Stable Diffusion Backstage | Going Cloud Use Case

About

Yile Technology

Established in 2018, Yile Technology comprises a professional operations team passionate about gaming, focused on development and marketing. With a commitment to innovation and excellence, they develop high-quality game apps such as Bao Ni Fa and G-bao Online.

‍

Solution

Streamlining Operations with Stable Diffusion Backstage Service

To meet the diverse design needs of different departments, Yile needed to deploy various training models across multiple machines. They sought a flexible and unified management solution to save time and control machine usage costs effectively.

Going Cloud customized the Stable Diffusion Backstage service to establish a backend system tailored to the client's needs, providing the following functionalities:

‍
‍
Key Features

Model Management: Centralized management of all models, along with the flexibility to allocate each model to different machines as needed.
Diversified Content Creation: Enabling upload of various training data and Extra Networks* function for enhanced image creation capability.
Machine Scheduling: Optimizing machine schedule by managing daily power operations and automatically powering off machines during idle times.
Cost Monitoring: Visualization of machine usage costs, including alerts for different departmental usage patterns, machine type, and consumption.

_{*Extra Networks: A Stable Diffusion function used to manage and apply specialized add-on files, enabling customization of images.}

‍

Key Features

Solution Architecture

Result

Optimized Efficiency and Reduced Costs

The introduction of the customized Stable Diffusion Backstage enabled Yile Technology to;

Manage various Stable Diffusion models efficiently, with users from different departments sharing uploaded models in a unified platform.
Gain insights on departmental usage patterns and machine utilization for enhanced cost management.

Stable Diffusion Backstage for Yile Technology