zf-kbot/inpaint-and-guess-prompt – Run with an API on Replicate

zf-kbot / inpaint-and-guess-prompt

Use a mask to inpaint the image or generate a prompt based on the mask.

Cold

Public
42.5K runs
L40S

Run with an API

Playground API Examples README Versions

Input

predict_type

string

Predict Type

Default: "standard"

image

*file

Preview

Input Image

mask

*file

Preview

Mask Image

prompt

string

Shift + Return to add a new line

Prompt

Default: ""

negative_prompt

string

Shift + Return to add a new line

Negative Prompt

Default: ""

grow_size

integer

(minimum: 1, maximum: 4)

Grow Size

Default: 1

fine_edge

string

Fine Edge

Default: "disable"

edge_strength

number

(minimum: 0, maximum: 5)

Edge Strength

Default: 0.55

color_strength

number

(minimum: 0, maximum: 5)

Color Strength

Default: 0.55

inpaint_strength

number

(minimum: 0, maximum: 5)

Inpaint Strength

Default: 1

seed

integer

Random seed

Default: 0

steps

integer

(minimum: 1, maximum: 50)

Steps

Default: 20

cfg

number

(minimum: 0, maximum: 20)

CFG

Default: 5

sampler

string

Sampler

Default: "euler_ancestral"

scheduler

string

Scheduler

Default: "karras"

Run this model in Node.js with one line of code:

npx create-replicate --model=zf-kbot/inpaint-and-guess-prompt

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run zf-kbot/inpaint-and-guess-prompt using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "zf-kbot/inpaint-and-guess-prompt:c3044b0dd1f7abe4f5f095039ab46b85d5e1d55f3837594261a472b2dc311dbb",
  {
    input: {
      cfg: 5,
      mask: "https://replicate.delivery/pbxt/MYJY7ENusmrLv2bdygK666ZsxI5xlFTjbIlTx3SEKSlM7oGe/45988b42-c522-4732-a122-cde32497caca-mask.jpg",
      seed: 0,
      image: "https://replicate.delivery/pbxt/MYJY7k5z525kc9Ichp76uuU6WX8CwXeQQ3cDiFp9QGLLbK3J/mom_1.jpg",
      steps: 20,
      prompt: "white hair",
      sampler: "euler_ancestral",
      fine_edge: "disable",
      grow_size: 1,
      scheduler: "karras",
      predict_type: "standard",
      edge_strength: 0.55,
      color_strength: 0.55,
      negative_prompt: "",
      inpaint_strength: 1
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run zf-kbot/inpaint-and-guess-prompt using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "zf-kbot/inpaint-and-guess-prompt:c3044b0dd1f7abe4f5f095039ab46b85d5e1d55f3837594261a472b2dc311dbb",
    input={
        "cfg": 5,
        "mask": "https://replicate.delivery/pbxt/MYJY7ENusmrLv2bdygK666ZsxI5xlFTjbIlTx3SEKSlM7oGe/45988b42-c522-4732-a122-cde32497caca-mask.jpg",
        "seed": 0,
        "image": "https://replicate.delivery/pbxt/MYJY7k5z525kc9Ichp76uuU6WX8CwXeQQ3cDiFp9QGLLbK3J/mom_1.jpg",
        "steps": 20,
        "prompt": "white hair",
        "sampler": "euler_ancestral",
        "fine_edge": "disable",
        "grow_size": 1,
        "scheduler": "karras",
        "predict_type": "standard",
        "edge_strength": 0.55,
        "color_strength": 0.55,
        "negative_prompt": "",
        "inpaint_strength": 1
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run zf-kbot/inpaint-and-guess-prompt using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "zf-kbot/inpaint-and-guess-prompt:c3044b0dd1f7abe4f5f095039ab46b85d5e1d55f3837594261a472b2dc311dbb",
    "input": {
      "cfg": 5,
      "mask": "https://replicate.delivery/pbxt/MYJY7ENusmrLv2bdygK666ZsxI5xlFTjbIlTx3SEKSlM7oGe/45988b42-c522-4732-a122-cde32497caca-mask.jpg",
      "seed": 0,
      "image": "https://replicate.delivery/pbxt/MYJY7k5z525kc9Ichp76uuU6WX8CwXeQQ3cDiFp9QGLLbK3J/mom_1.jpg",
      "steps": 20,
      "prompt": "white hair",
      "sampler": "euler_ancestral",
      "fine_edge": "disable",
      "grow_size": 1,
      "scheduler": "karras",
      "predict_type": "standard",
      "edge_strength": 0.55,
      "color_strength": 0.55,
      "negative_prompt": "",
      "inpaint_strength": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{ "type": "standard", "image": "https://replicate.delivery/xezq/o42hNGIUs4YIJBrO6PATqdgIYeGirEEHvHXYkDl0RtzzXMJKA/output.png" }

