Luma Image to Image in ComfyUI: Prompt-Driven Image Editing
Edit existing images with the Luma Image to Image node in ComfyUI: prompt-driven changes to objects and shapes, with image weight control over the input.
The Luma Image to Image node allows you to modify existing images based on text prompts using Luma AI technology, while preserving certain features and structures from the original image.
What Luma Image to Image is good at
Prompt-driven image editing: Modifies existing images based on text prompts while preserving certain features and structures from the original
Changing objects and shapes: The node works well for changing objects and shapes, though it may not be ideal for color changes
Adjustable input influence: The image_weight parameter controls how strongly the input image shapes the result, with lower values staying closer to the original
Example outputs
Results at different image_weight values, showing how strongly the input image influences the generated output:
To use the Partner Nodes, you need to ensure that you are logged in properly and using a permitted network environment. Please refer to the Partner Nodes Overview section of the documentation to understand the specific requirements for using the Partner Nodes.
Workflows in this guide can be found in the Workflow Templates.
If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
You are not using the latest ComfyUI version (Nightly version)
So, if you find any core node missing in this document, it might be because the new core nodes have not yet been released in the latest stable version. Please wait for the next stable release.
Luma Image to Image Partner Nodes Workflow
This feature works well for changing objects and shapes. However, it may not be ideal for color changes. We recommend using lower weight values, around 0.0 to 0.1.
1. Download Workflow File
Download and drag the following image into ComfyUI to load the workflow (workflow information is included in the image metadata):Download this image to use as input:
2. Complete the Workflow Steps
Follow these numbered steps:
Click Upload on the Load Image node to upload your input image
(Optional) Modify the workflow prompts
(Optional) Adjust image_weight to change input image influence (lower values stay closer to original)
Click Run or use shortcut Ctrl(cmd) + Enter to generate the image
After API returns results, view the generated image in the Save Image node. Images are saved to the ComfyUI/output/ directory