fermatresearch/magic-style-transfer:3b5fa5d3 | Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

fermatresearch /magic-style-transfer:3b5fa5d3

Input

prompt

string

Shift + Return to add a new line

shot in the style of sksfer, words "MARC AGUILAR" by Van Gogh, colorful patternshot in the style of sksfer, words "MARC AGUILAR" by Van Gogh, colorful pattern

Input prompt

Default: "An astronaut riding a rainbow unicorn"

image

file

Preview

Input image

ip_image

file

Preview

Input image for img2img or inpaint mode

condition_depth_scale

number

(minimum: 0, maximum: 2)

The bigger this number is, the more ControlNet interferes

Default: 0.35

condition_canny_scale

number

(minimum: 0, maximum: 2)

The bigger this number is, the more ControlNet interferes

Default: 0.15

lora_scale

number

(minimum: 0, maximum: 1)

LoRA additive scale. Only applicable on trained models.

Default: 0.9

ip_scale

number

(minimum: 0, maximum: 1)

IP Adapter strength.

Default: 0.3

strength

number

(minimum: 0, maximum: 1)

When img2img is active, the denoising strength. 1 means total destruction of the input image.

Default: 0.9

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

background_color

string

Shift + Return to add a new line

When passing an image with alpha channel, it will be replaced with this color

Default: "#A2A2A2"

resizing_scale

number

(minimum: 1, maximum: 10)

If you want the image to have a solid margin. Scale of the solid margin. 1.0 means no resizing.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 30

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output

Default: 1

scheduler

string

scheduler

Default: "K_EULER"

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 4

seed

integer

Random seed. Leave blank to randomize the seed

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

lora_weights

string

Shift + Return to add a new line

Replicate LoRA weights to use. Leave blank to use the default weights.

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

npx create-replicate --model=fermatresearch/magic-style-transfer

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

const output = await replicate.run(
  "fermatresearch/magic-style-transfer:3b5fa5d360c361090f11164292e45cc5d14cea8d089591d47c580cac9ec1c7ca",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KbVQ4ItrGWdUk9jN7KdNo5nr7h9CxSvJncYIhKtDlpA61nyl/Screenshot%202024-03-20%20at%2019.09.12.png",
      prompt: "shot in the style of sksfer, words \"MARC AGUILAR\" by Van Gogh, colorful pattern",
      ip_image: "https://replicate.delivery/pbxt/KbVQ45hsJ2OSfsMuV7FUWjCodQCIosVO3LofwKHfO7rghXGs/339009%402x.jpg",
      ip_scale: 0.83,
      strength: 1,
      scheduler: "K_EULER",
      lora_scale: 0.3,
      num_outputs: 1,
      guidance_scale: 7.5,
      resizing_scale: 1,
      apply_watermark: true,
      negative_prompt: "",
      background_color: "#A2A2A2",
      num_inference_steps: 30,
      condition_canny_scale: 0.9,
      condition_depth_scale: 0.09
    }
  }
);

