Skip to main content

​
1.1 What is GMI Studio

GMI Studio is a cloud‑native workflow editor and execution environment for running Comfy‑based AI pipelines on GMI Cloud’s GPU infrastructure. It allows users to visually compose workflows using nodes and run multimodal inference directly in the browser.

​
1.2 Who Is This Platform For

GMI Studio is designed for:
  • AI creators and artists building image, video, LLM, and audio workflows
  • Engineers prototyping or deploying inference pipelines
  • Teams collaborating on reproducible AI workflows
Because all execution runs on GMI Cloud’s managed GPU backend, users do not need personal hardware GPUs or local GPU setup to build or run workflows.

​
1.3 Key Concepts

  • Workflows: Directed graphs defining how nodes connect and execute
  • Nodes: Individual functional units (e.g., upload, inference, save)
  • Sessions: A single execution run of a workflow
  • Execution Engine: GMI’s backend system that schedules and runs workflows on GPUs

​
1.4 What’s Included in This User Manual

This user manual includes the following sections:
  • Platform Overview: Explains core concepts and how GMI Studio fits into GMI Cloud.
  • Getting Started: How to sign in, access the console, and create your first workflow.
  • Workflow Building: Instructions on using the canvas, nodes, and editor tools to design workflows.
  • Saving & Running Workflows: Guidance on saving workflows, executing them, tracking progress, viewing prompt execution status, and previewing outputs.
  • Managing & Reusing Workflows: How to edit, duplicate, delete, and organize workflows.
  • Step-by-Step Tutorials: Guided examples for image, video, audio, and batch workflows.