daanelson / flux-fill-dev-big

Image inpainting with flux

  • Public
  • 31 runs
  • H100
  • GitHub
  • Weights
  • License

Input

*string
Shift + Return to add a new line

Prompt for generated image

*file
Preview
image

The image to inpaint. Can contain alpha mask. If the image width or height are not multiples of 32, they will be scaled to the closest multiple of 32. If the image dimensions don't fit within 2048x2048, it will be scaled down to fit.

file
Preview
mask

A black-and-white image that describes the part of the image to inpaint. Black areas will be preserved while white areas will be inpainted.

integer
(minimum: 1, maximum: 4)

Number of outputs to generate

Default: 1

integer
(minimum: 1, maximum: 50)

Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.

Default: 28

number
(minimum: 0, maximum: 100)

Guidance for generated image

Default: 30

integer

Random seed. Set for reproducible generation

string

Approximate number of megapixels for generated image. Use match_input to match the size of the input (with an upper limit of 1440x1440 pixels)

Default: "1"

string

Format of the output images

Default: "webp"

integer
(minimum: 0, maximum: 100)

Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs

Default: 80

boolean

This model’s safety checker can’t be disabled when running on the website. Learn more about platform safety on Replicate.

Disable safety checker for generated images.

Default: false

Output

output
Generated in

Run time and cost

This model runs on Nvidia H100 GPU hardware. We don't yet have enough runs of this model to provide performance information.

Readme

FLUX.1 Fill [dev]

FLUX.1 Fill [dev] brings professional-quality inpainting to open development. Paint over any part of an image, describe what you want to see instead, and get natural results that respect the original context.

This is the same technology that powers Fill [pro], optimized for developers building creative tools. The model weights and code are available on Hugging Face under the Flux Dev License.

This model supports input image sizes up to 2048x2048; to select, set megapixels input to match_input. Larger generations will take a longer time.