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

output = replicate.run(
    "fermatresearch/magic-style-transfer:3b5fa5d360c361090f11164292e45cc5d14cea8d089591d47c580cac9ec1c7ca",
    input={
        "image": "https://replicate.delivery/pbxt/KbVQ4ItrGWdUk9jN7KdNo5nr7h9CxSvJncYIhKtDlpA61nyl/Screenshot%202024-03-20%20at%2019.09.12.png",
        "prompt": "shot in the style of sksfer, words \"MARC AGUILAR\" by Van Gogh, colorful pattern",
        "ip_image": "https://replicate.delivery/pbxt/KbVQ45hsJ2OSfsMuV7FUWjCodQCIosVO3LofwKHfO7rghXGs/339009%402x.jpg",
        "ip_scale": 0.83,
        "strength": 1,
        "scheduler": "K_EULER",
        "lora_scale": 0.3,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "resizing_scale": 1,
        "apply_watermark": True,
        "negative_prompt": "",
        "background_color": "#A2A2A2",
        "num_inference_steps": 30,
        "condition_canny_scale": 0.9,
        "condition_depth_scale": 0.09
    }
)
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-style-transfer 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": "fermatresearch/magic-style-transfer:3b5fa5d360c361090f11164292e45cc5d14cea8d089591d47c580cac9ec1c7ca",
    "input": {
      "image": "https://replicate.delivery/pbxt/KbVQ4ItrGWdUk9jN7KdNo5nr7h9CxSvJncYIhKtDlpA61nyl/Screenshot%202024-03-20%20at%2019.09.12.png",
      "prompt": "shot in the style of sksfer, words \\"MARC AGUILAR\\" by Van Gogh, colorful pattern",
      "ip_image": "https://replicate.delivery/pbxt/KbVQ45hsJ2OSfsMuV7FUWjCodQCIosVO3LofwKHfO7rghXGs/339009%402x.jpg",
      "ip_scale": 0.83,
      "strength": 1,
      "scheduler": "K_EULER",
      "lora_scale": 0.3,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "resizing_scale": 1,
      "apply_watermark": true,
      "negative_prompt": "",
      "background_color": "#A2A2A2",
      "num_inference_steps": 30,
      "condition_canny_scale": 0.9,
      "condition_depth_scale": 0.09
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-20T18:10:35.114254Z",
  "created_at": "2024-03-20T18:10:21.157751Z",
  "data_removed": false,
  "error": null,
  "id": "l362oidbq3lho4epawqurablle",
  "input": {
    "image": "https://replicate.delivery/pbxt/KbVQ4ItrGWdUk9jN7KdNo5nr7h9CxSvJncYIhKtDlpA61nyl/Screenshot%202024-03-20%20at%2019.09.12.png",
    "prompt": "shot in the style of sksfer, words \"MARC AGUILAR\" by Van Gogh, colorful pattern",
    "ip_image": "https://replicate.delivery/pbxt/KbVQ45hsJ2OSfsMuV7FUWjCodQCIosVO3LofwKHfO7rghXGs/339009%402x.jpg",
    "ip_scale": 0.83,
    "strength": 1,
    "scheduler": "K_EULER",
    "lora_scale": 0.3,
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "resizing_scale": 1,
    "apply_watermark": true,
    "negative_prompt": "",
    "background_color": "#A2A2A2",
    "num_inference_steps": 30,
    "condition_canny_scale": 0.9,
    "condition_depth_scale": 0.09
  },
  "logs": "Using seed: 55864\nPrompt: shot in the style of sksfer, words \"MARC AGUILAR\" by Van Gogh, colorful pattern\nOriginal width:1420, height:774\nAspect Ratio: 1.83\nnew_width:1344, new_height:768\nYou have 2 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:09,  2.97it/s]\n  7%|▋         | 2/30 [00:00<00:10,  2.77it/s]\n 10%|█         | 3/30 [00:01<00:10,  2.65it/s]\n 13%|█▎        | 4/30 [00:01<00:09,  2.61it/s]\n 17%|█▋        | 5/30 [00:01<00:09,  2.59it/s]\n 20%|██        | 6/30 [00:02<00:09,  2.57it/s]\n 23%|██▎       | 7/30 [00:02<00:08,  2.56it/s]\n 27%|██▋       | 8/30 [00:03<00:08,  2.55it/s]\n 30%|███       | 9/30 [00:03<00:08,  2.55it/s]\n 33%|███▎      | 10/30 [00:03<00:07,  2.54it/s]\n 37%|███▋      | 11/30 [00:04<00:07,  2.54it/s]\n 40%|████      | 12/30 [00:04<00:07,  2.54it/s]\n 43%|████▎     | 13/30 [00:05<00:06,  2.54it/s]\n 47%|████▋     | 14/30 [00:05<00:06,  2.54it/s]\n 50%|█████     | 15/30 [00:05<00:05,  2.54it/s]\n 53%|█████▎    | 16/30 [00:06<00:05,  2.54it/s]\n 57%|█████▋    | 17/30 [00:06<00:05,  2.54it/s]\n 60%|██████    | 18/30 [00:07<00:04,  2.53it/s]\n 63%|██████▎   | 19/30 [00:07<00:04,  2.53it/s]\n 67%|██████▋   | 20/30 [00:07<00:03,  2.53it/s]\n 70%|███████   | 21/30 [00:08<00:03,  2.53it/s]\n 73%|███████▎  | 22/30 [00:08<00:03,  2.53it/s]\n 77%|███████▋  | 23/30 [00:08<00:02,  2.53it/s]\n 80%|████████  | 24/30 [00:09<00:02,  2.53it/s]\n 83%|████████▎ | 25/30 [00:09<00:01,  2.53it/s]\n 87%|████████▋ | 26/30 [00:10<00:01,  2.53it/s]\n 90%|█████████ | 27/30 [00:10<00:01,  2.53it/s]\n 93%|█████████▎| 28/30 [00:10<00:00,  2.53it/s]\n 97%|█████████▋| 29/30 [00:11<00:00,  2.53it/s]\n100%|██████████| 30/30 [00:11<00:00,  2.52it/s]\n100%|██████████| 30/30 [00:11<00:00,  2.55it/s]",
  "metrics": {
    "predict_time": 13.938835,
    "total_time": 13.956503
  },
  "output": [
    "https://replicate.delivery/pbxt/U8K8kORxUV76CJeWFZSPIu8AX2fPLZreCEzY9VD7Z7J1EbElA/out-0.png"
  ],
  "started_at": "2024-03-20T18:10:21.175419Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/l362oidbq3lho4epawqurablle",
    "cancel": "https://api.replicate.com/v1/predictions/l362oidbq3lho4epawqurablle/cancel"
  },
  "version": "3b5fa5d360c361090f11164292e45cc5d14cea8d089591d47c580cac9ec1c7ca"
}

