Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.comfy.org/llms.txt

Use this file to discover all available pages before exploring further.

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub
The Grok Image Edit node modifies an existing image based on a text prompt. It uses the Grok API to generate one or more new images that are variations of the input, guided by your description.

Inputs

ParameterData TypeRequiredRangeDescription
modelCOMBOYes"grok-imagine-image-quality"
"grok-imagine-image-pro"
"grok-imagine-image"
"grok-imagine-image-beta"
The specific AI model to use for image editing.
imageIMAGEYesThe input image(s) to be edited. Supports up to 3 input images, except for the “pro” model which supports only 1.
promptSTRINGYesThe text prompt used to generate the edited image. Must be at least 1 character after stripping whitespace.
resolutionCOMBOYes"1K"
"2K"
The resolution for the output image.
number_of_imagesINTNo1 to 10Number of edited images to generate (default: 1).
seedINTNo0 to 2147483647Seed to determine if node should re-run; actual results are nondeterministic regardless of seed (default: 0).
aspect_ratioCOMBONo"auto"
"1:1"
"2:3"
"3:2"
"3:4"
"4:3"
"9:16"
"16:9"
"9:19.5"
"19.5:9"
"9:20"
"20:9"
"1:2"
"2:1"
The aspect ratio for the output image. Only allowed when multiple images are connected to the image input. If set to “auto”, the aspect ratio is determined automatically (default: “auto”).
Important constraints:
  • The image input supports up to 3 images, except when using the grok-imagine-image-pro model, which supports only 1 input image.
  • The aspect_ratio parameter can only be set to a custom value (not “auto”) when multiple images are connected to the image input. Setting a custom aspect ratio with a single input image will cause an error.

Outputs

Output NameData TypeDescription
outputIMAGEThe edited image(s) generated by the node. If number_of_images is greater than 1, the outputs are concatenated into a batch.

Source fingerprint (SHA-256): 31cfe7ad382033f69330ed4de1ec831ccc25156498563e1541368e2662ed3ddb