Stable Diffusion Backstage

Streamline model and machine management with Stable Diffusion Backstage, reducing time and costs.

Yile partnered with Going Cloud to build a Stable Diffusion backstage. Efficiently manage models and machines with the Stable Diffusion Backstage service, saving time and costs associated with administration.

About

Yile Technology

Established in 2018, Yile Technology is comprised of 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."

Challenge and Solution
Various Models Require Time and Cost-Efficient Management

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

Customized the Stable Diffusion Backstage service to establish a backend system

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

Model Management: Centralized management of all models, with the ability to allocate them to different machines.

File Upload: Support for uploading various training data and Extra Networks(*).

Machine Scheduling: Support for scheduling machine power on/off daily to save costs during idle periods.

Cost Monitoring: Visualization of machine usage costs, with alerts for different departmental usage patterns, machine type, and consumption.

* A Stable Diffusion function which can enhances image quality, adds styles, optimizes tasks, supports diverse inputs.

Solution Architecture

Deploy Machine Learning Models with AWS SageMaker Without Managing Servers

Result
Optimizing Efficiency and Reducing Costs with Going Cloud's Stable Diffusion Service

With the Going Cloud Stable Diffusion Backstage service, Yile Technology efficiently manages Stable Diffusion models, enabling colleagues from different departments to share uploaded models in a unified backend. Additionally, through visual analysis of usage cost data, they gain insights into departmental usage patterns and machine utilization, effectively controlling overall costs, reducing unnecessary expenditures, and optimizing overall efficiency.

back icon
Back to Top icon
Top