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

ParameterData TypeRequiredRangeDescription
imageIMAGEYes-The input image to be expanded
promptSTRINGNo-Prompt for the image generation (default: "")
prompt_upsamplingBOOLEANNo-Whether 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)
topINTNo0-2048Number of pixels to expand at the top of the image (default: 0)
bottomINTNo0-2048Number of pixels to expand at the bottom of the image (default: 0)
leftINTNo0-2048Number of pixels to expand at the left of the image (default: 0)
rightINTNo0-2048Number of pixels to expand at the right of the image (default: 0)
guidanceFLOATNo1.5-100Guidance strength for the image generation process (default: 60)
stepsINTNo15-50Number of steps for the image generation process (default: 50)
seedINTNo0-18446744073709551615The random seed used for creating the noise. (default: 0)

Outputs

Output NameData TypeDescription
imageIMAGEThe expanded output image