Skip to main content
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

ParameterDescriptionData TypeRequiredRange
imageThe input image to be inpaintedIMAGEYes-
maskThe mask defining which areas of the image should be filledMASKYes-
promptPrompt for the image generation (default: empty string)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-
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
output_imageThe generated image with the masked areas filled according to the promptIMAGE
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): 68f9834a58d6e2d14743adafb1f791880f0af30fdb65cb6201af5616945bb56b