demobook

ComfyUI: Applying LoRA for Style Modification

ComfyUITry it →Watch full video →pixaroma ·

Demo summary

Demonstration of adding a LoRA loader to a workflow, using trigger words, and adjusting LoRA strength to change a robot into a 'cake style' robot.

Step-by-step

  1. Download the LoRA model file and place it in the 'models/loras' folder within your ComfyUI directory.
  2. Press the 'R' key in ComfyUI to refresh node definitions so the new model appears.
  3. Select the LoRA from the dropdown menu in the LoRA loader node.
  4. Add the specific trigger word for the LoRA to your positive prompt.
  5. Connect the 'Model' output from your checkpoint to the LoRA loader input.
  6. Connect the 'Model' output from the LoRA loader to the KSampler input.
  7. Set the seed to 'fixed' to ensure consistent results during testing.

Options

  • Bypass the LoRA node by right-clicking it and selecting 'Bypass' to see the image without the effect.
  • Organize LoRAs into subfolders named after their base models (e.g., SD15, SDXL).
  • Color-code nodes (e.g., blue) to make them easier to identify in large workflows.

Watch out for

  • LoRA models must be downloaded separately as they are not included in the workflow text file.
  • If ComfyUI was open when you added the model file, you must refresh the UI to see it.
  • Many LoRAs will have little or no effect if the specific trigger word is missing from the prompt.

Tips

  • Organize your LoRA folder by base model compatibility to avoid mixing incompatible files.
  • Place the trigger word at the beginning of the prompt to ensure you don't forget it.
  • Always read the LoRA description from the download source to find the required trigger words.
  • Add a 'Note' node near your LoRA loader to store trigger words for future reference.

Highlights

“It is easier to learn the basics first and then we can make things more complex as we move forward.”

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 ScratchA 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 ModificationCurrentDemonstration 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 Style Transfer

  1. 2:35:539:48Applying LoRA for Style ModificationCurrentDemonstration of adding a LoRA loader to a workflow, using trigger words, and adjusting LoRA strength to change a robot into a 'cake style' robot.pixaroma
  2. 12:481:45Style transformation and line art conversionThe creator demonstrates transforming a portrait into a watercolor painting and converting a 3D-style bunny into a line art illustration using specific style prompts.pixaroma
  3. 25:461:20Apply LoRA models to Flux KontextThe creator shows how to use the Power Lora Loader to apply a 'Glass Prism' LoRA to a product image to transform its visual style.pixaroma
  4. 4:090:55Anime style transfer and text renderingThe demonstration shows how to transform a real photo into an anime character eating in a restaurant while successfully rendering specific text in a chat bubble using the Flux Kontext model.Sebastian Kamph
  5. 12:371:20Create 3D text using ControlNet in the cloudA demonstration of using a ControlNet workflow on Running Hub to transform a simple black-and-white text image into a 3D rendered effect.pixaroma
  6. 8:540:42Style transfer to watercolor paintingThe video shows how to use a reference image to transform a realistic house photo into a watercolor painting style using Flux Kontext.Urban Decoders
  7. 11:001:54Applying LoRAs for line drawings and Lego stylesThe user demonstrates stacking LoRA models in ComfyUI to transform buildings into line drawings or Lego-style structures using Flux Kontext.Urban Decoders
demobook

Show, don’t tell.

Categories

Video & AnimationImage Generation & EditingSales TechEmail Marketing

About

SubmitAboutPrivacyTermsContact

© demobook.co