Skip to main content
Grok Image is xAI’s image generation model, available in ComfyUI through the Grok partner nodes. It generates images from text prompts and edits uploaded images with natural-language instructions, supporting 13 aspect ratios and 1K or 2K 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.
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 If you can’t find them in the template, your ComfyUI may be outdated.If nodes are missing when loading a workflow, possible reasons: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

​
Grok: Text to Image

Generate images from a text prompt with the standard grok-imagine-image model. This workflow is the fastest way to create single images in ComfyUI with Grok, supporting 13 aspect ratios and 1K or 2K output. Grok text-to-image workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Grok Imagine” in Template Library
Grok text-to-image output

​
Workflow overview

This workflow uses two nodes:
  • GrokImageNode: the core node, configured with the grok-imagine-image model
  • SaveImage: saves the generated image

​
Steps to run

  1. Enter your prompt: describe the scene and style in the GrokImageNode
  2. Choose aspect ratio: pick from ratios such as 1:1, 16:9, 9:16, and more
  3. Set resolution: 1K or 2K
  4. Click Queue: press Ctrl+Enter to generate

​
Grok: Image Edit

Edit an uploaded image with natural-language instructions. This workflow keeps the original composition and changes the scene, lighting, or style based on your prompt. Grok image edit workflow preview

Run on Comfy Cloud

Open in Comfy Cloud

Download Workflow

Download JSON or search “Grok Imagine” in Template Library
Grok image edit output

​
Workflow overview

This workflow uses three nodes:
  • LoadImage: provides the source image to edit
  • GrokImageEditNode: the core node, configured with the grok-imagine-image model
  • SaveImage: saves the edited image

​
Steps to run

  1. Load an image: connect your image to the LoadImage node
  2. Describe the edit: tell the model what to change in the GrokImageEditNode prompt
  3. Click Queue: press Ctrl+Enter to generate