black-forest-labs/flux-fill-dev

Open-weight inpainting model for editing and extending images. Guidance-distilled from FLUX.1 Fill [pro].

Capabilities

Reference ImagesSeed

Cost

Community model (estimated from hardware time)

Input Parameters

Name	Type	Description	Default	Constraints
`image`*	string(uri)	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 1440x1440, it will be scaled down to fit.	`—`	—
`prompt`*	string	Prompt for generated image	`—`	—
`disable_safety_checker`	boolean	Disable safety checker for generated images.	`false`	—
`guidance`	number	Guidance for generated image	`30`	min: 0, max: 100
`lora_scale`	number	Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.	`1`	min: -1, max: 3
`lora_weights`	string	Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'	`—`	—
`mask`	string(uri)	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.	`—`	—
`megapixels`	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)	`"1"`	10.25match_input
`num_inference_steps`	integer	Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.	`28`	min: 1, max: 50
`num_outputs`	integer	Number of outputs to generate	`1`	min: 1, max: 4
`output_format`	string	Format of the output images	`"webp"`	webpjpgpng
`output_quality`	integer	Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs	`80`	min: 0, max: 100
`seed`	integer	Random seed. Set for reproducible generation	`—`	—

imagerequiredstring

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 1440x1440, it will be scaled down to fit.

promptrequiredstring

Prompt for generated image

disable_safety_checkerboolean

Disable safety checker for generated images.

Default: false

guidancenumber

Guidance for generated image

Default: 30min: 0, max: 100

lora_scalenumber

Determines how strongly the main LoRA should be applied. Sane results between 0 and 1 for base inference. For go_fast we apply a 1.5x multiplier to this value; we've generally seen good performance when scaling the base value by that amount. You may still need to experiment to find the best value for your particular lora.

Default: 1min: -1, max: 3

lora_weightsstring

Load LoRA weights. Supports Replicate models in the format <owner>/<username> or <owner>/<username>/<version>, HuggingFace URLs in the format huggingface.co/<owner>/<model-name>, CivitAI URLs in the format civitai.com/models/<id>[/<model-name>], or arbitrary .safetensors URLs from the Internet. For example, 'fofr/flux-pixar-cars'

maskstring

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.

megapixelsstring

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"

10.25match_input

num_inference_stepsinteger

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

Default: 28min: 1, max: 50

num_outputsinteger

Number of outputs to generate

Default: 1min: 1, max: 4

output_formatstring

Format of the output images

Default: "webp"

webpjpgpng

output_qualityinteger

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

Default: 80min: 0, max: 100

seedinteger

Random seed. Set for reproducible generation

Version: a053f8412561Updated: 7/25/20261.5M runs