logerzhu/ad-inpaint – Run with an API on Replicate

logerzhu / ad-inpaint

Product advertising image generator

Cold

Public
542.5K runs
A100 (80GB)

Run with an API

Playground API Examples README Versions

Input

image_path

*file

input image

product_size

string

Max product size

Default: "Original"

prompt

*string

Shift + Return to add a new line

modern sofa+ in a contemporary living room, filled with stylish decor+;modern, contemporary, sofa, living room, stylish decormodern sofa+ in a contemporary living room, filled with stylish decor+;modern, contemporary, sofa, living room, stylish decor

Product name or prompt

negative_prompt

string

Shift + Return to add a new line

illustration, 3d, sepia, painting, cartoons, sketch, (worst quality:2)illustration, 3d, sepia, painting, cartoons, sketch, (worst quality:2)

Anything you don't want in the photo

Default: "low quality, out of frame, illustration, 3d, sepia, painting, cartoons, sketch, watermark, text, Logo, advertisement"

api_key

string

Shift + Return to add a new line

OpenAI api_key, enhance prompt with ChatGPT if provided

pixel

string

image total pixel

Default: "512 * 512"

scale

integer

(minimum: 0, maximum: 4)

Factor to scale image by (maximum: 4)

Default: 3

image_num

integer

(minimum: 0, maximum: 4)

Number of image to generate

Default: 1

guidance_scale

number

Guidance Scale

Default: 7.5

num_inference_steps

integer

Inference Steps

Default: 20

manual_seed

integer

Manual Seed

Default: -1

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

npx create-replicate --model=logerzhu/ad-inpaint

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 logerzhu/ad-inpaint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "logerzhu/ad-inpaint:b1c17d148455c1fda435ababe9ab1e03bc0d917cc3cf4251916f22c45c83c7df",
  {
    input: {
      pixel: "512 * 512",
      scale: 3,
      prompt: "modern sofa+ in a contemporary living room, filled with stylish decor+;modern, contemporary, sofa, living room, stylish decor",
      image_num: 4,
      image_path: "https://replicate.delivery/pbxt/JAIk0rFAOUG00uetuiLOHPz42lBcf7QfX3xWi7TVaxMXXD4n/sofa1.png",
      manual_seed: -1,
      product_size: "0.5 * width",
      guidance_scale: 7.5,
      negative_prompt: "illustration, 3d, sepia, painting, cartoons, sketch, (worst quality:2)",
      num_inference_steps: 20
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