{
  "completed_at": "2025-02-24T02:31:03.951823Z",
  "created_at": "2025-02-24T02:30:59.292000Z",
  "data_removed": false,
  "error": null,
  "id": "9k8vwagzvhrma0cn6q5v8x792w",
  "input": {
    "cfg": 5,
    "mask": "https://replicate.delivery/pbxt/MYJY7ENusmrLv2bdygK666ZsxI5xlFTjbIlTx3SEKSlM7oGe/45988b42-c522-4732-a122-cde32497caca-mask.jpg",
    "seed": 0,
    "image": "https://replicate.delivery/pbxt/MYJY7k5z525kc9Ichp76uuU6WX8CwXeQQ3cDiFp9QGLLbK3J/mom_1.jpg",
    "steps": 20,
    "prompt": "white hair",
    "sampler": "euler_ancestral",
    "fine_edge": "disable",
    "grow_size": 1,
    "scheduler": "karras",
    "predict_type": "standard",
    "edge_strength": 0.55,
    "color_strength": 0.55,
    "negative_prompt": "",
    "inpaint_strength": 1
  },
  "logs": "standard mode\nRequested to load SD1ClipModel\nLoading 1 new model\nApply edge controlnet\nBase model type: SD1.5\nBrushNet image.shape = torch.Size([1, 1024, 1024, 3]) mask.shape = torch.Size([1, 1024, 1024])\nBrushNet CL: image_latents shape = torch.Size([1, 4, 128, 128]) interpolated_mask shape = torch.Size([1, 1, 128, 128])\nRequested to load BaseModel\nLoading 1 new model\nBrushNet inference: do_classifier_free_guidance is True\nBrushNet inference, step = 0: image batch = 1, got 2 latents, starting from 0\nBrushNet inference: sample torch.Size([2, 4, 128, 128]) , CL torch.Size([2, 5, 128, 128]) dtype torch.float16\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:02,  6.53it/s]\n 10%|█         | 2/20 [00:00<00:02,  6.49it/s]\n 15%|█▌        | 3/20 [00:00<00:02,  6.49it/s]\n 20%|██        | 4/20 [00:00<00:02,  6.47it/s]\n 25%|██▌       | 5/20 [00:00<00:02,  6.47it/s]\n 30%|███       | 6/20 [00:00<00:02,  6.47it/s]\n 35%|███▌      | 7/20 [00:01<00:02,  6.46it/s]\n 40%|████      | 8/20 [00:01<00:01,  6.44it/s]\n 45%|████▌     | 9/20 [00:01<00:01,  6.45it/s]\n 50%|█████     | 10/20 [00:01<00:01,  6.45it/s]\n 55%|█████▌    | 11/20 [00:01<00:01,  6.45it/s]\n 60%|██████    | 12/20 [00:01<00:01,  6.45it/s]\n 65%|██████▌   | 13/20 [00:02<00:01,  6.45it/s]\n 70%|███████   | 14/20 [00:02<00:00,  6.44it/s]\n 75%|███████▌  | 15/20 [00:02<00:00,  6.45it/s]\n 80%|████████  | 16/20 [00:02<00:00,  6.44it/s]\n 85%|████████▌ | 17/20 [00:02<00:00,  6.44it/s]\n 90%|█████████ | 18/20 [00:02<00:00,  6.44it/s]\n 95%|█████████▌| 19/20 [00:02<00:00,  6.45it/s]\n100%|██████████| 20/20 [00:03<00:00,  6.44it/s]\n100%|██████████| 20/20 [00:03<00:00,  6.45it/s]",
  "metrics": {
    "predict_time": 4.652047751,
    "total_time": 4.659823
  },
  "output": {
    "type": "standard",
    "image": "https://replicate.delivery/xezq/o42hNGIUs4YIJBrO6PATqdgIYeGirEEHvHXYkDl0RtzzXMJKA/output.png"
  },
  "started_at": "2025-02-24T02:30:59.299775Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/9k8vwagzvhrma0cn6q5v8x792w",
    "cancel": "https://api.replicate.com/v1/predictions/9k8vwagzvhrma0cn6q5v8x792w/cancel"
  },
  "version": "c3044b0dd1f7abe4f5f095039ab46b85d5e1d55f3837594261a472b2dc311dbb"
}

Generated in

4.7 seconds

Tweak it Share Report

Run time and cost

This model costs approximately $0.0069 to run on Replicate, or 144 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 8 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Overview 🌈

This model supports two modes, image inpaint and prompt generation

Using in Website 🖥️

Home: Remaker AI

Web Features: Photo Editor

Getting Started 🚀

Inpaint

“predict_type” param selection “standard” for inpaint mode
Upload your image to “image” param
Upload the mask image to “mask” param
Input the inpaint prompt
Get image!

Guess Prompt

“predict_type” param selection “guess” for guess mode
Upload your image to “image” param
Upload the mask image to “mask” param
Get prompt! (The model will guess the final prompt based on the image position marked by the mask)