Image-to-Image Workflow in ComfyUI
ComfyUI
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
- Add a Load Image node to the workflow
- Upload or select the image you want to use as a structural guide
- Connect the Load Image node to a VAE Encode node
- Connect the VAE Encode node output to the Latent input of the K Sampler
- Adjust the Denoise setting in the K Sampler to a value below 1.0
- 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)”
- 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.ComfyUI· AI Image Generator
- 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.ComfyUI· AI Image Generator
- 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.ComfyUI· Image to Image
- Watch “ComfyUI Explained: How AI Image Generation Actually Works (Step-by-Step)” →
Image to Image
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
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
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- 8:512:02Image-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
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
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- 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
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
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
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
4:040:41Upload character reference imageThe user shows how to upload a reference image for character replacement or stylization within the ComfyUI workflow.MDMZ