demobook

ComfyUI: Building a Text-to-Image Workflow from Scratch

ComfyUITry it →Watch full video →pixaroma ·

Demo summary

A step-by-step build of a standard diffusion pipeline using Load Checkpoint, CLIP Text Encode, Empty Latent Image, KSampler, and VAE Decode.

Step-by-step

  1. Open the 'getting started' folder and select 'workflow number one'
  2. Add a 'Load Checkpoint' node to select and load your AI model
  3. Add two 'CLIP Text Encode' nodes to serve as your positive and negative prompts
  4. Add an 'Empty Latent Image' node to define the width and height of the generation
  5. Connect the nodes to a 'KSampler' node to execute the image generation process
  6. Connect the KSampler output to a 'VAE Decode' node to convert the latent data into a viewable image

Options

  • Color-code CLIP Text Encode nodes (e.g., green for positive, red for negative) for easier recognition
  • Use a 'Note' node to add descriptive labels next to each functional node

Watch out for

  • Larger and more advanced models require more VRAM and a stronger graphics card to run properly
  • The KSampler produces a 'latent' format that is not visible until it passes through a VAE Decode node

Tips

  • Think of the Model/Checkpoint as the 'photographer' you are hiring for the task
  • Use the CLIP Text Encode node as a 'translator' between human language and AI instructions
  • Treat the Empty Latent Image node as choosing your 'photo paper' size before the shoot
  • View the KSampler as the 'photo shoot' itself where the actual creation happens
  • Think of VAE Decode as the 'dark room' where the hidden latent image is developed into a visible photo

All demos from “ComfyUI Course - Learn ComfyUI From Scratch | Full 5 Hour Course (Ep01)”

  1. 9:173:04Install ComfyUI using Easy InstallThe instructor demonstrates how to download the ComfyUI Easy Install zip from GitHub, extract it, and run the BAT file to set up a portable local installation.ComfyUIAI Image Generator
  2. 13:355:23ComfyUI Interface OverviewA walkthrough of the ComfyUI UI, demonstrating the canvas, node search, top bar controls, view settings, and how to properly close the application.ComfyUIAI Image Generator
  3. 18:588:14Running a Ready-Made WorkflowThe video shows how to load a .json workflow, download the required Juggernaut Reborn model, refresh the node list, and generate an image of a cat.ComfyUIAI Image Generator
  4. 27:266:13Building a Basic Image Processing WorkflowDemonstration of adding nodes (Load Image, Image Crop, Save Image) and connecting them via color-coded links to perform non-AI image tasks.ComfyUIAI Crop Image
  5. 44:186:05Using Math and Grouping NodesThe instructor shows how to use Math Int and Preview as Text nodes for automation and how to organize nodes into Groups for better workflow management.ComfyUIAI Image Generator
  6. 1:12:0414:42Building a Text-to-Image Workflow from ScratchCurrentA step-by-step build of a standard diffusion pipeline using Load Checkpoint, CLIP Text Encode, Empty Latent Image, KSampler, and VAE Decode.ComfyUIAI Image Generator
  7. 1:27:395:06Image-to-Image Workflow with Denoise ControlDemonstration of converting a text-to-image workflow into an image-to-image setup using VAE Encode and adjusting the denoise parameter to control variation.ComfyUIImage to Image
  8. 1:48:162:58Managing Custom Nodes with ComfyUI ManagerThe video walks through searching for, installing, and uninstalling custom nodes (specifically the 'Align' node) using the built-in Manager.ComfyUIAI Image Generator
  9. 2:35:539:48Applying LoRA for Style ModificationDemonstration of adding a LoRA loader to a workflow, using trigger words, and adjusting LoRA strength to change a robot into a 'cake style' robot.ComfyUIAI Style Transfer
  10. 2:47:359:01Guiding Structure with ControlNetThe video shows how to use Canny and Depth ControlNet models with pre-processors to guide image generation based on an input sketch or 3D text.ComfyUIAI Image Generator
  11. 3:11:488:27Generating Images with Z-Image TurboA demonstration of setting up the modern Z-Image Turbo model, including the specific Model Sampling AuraFlow node and high-quality prompt generation.ComfyUIAI Image Generator
  12. 4:13:595:52Integrating ChatGPT API for Prompt GenerationThe instructor demonstrates signing into the ComfyUI API and using a ChatGPT node to automatically generate detailed image prompts for local models.ComfyUIAI Image Generator
  13. Watch “ComfyUI Course - Learn ComfyUI From Scratch | Full 5 Hour Course (Ep01)” →

AI Image Generator

  1. 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
  2. 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
  3. 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
  4. 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
  5. 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
  6. 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
  7. 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
  8. 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
  9. 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
  10. 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
  11. 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
  12. 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
demobook

Show, don’t tell.

Categories

Video & AnimationImage Generation & EditingSales TechEmail Marketing

About

SubmitAboutPrivacyTermsContact

© demobook.co