enhanced detail and quality, refining it to your desired outcome.
Each additional step introduces small, incremental changes to the image, allowing for further refinement. You can generate images with up to 150 steps, providing a high level of control over the final result.
Sogni uses the super efficient DPM Solver scheduler by default, which achieves impressive results in just 20 or 25 steps, ensuring both efficiency and quality. You can select other Schedulers and Time Spacing algorithms in the Advanced tab of the Control Bar.
Tip: To expedite the generation process, start with a smaller number of steps, typically between 15 and 30. During this stage, you can type or edit your prompt, adjust other settings, and more. Once you achieve a satisfactory image, you can lock the seed and increase the number of steps to regenerate the image with enhanced detail and quality, refining it to your desired outcome.
How to adjust the Steps
To adjust the steps, you can do this within Sogni's user interface by clicking the arrows up or down or by moving the scale.
About Latent Consistency Models (LCM) and SDXL-Turbo
These models can generate high-quality images much faster, requiring only 1 to 8 steps with a Guidance Scale between 1-3. By running an LCM or SDXL-Turbo on your M1 or M2 Mac, you can generate images at a rate of one per second.
When you select the LCM scheduler, the values of the Steps and Guidance Controls are automatically adjusted for a more fine-grained setup. The default values are set to 3 steps and a Guidance Scale of 1.015.
When you select the LCM scheduler, the values of the Steps and Guidance Controls are automatically adjusted for a more fine-grained setup. The default values are set to 3 steps and a Guidance Scale of 1.015.
Real-Time Generation: (macOS only)
When working with LCM or SDXL-Turbo and the LCM Scheduler, the option to generate images in "Real-Time" as you make changes to your settings becomes available. This allows you to see result changes as you type your prompt, adjust the Guidance Scale, switch styles, etc.
To enable Real-Time Generation, use the lightning button (⚡️) located next to the Steps and Guidance knobs.
To enable Real-Time Generation, use the lightning button (⚡️) located next to the Steps and Guidance knobs.
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, please feel free to join our Discord today!