Skip to main content

GPT Image

Generate or Edit an image using GPT Image

The GPT Image node is designed to interact with the GPT Image API, enabling you to generate and edit images based on a prompt and reference images.

GPT ImageGenerate Image
Prompt*Text (multiline)
ModelSelect
SizeSelect
SizeSelect
QualitySelect
BackgroundSelect
ModerationSelect
Node as configured in “Generate Image” mode. Fields marked * are required. Dots are connection handles.

Modes

This node reconfigures itself depending on the selected mode — each mode has its own fields.

ModeWhat it doesOutput
Generate ImageCreate a brand-new image from promptImage
Edit ImageModify an existing image by prompt, or use images to generate a new oneImage

Generate Image

Create a brand-new image from prompt

GPT ImageGenerate Image
Prompt*Text (multiline)
ModelSelect
SizeSelect
SizeSelect
QualitySelect
BackgroundSelect
ModerationSelect

Inputs

Each input can be typed in directly or connected to another node's output.

InputTypeRequiredDescription
PromptText (multiline)RequiredEnter your text here

Settings

SettingTypeDefaultDescriptionAvailable when
ModelSelectgpt-image-2
SizeSelectautoModel is “gpt-image-2”
SizeSelectautoModel is not “gpt-image-2”
QualitySelectauto
BackgroundSelectauto
ModerationSelectlowOptions: auto · low (default).
Model options
OptionDefault
gpt-image-2
gpt-image-1.5
gpt-image-1
Size options
OptionDefault
auto
1024x1024 (square)
1536x1024 (landscape)
1024x1536 (portrait)
2048x2048 (2K square)
2048x1152 (2K landscape)
3840x2160 (4K landscape)
2160x3840 (4K portrait)
Size options
OptionDefault
auto
1024x1024 (square)
1536x1024 (landscape)
1024x1536 (portrait)
Quality options
OptionDefault
auto
low
medium
high
Background options
OptionDefault
auto
opaque
transparent

Output: Image

Edit Image

Modify an existing image by prompt, or use images to generate a new one

GPT ImageEdit Image
Prompt*Text (multiline)
MaskFile upload
ImageFile upload
ModelSelect
SizeSelect
SizeSelect
QualitySelect

Inputs

Each input can be typed in directly or connected to another node's output.

InputTypeRequiredDescription
PromptText (multiline)RequiredEnter your text here
MaskFile uploadOptionalYou can provide a mask to indicate where the image should be edited. You can use the prompt to describe the full new image, not just the erased area. If you provide multiple input images, the mask will be applied to the first image.
ImageFile uploadOptional

Settings

SettingTypeDefaultDescriptionAvailable when
ModelSelectgpt-image-2
SizeSelectautoModel is “gpt-image-2”
SizeSelectautoModel is not “gpt-image-2”
QualitySelectauto
Model options
OptionDefault
gpt-image-2
gpt-image-1.5
gpt-image-1
Size options
OptionDefault
auto
1024x1024 (square)
1536x1024 (landscape)
1024x1536 (portrait)
2048x2048 (2K square)
2048x1152 (2K landscape)
3840x2160 (4K landscape)
2160x3840 (4K portrait)
Size options
OptionDefault
auto
1024x1024 (square)
1536x1024 (landscape)
1024x1536 (portrait)
Quality options
OptionDefault
auto
low
medium
high

Output: Image

Output