GrokImageEditNodeV2 - ComfyUI Built-in Node Documentation

Modify one or more existing images based on a text prompt.

Modify one or more existing images based on a text prompt. The node sends the connected reference image(s) and the prompt to the Grok image editing API using the selected model, then returns the edited image(s).

Inputs

Common Inputs

Parameter	Description	Data Type	Required	Range
model	The Grok image model to use. The sub-parameters shown below change depending on the selected model.	DYNAMIC_COMBO	Yes	”grok-imagine-image-2.0" "grok-imagine-image-quality" "grok-imagine-image-pro" "grok-imagine-image”
prompt	The text prompt used to generate the image. (default: "")	STRING	Yes	N/A
seed	Seed to determine if node should re-run; actual results are nondeterministic regardless of seed. (default: 0)	INT	Yes	0 to 2147483647

grok-imagine-image-2.0 Inputs

Parameter	Description	Data Type	Required	Range
resolution	Output resolution of the edited images.	COMBO	Yes	”1K" "2K”
number_of_images	Number of edited images to generate. (default: 1)	INT	Yes	1 to 10
quality	Quality level of the generated images.	COMBO	Yes	”medium" "low”
aspect_ratio	Aspect ratio of the edited image. (default: “auto”)	COMBO	Yes	”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”

grok-imagine-image-quality and grok-imagine-image Inputs

Shared by grok-imagine-image-quality and grok-imagine-image.

Parameter	Description	Data Type	Required	Range
resolution	Output resolution of the edited images.	COMBO	Yes	”1K" "2K”
number_of_images	Number of edited images to generate. (default: 1)	INT	Yes	1 to 10
aspect_ratio	Only allowed when multiple images are connected. (default: “auto”)	COMBO	Yes	”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”

grok-imagine-image-pro Inputs

Parameter	Description	Data Type	Required	Range
resolution	Output resolution of the edited images.	COMBO	Yes	”1K" "2K”
number_of_images	Number of edited images to generate. (default: 1)	INT	Yes	1 to 10

Reference Inputs

Parameter	Description	Data Type	Required	Range
images	Growable slot: connect 1 or more reference images to edit. The first slot is image, additional slots are image_1, image_2, etc. The maximum number of images depends on the selected model.	IMAGE	Yes	1 image for grok-imagine-image-pro 1 to 3 images for grok-imagine-image-2.0, grok-imagine-image-quality, and grok-imagine-image

Note on constraints:

• prompt must contain at least 1 non-whitespace character.
• At least one reference image is required for editing; the node raises an error if no image is connected.
• The maximum number of input images is 1 for grok-imagine-image-pro and 3 for grok-imagine-image-2.0, grok-imagine-image-quality, and grok-imagine-image. Connecting more images than the model supports raises an error.
• For grok-imagine-image-quality and grok-imagine-image, a custom aspect_ratio (anything other than “auto”) is only allowed when multiple images are connected. With a single image, aspect_ratio must be “auto”.
• For grok-imagine-image-2.0, aspect_ratio can be set freely even with a single image.
• The quality sub-parameter is only available with grok-imagine-image-2.0.

Outputs

Output Name	Description	Data Type
IMAGE	The edited image(s) returned by the Grok API. If a single image is generated, it is returned directly. If multiple images are generated, they are concatenated into a single batch tensor.	IMAGE

This documentation was AI-generated. If you find any errors or have suggestions for improvement, please feel free to contribute! Edit on GitHub

---

Source fingerprint (SHA-256): 7d75b1cb8405c5024567b1119bcbd5e4b318152605f74b62bdd5173dda75949f