Save 4 hours! We auto-setup your workflow! Free!

Drop your workflow.json — we handle every dependency, custom node, and model. Just open the link and run.

Auto-Setup Workflow Json (Free) Now!
ComfyUI > Nodes > comfyui-flux2-photomatch

ComfyUI Extension: comfyui-flux2-photomatch

Repo Name

comfyui-flux2-photomatch

Author
frkanozsoy (Account age: 0 days)
Nodes
View all nodes(1)
Latest Updated
2026-11-03
Github Stars
0.0K

How to Install comfyui-flux2-photomatch

Install this extension via the ComfyUI Manager by searching for comfyui-flux2-photomatch
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter comfyui-flux2-photomatch in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

comfyui-flux2-photomatch Description

comfyui-flux2-photomatch adds FLUX.2 Klein nodes for guiding image generation and a masked photo-matching node that adjusts color, brightness, and grain to blend edits with reference photos.

comfyui-flux2-photomatch Introduction

comfyui-flux2-photomatch brings two sets of ComfyUI tools together in one custom-node pack:

  • FLUX.2 Klein Enhancer provides helpers for guiding color, detail, text conditioning, identity, and reference images in workflows using the FLUX.2 Klein family.
  • Photo Color + Grain Match helps a generated or edited image sit more naturally beside a reference photograph by adjusting color and adding matching-looking luminance grain.

For example, if you have placed a generated subject into a photograph, the subject’s skin tones, contrast, or grain may look different from the rest of the scene. PhotoColorGrainMatch can use a reference image and masks to bring those qualities closer together. The Klein nodes address an earlier part of the creative process: guiding how an image is generated or refined.

The photo-matching node runs on the CPU using OpenCV and NumPy. It does not need a separate model, GPU memory, or network access, and its result is reproducible when you use the same inputs and seed. The pack does not include a new image-generation model; its Klein nodes are tools for workflows built around the FLUX.2 Klein family.

How comfyui-flux2-photomatch Works

Think of the pack as offering two kinds of help: direction while making an image and finishing work after an image exists.

The Klein helpers give a workflow ways to organize or influence generation. Their names describe the areas they address, such as color anchoring, detail control, identity guidance, feature transfer, and the use of multiple references. Exactly how they fit together depends on the ComfyUI workflow you build.

PhotoColorGrainMatch works with an existing source image, a reference image, and masks. It compares the colors in the relevant regions in Lab color space, a way of describing brightness separately from color. It then shifts the source toward the reference’s typical values and makes a limited adjustment to the spread of its brightness and colors. Finally, it adds luminance grain based on the reference. In everyday terms, it tries to make the selected part of one image feel more like it was photographed under the same visual conditions as the other.

Masks determine where the match is applied. A mask covering the whole source can create a consistent, whole-image grade. A small mask limits the adjustment to a particular area, but its edge needs enough softness to avoid looking like a pasted-on patch.

comfyui-flux2-photomatch Features

Photo Color + Grain Match

The PhotoColorGrainMatch node adjusts the selected image area toward a reference’s typical brightness and color, then adds matched luminance grain.

  • Region control: Use masks to choose the areas involved. An all-ones mask with a whole-frame reference is useful when you want a uniform grade across the image.
  • Brightness and color strength: luminance_strength and color_strength let you reduce the corresponding parts of the adjustment. If skin looks waxy or highlights become cream-colored, try lowering color_strength.
  • Edge softness: feather_px softens the transition around a masked area. A tight mask with too little feathering can leave a visible boundary. Feathering is capped at 64 pixels.
  • Repeatable results: Given the same inputs and seed, the node produces the same output. This makes it easier to compare deliberate changes to your workflow.

The node limits how strongly it rescales contrast and color. This helps contain extreme adjustments, but a reference that differs greatly from the source can still give an unnatural result. Choosing a closer reference and reducing color strength are practical ways to refine the match.

FLUX.2 Klein Workflow Helpers

The pack also provides these nodes for FLUX.2 Klein workflows:

NodeIntended area
Flux2KleinColorAnchorColor anchoring
Flux2KleinEnhancerConditioning and enhancement
Flux2KleinDetailControllerDetail control
Flux2KleinSectionedEncoderSectioned encoding
Flux2KleinMaskRefControllerMask and reference control
Flux2KleinTextEnhancerText-conditioning assistance
IdentityGuidanceIdentity guidance
IdentityFeatureTransferIdentity feature transfer
IdentityFeatureTransferAdvancedIdentity feature transfer
IdentityFeatureTransferV3Identity feature transfer
IdentityFeatureTransferFinalIdentity feature transfer
Flux2KleinKSamplerExperimentalExperimental sampling

These are nodes, not separate models. The provided documentation does not specify their individual controls or recommend settings for each identity-transfer variant, so treat their names as a guide to their purpose rather than as a promise that the variants are interchangeable. The KSampler is explicitly marked experimental.

Troubleshooting comfyui-flux2-photomatch

The matched area has a visible edge

  1. Check that the mask covers the area you intended to change.
  2. Increase feather_px to soften the transition. Remember that feathering is capped at 64 pixels.
  3. If the entire image should receive the same grade, use an all-ones mask and a whole-frame reference instead of a tight local mask.

Skin looks waxy or highlights look cream-colored

  1. Lower color_strength.
  2. Compare the source and reference. A strong difference between them may be pushing the color adjustment to its limit.
  3. Try a reference whose lighting and colors are closer to the result you want.

The adjustment appears in the wrong place

  1. Inspect both masks and confirm that they represent the intended regions.
  2. If you resized an image and its mask, make sure they underwent the same scaling transform and method so they remain aligned.
  3. When supplying an image through an API, check its PNG alpha channel. The browser’s mask painter does not run as part of an API request.

Frequently Asked Questions

Does Photo Color + Grain Match require a separate model or GPU memory?
No. PhotoColorGrainMatch runs on the CPU and does not use a model or VRAM.

Why does a mask from LoadImage behave differently than I expected?
For this workflow, a mask loaded from an image is derived from its alpha channel: transparent areas are masked. Inspect the image’s transparency if the selected region seems reversed or misplaced.

Can I use a mask painted in ComfyUI when calling the workflow through an API?
Do not rely on the browser-side mask painter for an API call. Supply a PNG whose alpha channel already contains the intended mask.

Will identical settings produce identical photo-matching results?
Yes, when the inputs and seed are the same, PhotoColorGrainMatch is reproducible.

Learn More about comfyui-flux2-photomatch

  • Explore the nodes in ComfyUI: Add the nodes by their display names, such as Photo Color + Grain Match or FLUX.2 Klein Color Anchor, and inspect their available inputs in your workflow.
  • Review the pack’s terms: See the repository’s MIT license.
  • Check the repository documentation for workflow-specific guidance: The supplied material does not include a tutorial, example workflow, screenshots, or a support forum, so no particular external resource can be recommended here.

comfyui-flux2-photomatch Related Nodes

RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

comfyui-flux2-photomatch detailed guide | ComfyUI