> ## Documentation Index
> Fetch the complete documentation index at: https://docs.rubbrband.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Inpaint Image Node

> Learn about Rubbrband's Inpaint Nodes

Inpaint nodes take a particular area of an image, and regenerate its contents given a prompt

**Flux Pro Inpaint Node**
Inpaint powered by Flux Pro.

<img src="https://rubbrband-static-assets-buckets.s3.us-east-1.amazonaws.com/docs/images/inpaint_flux_pro.jpg" />

**Inputs**

<ResponseField name="Prompt" type="string" required={true}>
  The prompt that describes the region to be inpainted. You do not need to
  describe the rest of the image.
</ResponseField>

<ResponseField name="Base Image" type="image" required={true}>
  The original image
</ResponseField>

<ResponseField name="Mask Image" type="mask" required={true}>
  The mask that is the section of the original image that needs to be redone.
</ResponseField>

**Settings**

<ResponseField name="Color Palette" type="color">
  The colors that you want in the output video
</ResponseField>

<ResponseField name="Dilate Mask Amount" type="number">
  A number representing the number of pixels to dilate the mask by. For example,
  if set to 1, that means every pixel *1* away from the shaded mask will also be
  inpainted.
</ResponseField>

<ResponseField name="Number of steps" type="integer">
  Increasing the number of steps increases the number of iterations the AI takes
  to generate your image. Increasing steps make generations take longer, but can
  sometimes lead to more coherent images.
</ResponseField>

<ResponseField name="seed" type="integer">
  A random number that will set the seed for the generation. Keeping the seed
  constant will result in the same outputs. -1 randomizes the seed.
</ResponseField>

**Outputs**

<ResponseField name="Image" type="image">
  The output image after the inpaint.
</ResponseField>

**Flux Dev Inpaint Node**
Inpaint powered by Flux Dev.

**Inputs**

<ResponseField name="Prompt" type="string" required={true}>
  The prompt that describes the region to be inpainted. You do not need to
  describe the rest of the image.
</ResponseField>

<ResponseField name="Base Image" type="image" required={true}>
  The original image
</ResponseField>

<ResponseField name="Mask Image" type="mask" required={true}>
  The mask that is the section of the original image that needs to be redone.
</ResponseField>

**Settings**

<ResponseField name="Color Palette" type="color">
  The colors that you want in the output video
</ResponseField>

<ResponseField name="Denoising Strength" type="number">
  A number that represents similarity to the prompt. Increasing this results in
  a generation that is more similar to the prompt, and less similar to the
  initial area. NOTE: In Rubbrband, with Flux Dev inpainting, we attempt to blur
  out the initial object before inpainting. As a result, if you set the
  denoising strength to very low values, you might receive blurry outputs in the
  area of interest.
</ResponseField>

<ResponseField name="Dilate Mask Amount" type="number">
  A number representing the number of pixels to dilate the mask by. For example,
  if set to 1, that means every pixel *1* away from the shaded mask will also be
  inpainted.
</ResponseField>

<ResponseField name="Number of steps" type="integer">
  Increasing the number of steps increases the number of iterations the AI takes
  to generate your image. Increasing steps make generations take longer, but can
  sometimes lead to more coherent images.
</ResponseField>

<ResponseField name="seed" type="integer">
  A random number that will set the seed for the generation. Keeping the seed
  constant will result in the same outputs. -1 randomizes the seed.
</ResponseField>

**Outputs**

<ResponseField name="Image" type="image">
  The output image after the inpaint.
</ResponseField>