prakharsaxena24/2d-to-real-style – Run with an API on Replicate

prakharsaxena24 / 2d-to-real-style

Cold

Public
495 runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

image

*file

Preview

input image

image_style

*file

Preview

Style image

style_strength

number

(minimum: 0, maximum: 3)

IpADapter style

Default: 0.4

structure_strength

number

(minimum: 0, maximum: 3)

ControlNet Strength

Default: 0.6

prompt

string

Shift + Return to add a new line

Prompt

Default: "masterpiece, best quality, highres"

negative_prompt

string

Shift + Return to add a new line

worst quality, low quality, normal qualityworst quality, low quality, normal quality

Negative Prompt

Default: "worst quality, low quality, normal quality"

num_inference_steps

integer

(minimum: 1, maximum: 100)

Num steps

Default: 30

guidance_scale

number

(minimum: 1, maximum: 50)

CFG

Default: 8

seed

integer

Seed

Default: 42

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

npx create-replicate --model=prakharsaxena24/2d-to-real-style

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";
import fs from "node:fs";

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

Run prakharsaxena24/2d-to-real-style using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "prakharsaxena24/2d-to-real-style:fef4d74fb7d11df35aa4bbdf3d8671b4d0352464dc67b169968393c657ab6038",
  {
    input: {
      seed: 42,
      image: "https://replicate.delivery/pbxt/LA886TPWPMFmz6yyQ02rYQN31X3UaOe8JUa9rW1n2OyEZ1jr/hands.png",
      prompt: "masterpiece, best quality, highres",
      image_style: "https://replicate.delivery/pbxt/LA885v0Wbi7Ty82M6QbxRURAuxWwcsXvGs2KMiWBv9QyKMdd/Style.png",
      guidance_scale: 8,
      style_strength: 0.4,
      negative_prompt: "worst quality, low quality, normal quality",
      structure_strength: 0.6,
      num_inference_steps: 30
    }
  }
);