Generated in

13.9 seconds

Tweak itReport View full prediction

Using seed: 55864
Prompt: shot in the style of sksfer, words "MARC AGUILAR" by Van Gogh, colorful pattern
Original width:1420, height:774
Aspect Ratio: 1.83
new_width:1344, new_height:768
You have 2 ControlNets and you have passed 1 prompts. The conditionings will be fixed across the prompts.
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:09,  2.97it/s]
  7%|▋         | 2/30 [00:00<00:10,  2.77it/s]
 10%|█         | 3/30 [00:01<00:10,  2.65it/s]
 13%|█▎        | 4/30 [00:01<00:09,  2.61it/s]
 17%|█▋        | 5/30 [00:01<00:09,  2.59it/s]
 20%|██        | 6/30 [00:02<00:09,  2.57it/s]
 23%|██▎       | 7/30 [00:02<00:08,  2.56it/s]
 27%|██▋       | 8/30 [00:03<00:08,  2.55it/s]
 30%|███       | 9/30 [00:03<00:08,  2.55it/s]
 33%|███▎      | 10/30 [00:03<00:07,  2.54it/s]
 37%|███▋      | 11/30 [00:04<00:07,  2.54it/s]
 40%|████      | 12/30 [00:04<00:07,  2.54it/s]
 43%|████▎     | 13/30 [00:05<00:06,  2.54it/s]
 47%|████▋     | 14/30 [00:05<00:06,  2.54it/s]
 50%|█████     | 15/30 [00:05<00:05,  2.54it/s]
 53%|█████▎    | 16/30 [00:06<00:05,  2.54it/s]
 57%|█████▋    | 17/30 [00:06<00:05,  2.54it/s]
 60%|██████    | 18/30 [00:07<00:04,  2.53it/s]
 63%|██████▎   | 19/30 [00:07<00:04,  2.53it/s]
 67%|██████▋   | 20/30 [00:07<00:03,  2.53it/s]
 70%|███████   | 21/30 [00:08<00:03,  2.53it/s]
 73%|███████▎  | 22/30 [00:08<00:03,  2.53it/s]
 77%|███████▋  | 23/30 [00:08<00:02,  2.53it/s]
 80%|████████  | 24/30 [00:09<00:02,  2.53it/s]
 83%|████████▎ | 25/30 [00:09<00:01,  2.53it/s]
 87%|████████▋ | 26/30 [00:10<00:01,  2.53it/s]
 90%|█████████ | 27/30 [00:10<00:01,  2.53it/s]
 93%|█████████▎| 28/30 [00:10<00:00,  2.53it/s]
 97%|█████████▋| 29/30 [00:11<00:00,  2.53it/s]
100%|██████████| 30/30 [00:11<00:00,  2.52it/s]
100%|██████████| 30/30 [00:11<00:00,  2.55it/s]