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
Inpaints image based on mask and prompt. This node uses the Flux.1 model to fill in masked areas of an image according to the provided text description, generating new content that matches the surrounding image.

Inputs

ParameterData TypeRequiredRangeDescription
imageIMAGEYes-The input image to be inpainted
maskMASKYes-The mask defining which areas of the image should be filled
promptSTRINGNo-Prompt for the image generation (default: empty string)
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)
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
output_imageIMAGEThe generated image with the masked areas filled according to the prompt