// 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 prakharsaxena24/2d-to-real-style using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "prakharsaxena24/2d-to-real-style:fef4d74fb7d11df35aa4bbdf3d8671b4d0352464dc67b169968393c657ab6038",
    input={
        "seed": 42,
        "image": "https://replicate.delivery/pbxt/LA886TPWPMFmz6yyQ02rYQN31X3UaOe8JUa9rW1n2OyEZ1jr/hands.png",
        "prompt": "masterpiece, best quality, highres",
        "image_style": "https://replicate.delivery/pbxt/LA885v0Wbi7Ty82M6QbxRURAuxWwcsXvGs2KMiWBv9QyKMdd/Style.png",
        "guidance_scale": 8,
        "style_strength": 0.4,
        "negative_prompt": "worst quality, low quality, normal quality",
        "structure_strength": 0.6,
        "num_inference_steps": 30
    }
)
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 prakharsaxena24/2d-to-real-style 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": "prakharsaxena24/2d-to-real-style:fef4d74fb7d11df35aa4bbdf3d8671b4d0352464dc67b169968393c657ab6038",
    "input": {
      "seed": 42,
      "image": "https://replicate.delivery/pbxt/LA886TPWPMFmz6yyQ02rYQN31X3UaOe8JUa9rW1n2OyEZ1jr/hands.png",
      "prompt": "masterpiece, best quality, highres",
      "image_style": "https://replicate.delivery/pbxt/LA885v0Wbi7Ty82M6QbxRURAuxWwcsXvGs2KMiWBv9QyKMdd/Style.png",
      "guidance_scale": 8,
      "style_strength": 0.4,
      "negative_prompt": "worst quality, low quality, normal quality",
      "structure_strength": 0.6,
      "num_inference_steps": 30
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-06-26T07:16:48.475518Z",
  "created_at": "2024-06-26T07:15:45.943000Z",
  "data_removed": false,
  "error": null,
  "id": "7e01n4m4jxrgp0cgadkbsbqcjr",
  "input": {
    "seed": 42,
    "image": "https://replicate.delivery/pbxt/LA886TPWPMFmz6yyQ02rYQN31X3UaOe8JUa9rW1n2OyEZ1jr/hands.png",
    "prompt": "masterpiece, best quality, highres",
    "image_style": "https://replicate.delivery/pbxt/LA885v0Wbi7Ty82M6QbxRURAuxWwcsXvGs2KMiWBv9QyKMdd/Style.png",
    "guidance_scale": 8,
    "style_strength": 0.4,
    "negative_prompt": "worst quality, low quality, normal quality",
    "structure_strength": 0.6,
    "num_inference_steps": 30
  },
  "logs": "0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:06,  4.49it/s]\n 10%|█         | 3/30 [00:00<00:03,  7.49it/s]\n 13%|█▎        | 4/30 [00:00<00:03,  7.46it/s]\n 17%|█▋        | 5/30 [00:00<00:03,  7.45it/s]\n 20%|██        | 6/30 [00:00<00:03,  7.44it/s]\n 23%|██▎       | 7/30 [00:00<00:03,  7.44it/s]\n 27%|██▋       | 8/30 [00:01<00:02,  7.43it/s]\n 30%|███       | 9/30 [00:01<00:02,  7.43it/s]\n 33%|███▎      | 10/30 [00:01<00:02,  7.42it/s]\n 37%|███▋      | 11/30 [00:01<00:02,  7.42it/s]\n 40%|████      | 12/30 [00:01<00:02,  7.42it/s]\n 43%|████▎     | 13/30 [00:01<00:02,  7.42it/s]\n 47%|████▋     | 14/30 [00:01<00:02,  7.42it/s]\n 50%|█████     | 15/30 [00:02<00:02,  7.42it/s]\n 53%|█████▎    | 16/30 [00:02<00:01,  7.42it/s]\n 57%|█████▋    | 17/30 [00:02<00:01,  7.42it/s]\n 60%|██████    | 18/30 [00:02<00:01,  7.42it/s]\n 63%|██████▎   | 19/30 [00:02<00:01,  7.42it/s]\n 67%|██████▋   | 20/30 [00:02<00:01,  7.42it/s]\n 70%|███████   | 21/30 [00:02<00:01,  7.42it/s]\n 73%|███████▎  | 22/30 [00:02<00:01,  7.42it/s]\n 77%|███████▋  | 23/30 [00:03<00:00,  7.42it/s]\n 80%|████████  | 24/30 [00:03<00:00,  7.42it/s]\n 83%|████████▎ | 25/30 [00:03<00:00,  7.42it/s]\n 87%|████████▋ | 26/30 [00:03<00:00,  7.42it/s]\n 90%|█████████ | 27/30 [00:03<00:00,  7.42it/s]\n 93%|█████████▎| 28/30 [00:03<00:00,  7.42it/s]\n 97%|█████████▋| 29/30 [00:03<00:00,  7.42it/s]\n100%|██████████| 30/30 [00:04<00:00,  7.42it/s]\n100%|██████████| 30/30 [00:04<00:00,  7.38it/s]\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:07,  3.68it/s]\n  7%|▋         | 2/30 [00:00<00:05,  5.21it/s]\n 10%|█         | 3/30 [00:00<00:04,  6.02it/s]\n 13%|█▎        | 4/30 [00:00<00:04,  6.48it/s]\n 17%|█▋        | 5/30 [00:00<00:03,  6.78it/s]\n 20%|██        | 6/30 [00:00<00:03,  6.97it/s]\n 23%|██▎       | 7/30 [00:01<00:03,  7.09it/s]\n 27%|██▋       | 8/30 [00:01<00:03,  7.16it/s]\n 30%|███       | 9/30 [00:01<00:02,  7.23it/s]\n 33%|███▎      | 10/30 [00:01<00:02,  7.27it/s]\n 37%|███▋      | 11/30 [00:01<00:02,  7.29it/s]\n 40%|████      | 12/30 [00:01<00:02,  7.31it/s]\n 43%|████▎     | 13/30 [00:01<00:02,  7.33it/s]\n 47%|████▋     | 14/30 [00:02<00:02,  7.34it/s]\n 50%|█████     | 15/30 [00:02<00:02,  7.34it/s]\n 53%|█████▎    | 16/30 [00:02<00:01,  7.35it/s]\n 57%|█████▋    | 17/30 [00:02<00:01,  7.36it/s]\n 60%|██████    | 18/30 [00:02<00:01,  7.36it/s]\n 63%|██████▎   | 19/30 [00:02<00:01,  7.36it/s]\n 67%|██████▋   | 20/30 [00:02<00:01,  7.36it/s]\n 70%|███████   | 21/30 [00:02<00:01,  7.36it/s]\n 73%|███████▎  | 22/30 [00:03<00:01,  7.36it/s]\n 77%|███████▋  | 23/30 [00:03<00:00,  7.36it/s]\n 80%|████████  | 24/30 [00:03<00:00,  7.36it/s]\n 83%|████████▎ | 25/30 [00:03<00:00,  7.36it/s]\n 87%|████████▋ | 26/30 [00:03<00:00,  7.36it/s]\n 90%|█████████ | 27/30 [00:03<00:00,  7.36it/s]\n 93%|█████████▎| 28/30 [00:03<00:00,  7.36it/s]\n 97%|█████████▋| 29/30 [00:04<00:00,  7.36it/s]\n100%|██████████| 30/30 [00:04<00:00,  7.35it/s]\n100%|██████████| 30/30 [00:04<00:00,  7.12it/s]",
  "metrics": {
    "predict_time": 10.816792843,
    "total_time": 62.532518
  },
  "output": [
    "https://replicate.delivery/pbxt/57G7NnY4JDKaPlRRogaBUdOplwsNfd244RhKcqjNlRNwkLhJA/out-42-0.png"
  ],
  "started_at": "2024-06-26T07:16:37.658725Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/7e01n4m4jxrgp0cgadkbsbqcjr",
    "cancel": "https://api.replicate.com/v1/predictions/7e01n4m4jxrgp0cgadkbsbqcjr/cancel"
  },
  "version": "fef4d74fb7d11df35aa4bbdf3d8671b4d0352464dc67b169968393c657ab6038"
}

