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

⭐ Official ▶️ 1.2M runs 📅 Nov 2024 ⚙️ Cog 0.9.21 ⚖️ License

image-inpainting image-outpainting

About

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

Example Output

Prompt:

"a spaceship"

Output

Performance Metrics

9.54s Prediction Time

9.55s Total Time

1 Images

All Input Parameters

{
  "mask": "https://replicate.delivery/pbxt/M0hxLu8a1YBcybWuumSsfoEec8ooer6JZ2fR28vuM1U0CN9m/74b40bb1-364a-461a-bec5-200a38c7bc87.png",
  "image": "https://replicate.delivery/pbxt/M0hxMJeO7wFCMr7QYNZsjRxzHhz6ntlLllMteRQNsRD7f3Nf/flux-fill-dev.webp",
  "prompt": "a spaceship",
  "guidance": 30,
  "num_outputs": 1,
  "output_format": "webp",
  "output_quality": 80,
  "num_inference_steps": 28
}

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.
seed Type: integer: Random seed. Set for reproducible generation
image (required) Type: string: 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 (required) Type: string: Prompt for generated image
guidance Type: numberDefault: 30Range: 0 - 100: Guidance for generated image
lora_scale Type: numberDefault: 1Range: -1 - 3: 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.
megapixels Default: 1: Approximate number of megapixels for generated image. Use match_input to match the size of the input (with an upper limit of 1440x1440 pixels)
num_outputs Type: integerDefault: 1Range: 1 - 4: Number of outputs to generate
lora_weights Type: 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'
output_format Default: webp: Format of the output images
output_quality Type: integerDefault: 80Range: 0 - 100: Quality when saving the output images, from 0 to 100. 100 is best quality, 0 is lowest quality. Not relevant for .png outputs
num_inference_steps Type: integerDefault: 28Range: 1 - 50: Number of denoising steps. Recommended range is 28-50, and lower number of steps produce lower quality outputs, faster.
disable_safety_checker Type: booleanDefault: false: Disable safety checker for generated images.

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

running bf16 model, fp8 disabled
Using seed: 12554
Input image size: 1024x1024
Input image size set to: 1024x1024
0it [00:00, ?it/s]
1it [00:00,  6.43it/s]
2it [00:00,  5.21it/s]
3it [00:00,  4.91it/s]
4it [00:00,  4.78it/s]
5it [00:01,  4.71it/s]
6it [00:01,  4.67it/s]
7it [00:01,  4.63it/s]
8it [00:01,  4.62it/s]
9it [00:01,  4.61it/s]
10it [00:02,  4.60it/s]
11it [00:02,  4.60it/s]
12it [00:02,  4.60it/s]
13it [00:02,  4.59it/s]
14it [00:02,  4.59it/s]
15it [00:03,  4.59it/s]
16it [00:03,  4.59it/s]
17it [00:03,  4.58it/s]
18it [00:03,  4.58it/s]
19it [00:04,  4.57it/s]
20it [00:04,  4.57it/s]
21it [00:04,  4.57it/s]
22it [00:04,  4.57it/s]
23it [00:04,  4.57it/s]
24it [00:05,  4.57it/s]
25it [00:05,  4.58it/s]
26it [00:05,  4.58it/s]
27it [00:05,  4.58it/s]
28it [00:06,  4.57it/s]
28it [00:06,  4.63it/s]
Total safe images: 1 out of 1

Version Details

Version ID: a053f84125613d83e65328a289e14eb6639e10725c243e8fb0c24128e5573f4c
Version Created: March 31, 2025

Run on Replicate →