Skip to main content
This guide shows how to run the Luma Text to Image workflow in ComfyUI. For what the model is and what it does best, see the Luma Text to Image overview.
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.
Make sure your ComfyUI is updated.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 If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons:
  1. You are not using the latest ComfyUI version (Nightly version)
  2. Some nodes failed to import at startup

​
Luma Text to Image Partner Nodes Workflow

When the Luma Text to Image node is used without any image inputs, it functions as a text-to-image workflow. In this guide, we’ve created examples using style_image and image_luma_ref to showcase Luma AI’s excellent image processing capabilities.

​
1. Download Workflow Files

The workflow information is included in the metadata of the image below. Download and drag it into ComfyUI to load the workflow. Luma Text to Image Workflow Please download these images for input: Input Image - Reference Input Image - Style

​
2. Follow Steps to Run the Workflow

Luma Text to Image Workflow Steps Follow the numbered steps in the image to complete the basic workflow:
  1. Upload the reference image in the Load image node
  2. Upload the style reference image in the Load image (renamed to styleref) node
  3. (Optional) Modify the prompts in the Luma Text to Image node
  4. (Optional) Adjust the style_image_weight to control the style reference image’s influence
  5. Click the Run button or use the shortcut Ctrl(cmd) + Enter to generate the image
  6. After the API returns results, view the generated image in the Save Image node. Images are saved to the ComfyUI/output/ directory
Style Image Weight Comparison

​
3. Additional Notes

  • The node allows up to 4 reference images and character references simultaneously.
  • To enable multiple image inputs, right-click on the purple “Bypassed” nodes and set their mode to always