demobook

Image-to-Image Workflow in ComfyUI

ComfyUITry it →Watch full video →Joey /// VP Land ·

Demo summary

The demo shows an image-to-image setup using a 'Load Image' node and a VAE Encode node to use an existing image as a structural guide for the K Sampler.

Step-by-step

  1. Add a Load Image node to the workflow
  2. Upload or select the image you want to use as a structural guide
  3. Connect the Load Image node to a VAE Encode node
  4. Connect the VAE Encode node output to the Latent input of the K Sampler
  5. Adjust the Denoise setting in the K Sampler to a value below 1.0
  6. Select the DPM++ 2M sampler

Options

  • Use a sketch as the input image
  • Use a blocked-out render from Unreal Engine as the input image

Watch out for

  • The Denoise setting must be lower than 1.0 to retain the structure of the original image

Tips

  • Use image-to-image when text-to-image fails to provide the specific framing or blocking you need
  • If you load a default ComfyUI workflow, leave the sampler settings as they are initially as they are often optimized for that specific setup
  • Set Denoise to around 0.87 to significantly modify the image while keeping the basic composition

Highlights

“our workflow is pretty much the same except we have this blue box... which is to load our image”

All demos from “ComfyUI Explained: How AI Image Generation Actually Works (Step-by-Step)”

  1. 9:522:41Basic Text-to-Image Workflow in ComfyUIThe host walks through a standard text-to-image template in ComfyUI, explaining the 'Load Checkpoint' node for selecting models like Stable Diffusion XL and the difference between safe tensor and diffuser files.ComfyUIAI Image Generator
  2. 12:331:24CLIP Text Encoding in ComfyUIThe demo shows how to use CLIP Text Encode nodes for positive and negative prompting to translate text into latent vectors that the model can understand.ComfyUIAI Image Generator
  3. 13:575:43Configuring the K Sampler in ComfyUIA walkthrough of the K Sampler node settings, including seed generation, step count, CFG (classifier free guidance), and sampler algorithms like Euler.ComfyUIAI Image Generator
  4. 19:430:44VAE Decoding and Image Saving in ComfyUIThe host demonstrates the VAE Decode node to convert latent space data back into pixel space (JPEG/PNG) and the Save Image node for local file output.ComfyUIAI Image Generator
  5. 24:012:38Using LoRAs in ComfyUI WorkflowsThe video demonstrates how to insert a 'Load LoRA' node into a workflow to influence a base model's style or character consistency.ComfyUIAI Image Generator
  6. 27:340:56Managing Models and Missing Nodes in ComfyUIThe host shows the built-in model manager to download CLIP models and the 'Install Missing Nodes' feature to automatically fix broken workflows.ComfyUIAI Image Generator
  7. 28:561:50Image-to-Image Workflow in ComfyUICurrentThe demo shows an image-to-image setup using a 'Load Image' node and a VAE Encode node to use an existing image as a structural guide for the K Sampler.ComfyUIImage to Image
  8. Watch “ComfyUI Explained: How AI Image Generation Actually Works (Step-by-Step)” →

Image to Image

  1. 41:391:29Image-to-image generation with denoisingDemonstrates the image-to-image process by loading an existing photo and adjusting the denoising strength to create variations.AI Search
  2. 32:382:30Image-to-Image generation using DenoiseDemonstrates how the Denoise slider in the KSampler affects the transformation of a source image (cat) into a new subject (dog) based on a prompt.Sebastian Kamph
  3. 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.pixaroma
  4. 33:282:46Image-to-image transformation with Z-ImageThe user demonstrates how to modify a ComfyUI workflow to perform image-to-image tasks, converting a 3D animation into a realistic photo using Z-Image Turbo.AI Search
  5. 4:040:41Upload character reference imageThe user shows how to upload a reference image for character replacement or stylization within the ComfyUI workflow.MDMZ
  6. 28:561:50Image-to-Image Workflow in ComfyUICurrentThe demo shows an image-to-image setup using a 'Load Image' node and a VAE Encode node to use an existing image as a structural guide for the K Sampler.Joey /// VP Land
  7. 3:041:18Enhance 3D clay models with Flux and ControlNetThe creator demonstrates using the Flux model in ComfyUI with a Depth ControlNet to transform a gray 3D massing model into a detailed streetcar scene while maintaining structural integrity.Matt Hallett Visual
  8. 8:512:02Image-to-image enhancement with denoisingThe video shows how to use the 'denoising' strength in ComfyUI to blend a base 3D rendering with AI-generated details like autumn trees and realistic people.Matt Hallett Visual
  9. 9:050:49Image-to-image generation with FLUX.1 KontextDemonstration of uploading an image and using a natural language prompt to transform a character's appearance while maintaining consistency using FLUX.1 Kontext.AI様の下僕
  10. 9:314:03Image-to-image denoising with FluxThe user demonstrates how Flux handles image-to-image tasks by adjusting the denoise strength from 0.4 to 1.0 to show how it differs from Stable Diffusion.Artificial Images
  11. 2:450:14Analyzing reference images for Ghost Mask modeThe video shows the process of using the 'Analyze' button to generate a short description of a subject for the Ghost Mask reference mode.RedShade
demobook

Show, don’t tell.

Categories

Video & AnimationImage Generation & EditingSales TechEmail Marketing

About

SubmitAboutPrivacyTermsContact

© demobook.co