Luma Text to Image - ComfyUI Native Node Documentation
A node that converts text descriptions into high-quality images using Luma AI
The Luma Text to Image node allows you to create highly realistic and artistic images from text descriptions using Luma AI’s advanced image generation capabilities.
Node Function
This node connects to Luma AI’s text-to-image API, enabling users to generate images through detailed text prompts. Luma AI is known for its excellent realism and detail representation, particularly excelling at producing photorealistic content and artistic style images.
Parameters
Basic Parameters
Parameter | Type | Default | Description |
---|---|---|---|
prompt | String | "" | Text prompt describing the content to generate |
model | Select | - | Choose which generation model to use |
aspect_ratio | Select | 16:9 | Set the output image’s aspect ratio |
seed | Integer | 0 | Seed value to determine if the node should re-run, but actual results are independent of the seed |
style_image_weight | Float | 1.0 | Style image weight, range 0.0-1.0, only applies when style_image is provided, higher means stronger style reference |
Optional Parameters
Parameter | Type | Description |
---|---|---|
image_luma_ref | LUMA_REF | Luma reference node connection to influence generation with input images; up to 4 images |
style_image | Image | Style reference image; only 1 image will be used |
character_image | Image | Character reference images; can be a batch of multiple, up to 4 images |
Output
Output | Type | Description |
---|---|---|
IMAGE | Image | Generated image result |
Usage Example
Luma Text to Image Usage Example
Detailed guide for Luma Text to Image workflow
How It Works
The Luma Text to Image node analyzes the text prompt provided by the user and creates corresponding images through Luma AI’s generation models. This process uses deep learning technology to understand text descriptions and convert them into visual representations. Users can fine-tune the generation process by adjusting various parameters, including resolution, guidance scale, and negative prompts.
Additionally, the node supports using reference images and concept guidance to further influence the generation results, allowing creators to more precisely achieve their creative vision.
Source Code
[Node Source Code (Updated on 2025-05-03)]