Nodes Browser
ComfyDeploy: How ComfyUI-LumaAI-API works in ComfyUI?
What is ComfyUI-LumaAI-API?
Luma Dream Machine API official ComfyUI custom node.
How to install it in ComfyDeploy?
Head over to the machine page
- Click on the "Create a new machine" button
- Select the
Edit
build steps - Add a new step -> Custom Node
- Search for
ComfyUI-LumaAI-API
and select it - Close the build step dialig and then click on the "Save" button to rebuild the machine
ComfyUI-LumaAI-API
<p align="center"> <img src="./assets/luma_logo.png" alt="LumaAI Logo" width="200"> </p>This is a custom node for ComfyUI that allows you to use the Luma AI API directly in ComfyUI. Luma AI API is based on top of Dream Machine, which is a complete suite of models for image and video generation. For more information, see Luma AI API Documentation.
Requirements
Before using this node, you need to have an LumaAI API key. Get one here. If you want to use images as input, you will need to host them. As a suggestion, you can use ImgBB to host your images.
Installation
Installing manually
-
Navigate to the
ComfyUI/custom_nodes
directory. -
Clone this repository:
git clone https://github.com/lumalabs/ComfyUI-LumaAI-API.git
The path should be
ComfyUI/custom_nodes/ComfyUI-LumaAI-API/*
, where*
represents all the files in this repo. -
Install the dependencies:
- If you are using Windows (ComfyUI portable) run:
.\python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-LumaAI-API\requirements.txt
- If you are using Linux or MacOS, run:
cd ComfyUI-LumaAI-API && pip install -r requirements.txt
to install the dependencies.
-
If you don't want to expose your Luma API key, you can add it to the
config.ini
file and keep it empty in the node. -
Start ComfyUI and enjoy using the LumaAI API node!
Installing with ComfyUI-Manager
- Open ComfyUI-Manager and install the LumaAI API node (ComfyUI-LumaAI-API).
Installing with Comfy Registry
- Run
comfy node registry-install comfyui-lumaai-api
to install the node.
Nodes
Most of the nodes allow you to save locally the output video. If you keep the default filename
(empty string), the video will be saved in the outputs
folder using the generation_id
as the name.
For images, the node will always save the image locally, but you can set the filename
to save it with a custom name.
LumaAIClient
This node is used to create a LumaAI client.
LumaText2Video
This node is used to generate a video from a text prompt.
LumaImage2Video
This node is used to generate a video from an image. The image can be used as the first or last frame.
LumaInterpolateGenerations
This node is used to interpolate between two generations.
LumaExtendGeneration
This node is used to extend a generation. You can choose to extend before or after the generation.
LumaPreviewVideo
This node is used to preview a video. The video is resized to 768px to look better on ComfyUI.
ImgBBUpload
This node is used to upload an image to ImgBB and return the URL. We need this because Luma API currently only supports image urls as input. To use this node, you need to have an ImgBB API key. Create an account and get one here.
Reference
This node is used to create a reference from an image URL. It is used for style and image references.
ConcatReferences
This node is used to concatenate a list of references.
CharacterReference
This node is used to create a character reference from a list of image URLs.
ImageGeneration
This node is used to generate an image from a prompt.
ModifyImage
This node is used to modify an image.
Examples
For examples, see workflows folder. To use, just download the workflow json and import it into ComfyUI.
API Documentation
For more information about the Luma AI API, see Luma AI API Documentation.
Pricing
For pricing, see Luma AI Pricing.