Completing a Text-to-Image Workflow in ComfyUI

ComfyUI Try it →Watch full video →Fictitiousness · Nov 2025

Demo summary

The video shows the step-by-step connection of CLIP Text Encode nodes for prompts, Empty Latent Image for resolution, VAE Decode, and the Save Image node to complete a functional pipeline.

Step-by-step

Drag a connection link from the positive input of the K Sampler to a CLIP Text Encode node.
Copy and paste the CLIP Text Encode node and connect the duplicate to the negative input of the K Sampler.
Connect the CLIP output from the Load Checkpoint node to the CLIP input on both text encode nodes.
Drag out the Latent input from the K Sampler and select the Empty Latent Image node.
Set the image resolution in the Empty Latent Image node.
Drag a connection from the VAE output of the Load Checkpoint node and select the VAE Decode node.
Connect the Latent output of the K Sampler to the samples input of the VAE Decode node.
Drag a link from the VAE Decode image output and select the Save Image node.

Options

Experiment with different image sizes in the Empty Latent Image node
Set a custom file name and subfolder in the Save Image node

Watch out for

Images much larger than 1 megapixel (e.g., significantly over 1024x1024) will start to produce artifacts
Older Stable Diffusion models (pre-XL) may produce blurry details or artifacts if set higher than 512x512

Tips

Use 1024x1024 as the standard size for clean, detailed generations when using SDXL
Organize generations by using the subfolder setting in the Save Image node
Note that in SDXL, the VAE is baked into the model checkpoint, so you don't need a separate loader node

All demos from “ComfyUI for Beginners Pt. 1: Installation, Interface & Your First SDXL Workflow”

4:071:10Install ComfyUI and Manager with Stability MatrixThe video demonstrates how to use the Stability Matrix launcher to install ComfyUI in portable mode and add the ComfyUI Manager extension via the package menu.ComfyUI· AI Image Generator
6:504:15ComfyUI Interface and Sidebar NavigationA walkthrough of the ComfyUI interface, including the main menu, Q panel for tracking generations, model library, and the canvas tools for node navigation.ComfyUI· AI Image Generator
11:472:24Building a K Sampler and Checkpoint Node SetupThe creator demonstrates starting a blank workflow and connecting a K Sampler node to a Load Checkpoint node using the node-based drag-and-drop interface.ComfyUI· AI Image Generator
14:130:45Download SDXL Models via Stability Matrix BrowserThe demo shows how to use the built-in CivitAI integration in Stability Matrix to browse, filter for SDXL 1.0 checkpoints, and download them directly to the shared models folder.Stability AI· AI Image Generator
16:374:03Completing a Text-to-Image Workflow in ComfyUICurrentThe video shows the step-by-step connection of CLIP Text Encode nodes for prompts, Empty Latent Image for resolution, VAE Decode, and the Save Image node to complete a functional pipeline.ComfyUI· AI Image Generator
21:100:42Running an AI Image GenerationThe user enters a prompt and clicks 'Run', demonstrating how ComfyUI highlights active nodes with a green border as it processes the image through the pipeline.ComfyUI· AI Image Generator
21:523:43Adjusting K Sampler ParametersA walkthrough of the K Sampler settings including Seed, Steps, CFG scale, and Sampler/Scheduler selection to control the final image output.ComfyUI· AI Image Generator
Watch “ComfyUI for Beginners Pt. 1: Installation, Interface & Your First SDXL Workflow” →

AI Image Generator

8:418:40Building a ComfyUI workflow from scratchA step-by-step walkthrough of adding nodes (Checkpoint, CLIP Text Encode, KSampler, VAE Decode) and connecting them to build a custom image generation pipeline.AI Search
19:571:09Generating a medieval warrior with batch processingDemonstrates generating multiple images of a medieval warrior by increasing the batch size in the Empty Latent Image node.AI Search
25:330:32Importing workflows from image metadataShows how to drag an existing AI-generated image into the ComfyUI canvas to automatically reconstruct the entire node workflow used to create it.AI Search
58:094:05Controlling character poses with ControlNetDemonstrates using the OpenPose pre-processor and ControlNet Union model to force a generated princess character into a specific pose from a reference image.AI Search
1:360:57Install custom workflows and missing nodes in ComfyUIThe video demonstrates how to drag and drop a JSON workflow file into ComfyUI and use the Manager to identify and install missing custom nodes.Sebastian Kamph
3:020:20Search and install models via Model ManagerA walkthrough of using the ComfyUI Model Manager to search for specific AI models, such as ControlNet, and install them directly.Sebastian Kamph
3:281:10Running and managing image generation queuesDemonstration of starting a workflow using the 'Run' button, setting up 'Run Instant' for continuous generation, and using 'Run on Change' to trigger generation upon prompt edits.Sebastian Kamph
4:590:55Navigating the ComfyUI workspace and UI settingsShows how to use zoom, fit view, pan modes, and toggle link visibility or themes (light/dark mode) within the ComfyUI interface.Sebastian Kamph
11:311:49Adding and connecting nodes in ComfyUIThe video demonstrates adding a 'Load Image' node via the library or right-click menu and connecting it to other nodes like 'Save Image' using spaghetti links.Sebastian Kamph
19:431:34Converting widgets to inputs in ComfyUIShows how to convert a node's internal settings (like seed) into an external input pin and connect a 'Primitive' node to control it.Sebastian Kamph
25:032:06Managing seeds and randomizationShows the difference between 'Randomize' and 'Fixed' seed settings in the KSampler to either generate new variations or reproduce the same image.Sebastian Kamph
36:450:34Saving images to specific foldersShows how to use the 'Save Image' node and file path syntax to organize output images into custom subfolders.Sebastian Kamph