🖼️ Images

Official Documentation

⋙ Create Image

Creates an image given a prompt.

prompt string: A text description of the desired image(s).
model string: The model to use for image generation. Supported model ids include gpt-image-2, gpt-image-2-2026-04-21, gpt-image-1.5, chatgpt-image-latest, gpt-image-1, gpt-image-1-mini, dall-e-2, and dall-e-3.
n integer: The number of images to generate.
quality string: The quality of the image that will be generated.
response_format string: For dall-e-2 and dall-e-3, the format in which generated images are returned. Must be one of url or b64_json.
output_format string: For GPT image models, the output format. Must be one of png, jpeg, or webp.
background string: For GPT image models, the requested background. Must be one of transparent, opaque, or auto. gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds; for those models use opaque or auto. Transparent backgrounds require output_format set to png or webp.
size string: The size of the generated images. For gpt-image-2 and gpt-image-2-2026-04-21, arbitrary WIDTHxHEIGHT strings are supported, for example 1536x864. Width and height must both be divisible by 16, and the requested aspect ratio must be between 1:3 and 3:1. Standard GPT image sizes include 1024x1024, 1536x1024, and 1024x1536; auto is supported where the model allows it. dall-e-2 keeps the fixed 256x256, 512x512, and 1024x1024 sizes. dall-e-3 keeps 1024x1024, 1792x1024, and 1024x1792.
style string: The style of the generated images. Must be one of vivid or natural.
stream boolean: If true, the node emits image stream events as they arrive instead of returning a final response.data array in one message.
partial_images integer: When streaming GPT image responses, request between 0 and 3 partial images before the completed image event.
user string: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

⋙ Create Image Edit

Creates an edited or extended image given an original image and a prompt.

image string | string[]: The image to edit. Provide one local file path, or an array of local file paths for GPT image edit requests. GPT image models can accept up to 16 images; dall-e-2 still expects a single image.
prompt string: A text description of the desired image(s).
mask string: An additional image whose fully transparent areas (e.g. where alpha is zero) indicate where image should be edited. If you send multiple input images, the mask applies to the first image.
model string: The model to use for image generation. Use dall-e-2 or a GPT image model such as gpt-image-2, gpt-image-2-2026-04-21, gpt-image-1.5, or chatgpt-image-latest.
n integer: The number of images to generate. Must be between 1 and 10.
size string: The size of the generated images. gpt-image-2 and gpt-image-2-2026-04-21 support arbitrary WIDTHxHEIGHT strings such as 1536x864 when width and height are divisible by 16 and the aspect ratio stays between 1:3 and 3:1.
response_format string: For dall-e-2, the format in which the generated images are returned. Must be one of url or b64_json.
output_format string: For GPT image models, the output format. Must be one of png, jpeg, or webp.
background string: For GPT image models, the requested background. Must be one of transparent, opaque, or auto. gpt-image-2 and gpt-image-2-2026-04-21 do not support transparent backgrounds.
stream boolean: If true, the node emits image edit stream events as they arrive instead of returning a final response.data array.
partial_images integer: When streaming GPT image edits, request between 0 and 3 partial images before the completed image event.
user string: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

⋙ Create Image Variation

Creates a variation of a given image.

image string: The image to use as the basis for the variation(s).
model: The model to use for image generation.
n integer: The number of images to generate.
response_format string: The format in which the generated images are returned.
size string: The size of the generated images.
user string: A unique identifier representing your end-user, which can help OpenAI to monitor and detect abuse.

⋙ Create Image

msg.payload Properties

⋙ Create Image Edit

msg.payload Properties

⋙ Create Image Variation

msg.payload Properties