black-forest-labs/flux-fill-pro 🖼️🔢📝❓✓ → 🖼️

⭐ Official ▶️ 3.9M runs 📅 Nov 2024 ⚙️ Cog 0.16.11 ⚖️ License

image-editing image-inpainting image-object-removal image-outpainting

About

Professional inpainting and outpainting model with state-of-the-art performance. Edit or extend images with natural, seamless results.

Example Output

Prompt:

"movie poster says "FLUX FILL""

Output

Performance Metrics

8.22s Prediction Time

8.22s Total Time

1 Images

All Input Parameters

{
  "mask": "https://replicate.delivery/pbxt/M0gpLCYdCLbnhcz95Poy66q30XW9VSCN65DoDQ8IzdzlQonw/kill-bill-mask.png",
  "image": "https://replicate.delivery/pbxt/M0gpKVE9wmEtOQFNDOpwz1uGs0u6nK2NcE85IihwlN0ZEnMF/kill-bill-poster.jpg",
  "steps": 50,
  "prompt": "movie poster says \"FLUX FILL\"",
  "guidance": 60,
  "outpaint": "None",
  "output_format": "jpg",
  "safety_tolerance": 2,
  "prompt_upsampling": false
}

Input Parameters

mask Type: string: 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. Must have the same size as image. Optional if you provide an alpha mask in the original image. Must be jpeg, png, gif, or webp.
seed Type: integer: Random seed. Set for reproducible generation
image (required) Type: string: The image to inpaint. Can contain an alpha mask. Must be jpeg, png, gif, or webp.
steps Type: integerDefault: 50Range: 15 - 50: Number of diffusion steps. Higher values yield finer details but increase processing time.
prompt (required) Type: string: Text prompt for image generation
guidance Type: numberDefault: 60Range: 1.5 - 100: Controls the balance between adherence to the text prompt and image quality/diversity. Higher values make the output more closely match the prompt but may reduce overall image quality. Lower values allow for more creative freedom but might produce results less relevant to the prompt.
outpaint Default: None: A quick option for outpainting an input image. Mask will be ignored.
output_format Default: jpg: Format of the output images.
safety_tolerance Type: integerDefault: 2Range: 1 - 6: Safety tolerance, 1 is most strict and 6 is most permissive
prompt_upsampling Type: booleanDefault: false: Automatically modify the prompt for more creative generation

Output Schema

Output

Type: string • Format: uri

Example Execution Logs

Preparing prediction... 
Checking mask
Image size: 65.0KB
Image size: 1.4KB
Using seed: 33539
Creating prediction... 
Generating image...
Generated image in 7.8sec
Downloading output... 
Downloaded image in 0.30sec

Version Details

Version ID: 41c767bcbfffe54ef8f05eb4d0100f9314790f7fc43a7b88d73ec06839deddb9
Version Created: April 14, 2026

Run on Replicate →