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 logerzhu/ad-inpaint using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "logerzhu/ad-inpaint:b1c17d148455c1fda435ababe9ab1e03bc0d917cc3cf4251916f22c45c83c7df",
    input={
        "pixel": "512 * 512",
        "scale": 3,
        "prompt": "modern sofa+ in a contemporary living room, filled with stylish decor+;modern, contemporary, sofa, living room, stylish decor",
        "image_num": 4,
        "image_path": "https://replicate.delivery/pbxt/JAIk0rFAOUG00uetuiLOHPz42lBcf7QfX3xWi7TVaxMXXD4n/sofa1.png",
        "manual_seed": -1,
        "product_size": "0.5 * width",
        "guidance_scale": 7.5,
        "negative_prompt": "illustration, 3d, sepia, painting, cartoons, sketch, (worst quality:2)",
        "num_inference_steps": 20
    }
)
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 logerzhu/ad-inpaint 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": "logerzhu/ad-inpaint:b1c17d148455c1fda435ababe9ab1e03bc0d917cc3cf4251916f22c45c83c7df",
    "input": {
      "pixel": "512 * 512",
      "scale": 3,
      "prompt": "modern sofa+ in a contemporary living room, filled with stylish decor+;modern, contemporary, sofa, living room, stylish decor",
      "image_num": 4,
      "image_path": "https://replicate.delivery/pbxt/JAIk0rFAOUG00uetuiLOHPz42lBcf7QfX3xWi7TVaxMXXD4n/sofa1.png",
      "manual_seed": -1,
      "product_size": "0.5 * width",
      "guidance_scale": 7.5,
      "negative_prompt": "illustration, 3d, sepia, painting, cartoons, sketch, (worst quality:2)",
      "num_inference_steps": 20
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-07-26T16:12:09.608092Z",
  "created_at": "2023-07-26T16:10:16.040470Z",
  "data_removed": false,
  "error": null,
  "id": "ruw4whdbwnqkmntk45gfnbt4um",
  "input": {
    "pixel": "512 * 512",
    "scale": 3,
    "prompt": "modern sofa+ in a contemporary living room, filled with stylish decor+;modern, contemporary, sofa, living room, stylish decor",
    "image_num": 4,
    "image_path": "https://replicate.delivery/pbxt/JAIk0rFAOUG00uetuiLOHPz42lBcf7QfX3xWi7TVaxMXXD4n/sofa1.png",
    "manual_seed": -1,
    "product_size": "0.5 * width",
    "guidance_scale": 7.5,
    "negative_prompt": "illustration, 3d, sepia, painting, cartoons, sketch, (worst quality:2)",
    "num_inference_steps": 20
  },
  "logs": "1. Image matting: (2040, 1128)\n2. Generate ad images\nSeed: 10401463081148911623\n  0%|          | 0/5 [00:00<?, ?it/s]\n 20%|██        | 1/5 [00:00<00:00,  4.66it/s]\n 60%|██████    | 3/5 [00:00<00:00,  5.76it/s]\n100%|██████████| 5/5 [00:00<00:00,  8.13it/s]\n100%|██████████| 5/5 [00:00<00:00,  7.32it/s]\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:04,  4.67it/s]\n 10%|█         | 2/20 [00:00<00:03,  5.66it/s]\n 15%|█▌        | 3/20 [00:00<00:02,  6.07it/s]\n 20%|██        | 4/20 [00:00<00:02,  6.28it/s]\n 25%|██▌       | 5/20 [00:00<00:02,  6.41it/s]\n 30%|███       | 6/20 [00:00<00:02,  6.49it/s]\n 35%|███▌      | 7/20 [00:01<00:01,  6.54it/s]\n 40%|████      | 8/20 [00:01<00:01,  6.57it/s]\n 45%|████▌     | 9/20 [00:01<00:01,  6.60it/s]\n 50%|█████     | 10/20 [00:01<00:01,  6.61it/s]\n 55%|█████▌    | 11/20 [00:01<00:01,  6.63it/s]\n 60%|██████    | 12/20 [00:01<00:01,  6.64it/s]\n 65%|██████▌   | 13/20 [00:02<00:01,  6.64it/s]\n 70%|███████   | 14/20 [00:02<00:00,  6.65it/s]\n 75%|███████▌  | 15/20 [00:02<00:00,  6.65it/s]\n 80%|████████  | 16/20 [00:02<00:00,  6.65it/s]\n 85%|████████▌ | 17/20 [00:02<00:00,  6.65it/s]\n 90%|█████████ | 18/20 [00:02<00:00,  6.65it/s]\n 95%|█████████▌| 19/20 [00:02<00:00,  6.65it/s]\n100%|██████████| 20/20 [00:03<00:00,  6.66it/s]\n100%|██████████| 20/20 [00:03<00:00,  6.51it/s]\n4. Super resolution image\n- image 0\n- image 1\n- image 2\n- image 3",
  "metrics": {
    "predict_time": 18.413594,
    "total_time": 113.567622
  },
  "output": [
    "https://replicate.delivery/pbxt/OWLoZ3R76QKUPxv1D9K2p4xrjIhQycwAcoYxebqN3POsv3pIA/top.png",
    "https://replicate.delivery/pbxt/yBfegYrL1Yn91UhjDiRB2GghF81RkM7ewbyOrJeZ80yi99OFB/ad_inpaint_0.jpg",
    "https://replicate.delivery/pbxt/k1NvfCQBe0qLl0VaEULDWyMVcAosy6eHLb6VMX7obPDwe9OFB/ad_inpaint_1.jpg",
    "https://replicate.delivery/pbxt/wOJj1YoeoepFrEzCsbXfc9lcjyvoOF3SzlUMvtqXOJnze9OFB/ad_inpaint_2.jpg",
    "https://replicate.delivery/pbxt/3ZmtvTJWj3a0Al9XR7SSKqpAfLTZtrkM7t5KjLvz7Nqsv3pIA/ad_inpaint_3.jpg"
  ],
  "started_at": "2023-07-26T16:11:51.194498Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ruw4whdbwnqkmntk45gfnbt4um",
    "cancel": "https://api.replicate.com/v1/predictions/ruw4whdbwnqkmntk45gfnbt4um/cancel"
  },
  "version": "b1c17d148455c1fda435ababe9ab1e03bc0d917cc3cf4251916f22c45c83c7df"
}

Generated in

18.4 seconds

Tweak itReport

Examples

View more examples

Run time and cost

This model costs approximately $0.056 to run on Replicate, or 17 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 A100 (80GB) GPU hardware. Predictions typically complete within 40 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Automatically generate product advertising image.

This is a Demo based on stable-diffusion-2-inpainting and ControlNet, repaint the product background.

It is recommended to use Product png images with a transparent background. Non-transparent image will use the product image extracted by Tracer-B7 Networks.
prompt / negative_prompt uses the compel library for embedding, supporting the format of “Weighting + - (word)0.9”.