fermatresearch/magic-image-refiner – Run with an API on Replicate

fermatresearch / magic-image-refiner

A better alternative to SDXL refiners, providing a lot of quality and detail. Can also be used for inpainting or upscaling.

Cold

Public
929K runs
L40S
GitHub

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

UHD 4k vogue, a woman resting in a magic pool, face above the surface of the water, red frecklesUHD 4k vogue, a woman resting in a magic pool, face above the surface of the water, red freckles

Prompt for the model

image

file

Preview

Image to refine

mask

file

When provided, refines some section of the image. Must be the same size as the image

resolution

string

Image resolution

Default: "original"

resemblance

number

(minimum: 0, maximum: 1)

Conditioning scale for controlnet

Default: 0.75

creativity

number

(minimum: 0, maximum: 1)

Denoising strength. 1 means total destruction of the original image

Default: 0.25

hdr

number

(minimum: 0, maximum: 1)

HDR improvement over the original image

Default: 0

scheduler

string

Choose a scheduler.

Default: "DDIM"

steps

integer

Steps

Default: 20

guidance_scale

number

(minimum: 0.1, maximum: 30)

Scale for classifier-free guidance

Default: 7

seed

integer

Seed

negative_prompt

string

Shift + Return to add a new line

teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutantteeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant

Negative prompt

Default: "teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant"

guess_mode

boolean

In this mode, the ControlNet encoder will try best to recognize the content of the input image even if you remove all prompts. The `guidance_scale` between 3.0 and 5.0 is recommended.

Default: false

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

npx create-replicate --model=fermatresearch/magic-image-refiner

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 fermatresearch/magic-image-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "fermatresearch/magic-image-refiner:507ddf6f977a7e30e46c0daefd30de7d563c72322f9e4cf7cbac52ef0f667b13",
  {
    input: {
      hdr: 0,
      image: "https://replicate.delivery/pbxt/KA9yP9n3ZX5A5mkoPz3gsPzKTH1NA7LqVkQRTg7Sov46lOfo/0_1.webp",
      steps: 20,
      prompt: "UHD 4k vogue, a woman resting in a magic pool, face above the surface of the water, red freckles",
      scheduler: "DDIM",
      creativity: 0.25,
      guess_mode: false,
      resolution: "original",
      resemblance: 0.75,
      guidance_scale: 7,
      negative_prompt: "teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant"
    }
  }
);

// 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 fermatresearch/magic-image-refiner using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fermatresearch/magic-image-refiner:507ddf6f977a7e30e46c0daefd30de7d563c72322f9e4cf7cbac52ef0f667b13",
    input={
        "hdr": 0,
        "image": "https://replicate.delivery/pbxt/KA9yP9n3ZX5A5mkoPz3gsPzKTH1NA7LqVkQRTg7Sov46lOfo/0_1.webp",
        "steps": 20,
        "prompt": "UHD 4k vogue, a woman resting in a magic pool, face above the surface of the water, red freckles",
        "scheduler": "DDIM",
        "creativity": 0.25,
        "guess_mode": False,
        "resolution": "original",
        "resemblance": 0.75,
        "guidance_scale": 7,
        "negative_prompt": "teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant"
    }
)
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 fermatresearch/magic-image-refiner 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": "507ddf6f977a7e30e46c0daefd30de7d563c72322f9e4cf7cbac52ef0f667b13",
    "input": {
      "hdr": 0,
      "image": "https://replicate.delivery/pbxt/KA9yP9n3ZX5A5mkoPz3gsPzKTH1NA7LqVkQRTg7Sov46lOfo/0_1.webp",
      "steps": 20,
      "prompt": "UHD 4k vogue, a woman resting in a magic pool, face above the surface of the water, red freckles",
      "scheduler": "DDIM",
      "creativity": 0.25,
      "guess_mode": false,
      "resolution": "original",
      "resemblance": 0.75,
      "guidance_scale": 7,
      "negative_prompt": "teeth, tooth, open mouth, longbody, lowres, bad anatomy, bad hands, missing fingers, extra digit, fewer digits, cropped, worst quality, low quality, mutant"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

3.4 seconds

Tweak itReport

This example was created by a different version, fermatresearch/magic-image-refiner:3064c8a3.

Examples

View more examples

Run time and cost

This model costs approximately $0.0055 to run on Replicate, or 181 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 6 seconds.

Readme

This model doesn't have a readme.