Skip to main content
Outpaints image based on prompt. This node expands an image by adding pixels to the top, bottom, left, and right sides while generating new content that matches the provided text description.

Inputs

ParameterDescriptionData TypeRequiredRange
imageThe input image to be expandedIMAGEYes-
promptPrompt for the image generation (default: "")STRINGNo-
prompt_upsamplingWhether to perform upsampling on the prompt. If active, automatically modifies the prompt for more creative generation, but results are nondeterministic (same seed will not produce exactly the same result). (default: False)BOOLEANNo-
topNumber of pixels to expand at the top of the image (default: 0)INTNo0-2048
bottomNumber of pixels to expand at the bottom of the image (default: 0)INTNo0-2048
leftNumber of pixels to expand at the left of the image (default: 0)INTNo0-2048
rightNumber of pixels to expand at the right of the image (default: 0)INTNo0-2048
guidanceGuidance strength for the image generation process (default: 60)FLOATNo1.5-100
stepsNumber of steps for the image generation process (default: 50)INTNo15-50
seedThe random seed used for creating the noise. (default: 0)INTNo0-18446744073709551615

Outputs

Output NameDescriptionData Type
imageThe expanded output imageIMAGE
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): d8ef7e28fecd0d08fa8f61c714ada054162668bb961008230bd4d342564af713