Generated in

10.8 seconds

Tweak it ShareReport

0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:06,  4.49it/s]
 10%|█         | 3/30 [00:00<00:03,  7.49it/s]
 13%|█▎        | 4/30 [00:00<00:03,  7.46it/s]
 17%|█▋        | 5/30 [00:00<00:03,  7.45it/s]
 20%|██        | 6/30 [00:00<00:03,  7.44it/s]
 23%|██▎       | 7/30 [00:00<00:03,  7.44it/s]
 27%|██▋       | 8/30 [00:01<00:02,  7.43it/s]
 30%|███       | 9/30 [00:01<00:02,  7.43it/s]
 33%|███▎      | 10/30 [00:01<00:02,  7.42it/s]
 37%|███▋      | 11/30 [00:01<00:02,  7.42it/s]
 40%|████      | 12/30 [00:01<00:02,  7.42it/s]
 43%|████▎     | 13/30 [00:01<00:02,  7.42it/s]
 47%|████▋     | 14/30 [00:01<00:02,  7.42it/s]
 50%|█████     | 15/30 [00:02<00:02,  7.42it/s]
 53%|█████▎    | 16/30 [00:02<00:01,  7.42it/s]
 57%|█████▋    | 17/30 [00:02<00:01,  7.42it/s]
 60%|██████    | 18/30 [00:02<00:01,  7.42it/s]
 63%|██████▎   | 19/30 [00:02<00:01,  7.42it/s]
 67%|██████▋   | 20/30 [00:02<00:01,  7.42it/s]
 70%|███████   | 21/30 [00:02<00:01,  7.42it/s]
 73%|███████▎  | 22/30 [00:02<00:01,  7.42it/s]
 77%|███████▋  | 23/30 [00:03<00:00,  7.42it/s]
 80%|████████  | 24/30 [00:03<00:00,  7.42it/s]
 83%|████████▎ | 25/30 [00:03<00:00,  7.42it/s]
 87%|████████▋ | 26/30 [00:03<00:00,  7.42it/s]
 90%|█████████ | 27/30 [00:03<00:00,  7.42it/s]
 93%|█████████▎| 28/30 [00:03<00:00,  7.42it/s]
 97%|█████████▋| 29/30 [00:03<00:00,  7.42it/s]
100%|██████████| 30/30 [00:04<00:00,  7.42it/s]
100%|██████████| 30/30 [00:04<00:00,  7.38it/s]
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:07,  3.68it/s]
  7%|▋         | 2/30 [00:00<00:05,  5.21it/s]
 10%|█         | 3/30 [00:00<00:04,  6.02it/s]
 13%|█▎        | 4/30 [00:00<00:04,  6.48it/s]
 17%|█▋        | 5/30 [00:00<00:03,  6.78it/s]
 20%|██        | 6/30 [00:00<00:03,  6.97it/s]
 23%|██▎       | 7/30 [00:01<00:03,  7.09it/s]
 27%|██▋       | 8/30 [00:01<00:03,  7.16it/s]
 30%|███       | 9/30 [00:01<00:02,  7.23it/s]
 33%|███▎      | 10/30 [00:01<00:02,  7.27it/s]
 37%|███▋      | 11/30 [00:01<00:02,  7.29it/s]
 40%|████      | 12/30 [00:01<00:02,  7.31it/s]
 43%|████▎     | 13/30 [00:01<00:02,  7.33it/s]
 47%|████▋     | 14/30 [00:02<00:02,  7.34it/s]
 50%|█████     | 15/30 [00:02<00:02,  7.34it/s]
 53%|█████▎    | 16/30 [00:02<00:01,  7.35it/s]
 57%|█████▋    | 17/30 [00:02<00:01,  7.36it/s]
 60%|██████    | 18/30 [00:02<00:01,  7.36it/s]
 63%|██████▎   | 19/30 [00:02<00:01,  7.36it/s]
 67%|██████▋   | 20/30 [00:02<00:01,  7.36it/s]
 70%|███████   | 21/30 [00:02<00:01,  7.36it/s]
 73%|███████▎  | 22/30 [00:03<00:01,  7.36it/s]
 77%|███████▋  | 23/30 [00:03<00:00,  7.36it/s]
 80%|████████  | 24/30 [00:03<00:00,  7.36it/s]
 83%|████████▎ | 25/30 [00:03<00:00,  7.36it/s]
 87%|████████▋ | 26/30 [00:03<00:00,  7.36it/s]
 90%|█████████ | 27/30 [00:03<00:00,  7.36it/s]
 93%|█████████▎| 28/30 [00:03<00:00,  7.36it/s]
 97%|█████████▋| 29/30 [00:04<00:00,  7.36it/s]
100%|██████████| 30/30 [00:04<00:00,  7.35it/s]
100%|██████████| 30/30 [00:04<00:00,  7.12it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.016 to run on Replicate, or 62 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 12 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.