ComfyUI > Nodes > ComfyUI > Grok Image

ComfyUI Node: Grok Image

Class Name

GrokImageNode

Category
api node/image/Grok
Author
ComfyAnonymous (Account age: 763days)
Extension
ComfyUI
Latest Updated
2026-05-13
Github Stars
112.77K

How to Install ComfyUI

Install this extension via the ComfyUI Manager by searching for ComfyUI
  • 1. Click the Manager button in the main menu
  • 2. Select Custom Nodes Manager button
  • 3. Enter ComfyUI in the search bar
After installation, click the Restart button to restart ComfyUI. Then, manually refresh your browser to clear the cache and access the updated list of nodes.

Visit ComfyUI Online for ready-to-use ComfyUI environment

  • Free trial available
  • 16GB VRAM to 80GB VRAM GPU machines
  • 400+ preloaded models/nodes
  • Freedom to upload custom models/nodes
  • 200+ ready-to-run workflows
  • 100% private workspace with up to 200GB storage
  • Dedicated Support

Run ComfyUI Online

Grok Image Description

Generate images from text prompts using Grok API for AI artists to create visual content seamlessly with advanced image generation models.

Grok Image:

The GrokImageNode is designed to generate images based on a text prompt using the Grok API. This node is particularly useful for AI artists who want to create visual content from textual descriptions, allowing for a seamless transition from concept to image. By leveraging advanced image generation models, GrokImageNode provides a powerful tool for producing high-quality images that align with the user's creative vision. Its primary function is to interpret the given text prompt and produce an image that reflects the described scene or object, making it an essential component for artists looking to explore AI-driven image creation.

Grok Image Input Parameters:

prompt

The prompt parameter is a text input that serves as the primary driver for image generation. It should contain a detailed description of the image you wish to create. The more specific and vivid the prompt, the better the resulting image will align with your expectations. This parameter must have a minimum length of 1 character, and it is crucial to ensure that the prompt is clear and descriptive to achieve the desired outcome.

model

The model parameter specifies the image generation model to be used. Different models may have varying capabilities and limitations, such as the number of images they can process simultaneously. For instance, the "grok-imagine-image-pro" model supports only one input image, while other models may support up to three. Selecting the appropriate model is essential for optimizing the image generation process and ensuring compatibility with your input requirements.

image

The image parameter allows you to input existing images that can be used as a reference or starting point for the generation process. Depending on the model, you can input one to three images. This parameter is optional, but when used, it can significantly influence the final output by providing additional context or style cues for the generated image.

resolution

The resolution parameter determines the size of the generated image. It is important to specify the desired resolution to ensure that the output meets your quality and detail expectations. The resolution should be specified in a format that the model can interpret, typically in terms of width and height.

number_of_images

The number_of_images parameter defines how many images you want to generate from a single prompt. This allows for the creation of multiple variations of the same concept, providing a range of options to choose from. The maximum number of images that can be generated is determined by the model's capabilities.

seed

The seed parameter is used to initialize the random number generator, which influences the variability and reproducibility of the generated images. By setting a specific seed value, you can ensure that the same prompt will consistently produce the same image, which is useful for iterative design processes or when you want to recreate a specific result.

aspect_ratio

The aspect_ratio parameter controls the proportions of the generated image. It can be set to "auto" to let the model decide the best aspect ratio based on the input images, or you can specify a custom ratio. However, custom aspect ratios are only allowed when multiple images are connected to the image input, providing flexibility in how the final image is composed.

Grok Image Output Parameters:

image

The image output parameter provides the generated image based on the input prompt and parameters. This output is the culmination of the node's processing and reflects the interpretation of the text prompt by the selected model. The generated image can be used for further editing, sharing, or as a final piece of artwork.

Grok Image Usage Tips:

  • Use detailed and specific prompts to achieve more accurate and visually appealing results.
  • Experiment with different models to find the one that best suits your creative needs and input constraints.
  • Utilize the seed parameter to reproduce specific images consistently, which is helpful for refining designs.

Grok Image Common Errors and Solutions:

"The pro model supports only 1 input image."

  • Explanation: This error occurs when more than one image is provided as input while using the "grok-imagine-image-pro" model, which only supports a single input image.
  • Solution: Ensure that only one image is connected to the input when using this model.

"A maximum of 3 input images is supported."

  • Explanation: This error indicates that more than three images have been provided as input, exceeding the model's capacity.
  • Solution: Reduce the number of input images to three or fewer.

"Custom aspect ratio is only allowed when multiple images are connected to the image input."

  • Explanation: This error arises when a custom aspect ratio is specified without providing multiple input images.
  • Solution: Either connect multiple images to the input or set the aspect ratio to "auto" if only one image is used.

Grok Image Related Nodes

Go back to the extension to check out more related nodes.
ComfyUI
RunComfy
Copyright 2025 RunComfy. All Rights Reserved.

RunComfy is the premier ComfyUI platform, offering ComfyUI online environment and services, along with ComfyUI workflows featuring stunning visuals. RunComfy also provides AI Models, enabling artists to harness the latest AI tools to create incredible art.

Grok Image