Introduction

Getting Started

By the end of this chapter, you'll have Sweet Tea Studio installed, connected to ComfyUI, and staring at your first AI-generated image. The whole process takes about 30 minutes on a typical machine.

Sweet Tea wraps the power of ComfyUI in a creative workspace that feels more like a design tool than a node editor. You select a Pipe (a workflow turned into a clean set of controls), type a prompt, and generate. The results land in your Gallery with every setting recorded so you can reproduce or riff on anything you make.

What You'll Need

Before you launch Sweet Tea for the first time, make sure you have:

• A supported machine — Windows 10+, macOS 12+, or a modern Linux distro (Ubuntu 22.04+, Fedora 38+, etc.)
• Disk space — At least 15 GB free for the app, a base model, and some outputs. Heavy model collections will need more.
• ComfyUI — Either an existing install or a willingness to let Sweet Tea set one up for you. If you don't have ComfyUI yet, don't worry — the managed setup path handles it.

Tip: You don't need a web account to generate images locally. Account linking is optional and can be done anytime later from Settings.

Download and Install

Grab the latest installer from /download and follow the steps for your platform:

Windows

1. Download the .exe installer.
2. Run it and follow the setup wizard.
3. Launch Sweet Tea Studio from your Start menu or desktop shortcut.

macOS

1. Download the .dmg file.
2. Open the disk image and drag Sweet Tea Studio into your Applications folder.
3. Launch from Applications. On first run, macOS may ask you to confirm you want to open an app from an identified developer — click Open.

Linux

1. Download the .AppImage or .deb package.
2. For AppImage, make it executable and run it:

chmod +x "Sweet Tea Studio-*.AppImage"
./"Sweet Tea Studio-*.AppImage"

For .deb, install with your package manager:

sudo dpkg -i sweet-tea-studio_*.deb

3. Launch Sweet Tea Studio from your application menu or terminal.

Note: The full installation chapter at Installation & Setup covers data paths, environment variables, and advanced configuration for each platform.

Connect to ComfyUI

When Studio opens, it needs to connect to a ComfyUI runtime — this is the Engine that actually executes your image generation workflows. You have two paths:

Path A: Let Studio manage ComfyUI (recommended for new users)

1. Open Settings from the sidebar.
2. Under the Engine section, choose Managed Runtime.
3. Point it to where ComfyUI is installed (or where you'd like it set up).
4. Studio will start ComfyUI for you and manage the connection automatically.

Path B: Connect to an existing ComfyUI instance

If you already run ComfyUI separately and want to keep that setup:

1. Open Settings from the sidebar.
2. Under Engine, enter your ComfyUI URL (default is http://127.0.0.1:8188).
3. Make sure your ComfyUI instance is running.

Either way, watch the status bar at the bottom of the window. When it shows a healthy connection, you're ready to generate.

Warning: If the status bar shows a connection error for more than a minute, don't skip ahead — head to ComfyUI Integration to diagnose the issue before importing workflows or changing other settings.

Generate Your First Image

With the engine connected, here's how to create your first image:

1. Click Prompt Studio in the sidebar — this is your main workspace.
2. Select a Pipe from the dropdown at the top. If you have a pipe loaded (either from the starter set or one you've imported), pick it.
3. In the prompt field, type something simple and descriptive:

a cozy cabin in autumn fog, warm light spilling from the windows, cinematic

4. Leave other settings at their defaults for now.
5. Click Generate (or press the generate shortcut).
6. Watch the progress in the generation feed on the right. Your image moves through Queued, Running, and then Completed.

That's it — your first image is done.

Find Your Result in Gallery

Once the generation completes:

1. Click the image in the generation feed to open it, or navigate to Gallery in the sidebar.
2. Your image appears with a full metadata panel: the exact prompt, model, sampler, steps, seed, and everything else that went into it.
3. Try clicking Re-run or copying the settings to Prompt Studio with a small tweak (bump the steps by 5, or change a word in the prompt) to see how controlled iteration works.

Tip: Every image in Sweet Tea records its full generation settings. If you ever make something great, you can always get back to exactly how you made it — or branch from it with a small change.

What to Explore Next

You've got the basics down. Here's where to go depending on what interests you:

• Understand the big picture — Core Concepts explains how Engines, Pipes, Projects, and the Gallery fit together.
• Lock down your setup — Installation & Setup covers data directories, environment variables, and platform-specific details you may want to configure now.
• Dive deeper into generation — Prompt Studio covers the full workspace, including batch generation, image inputs, the inpaint editor, and keyboard shortcuts.
• Import your own workflows — If you have existing ComfyUI workflows, Pipes & Workflows shows you how to bring them in.

Next: Core Concepts