fofr/illusions – Run with an API on Replicate

fofr / illusions

Create illusions with img2img and masking support

Cold

Public
48.1K runs
L40S
GitHub

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Default: "a painting of a 19th century town"

negative_prompt

string

Shift + Return to add a new line

ugly, disfigured, low quality, blurry, nsfwugly, disfigured, low quality, blurry, nsfw

The negative prompt to guide image generation.

Default: "ugly, disfigured, low quality, blurry, nsfw"

num_inference_steps

integer

(minimum: 20, maximum: 100)

Number of diffusion steps

Default: 40

guidance_scale

number

(minimum: 0.1, maximum: 30)

Scale for classifier-free guidance

Default: 7.5

seed

integer

width

integer

Default: 768

height

integer

Default: 768

sizing_strategy

string

Decide how to resize images – use width/height, resize based on input image or control image

Default: "width/height"

num_outputs

integer

(minimum: 1, maximum: 4)

Number of outputs

Default: 1

control_image

file

Preview

Control image

image

file

Preview

Optional img2img

mask_image

file

Optional mask for inpainting

prompt_strength

number

(minimum: 0, maximum: 1)

Prompt strength when using img2img / inpaint. 1.0 corresponds to full destruction of information in image

Default: 0.8

controlnet_conditioning_scale

number

(minimum: 0, maximum: 4)

How strong the controlnet conditioning is

Default: 0.75

controlnet_start

number

(minimum: 0, maximum: 1)

When controlnet conditioning starts

Default: 0

controlnet_end

number

(minimum: 0, maximum: 1)

When controlnet conditioning ends

Default: 1

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

npx create-replicate --model=fofr/illusions

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

const output = await replicate.run(
  "fofr/illusions:579b32db82b24584c3c6155fe3ae12e8fce50ba28b575c23e8a1f5f3a5e99ed8",
  {
    input: {
      seed: -1,
      image: "https://replicate.delivery/pbxt/JouANiZNiW2mwouIgIk1VySvjL9MBmaPD6Ib8HyfW81CJzRR/out-0-44.png",
      width: 768,
      height: 768,
      prompt: "a painting of a 19th century town",
      num_outputs: 1,
      control_image: "https://replicate.delivery/pbxt/JouAO2zaHgb66YVChJagSYz0LcGqv3QgG4BS71mioFbBHWTZ/spiral_black_transparent-2513050263.jpg",
      controlnet_end: 1,
      guidance_scale: 7.5,
      negative_prompt: "ugly, disfigured, low quality, blurry, nsfw",
      prompt_strength: 0.75,
      sizing_strategy: "width/height",
      controlnet_start: 0,
      num_inference_steps: 40,
      controlnet_conditioning_scale: 0.75
    }
  }
);
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 fofr/illusions using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/illusions:579b32db82b24584c3c6155fe3ae12e8fce50ba28b575c23e8a1f5f3a5e99ed8",
    input={
        "seed": -1,
        "image": "https://replicate.delivery/pbxt/JouANiZNiW2mwouIgIk1VySvjL9MBmaPD6Ib8HyfW81CJzRR/out-0-44.png",
        "width": 768,
        "height": 768,
        "prompt": "a painting of a 19th century town",
        "num_outputs": 1,
        "control_image": "https://replicate.delivery/pbxt/JouAO2zaHgb66YVChJagSYz0LcGqv3QgG4BS71mioFbBHWTZ/spiral_black_transparent-2513050263.jpg",
        "controlnet_end": 1,
        "guidance_scale": 7.5,
        "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
        "prompt_strength": 0.75,
        "sizing_strategy": "width/height",
        "controlnet_start": 0,
        "num_inference_steps": 40,
        "controlnet_conditioning_scale": 0.75
    }
)
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 fofr/illusions 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": "579b32db82b24584c3c6155fe3ae12e8fce50ba28b575c23e8a1f5f3a5e99ed8",
    "input": {
      "seed": -1,
      "image": "https://replicate.delivery/pbxt/JouANiZNiW2mwouIgIk1VySvjL9MBmaPD6Ib8HyfW81CJzRR/out-0-44.png",
      "width": 768,
      "height": 768,
      "prompt": "a painting of a 19th century town",
      "num_outputs": 1,
      "control_image": "https://replicate.delivery/pbxt/JouAO2zaHgb66YVChJagSYz0LcGqv3QgG4BS71mioFbBHWTZ/spiral_black_transparent-2513050263.jpg",
      "controlnet_end": 1,
      "guidance_scale": 7.5,
      "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
      "prompt_strength": 0.75,
      "sizing_strategy": "width/height",
      "controlnet_start": 0,
      "num_inference_steps": 40,
      "controlnet_conditioning_scale": 0.75
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-11-28T11:32:46.230072Z",
  "created_at": "2024-11-28T11:32:43.659000Z",
  "data_removed": false,
  "error": null,
  "id": "tjnxcd3t1drm80ckea5t26p0g4",
  "input": {
    "seed": -1,
    "image": "https://replicate.delivery/pbxt/JouANiZNiW2mwouIgIk1VySvjL9MBmaPD6Ib8HyfW81CJzRR/out-0-44.png",
    "width": 768,
    "height": 768,
    "prompt": "a painting of a 19th century town",
    "num_outputs": 1,
    "control_image": "https://replicate.delivery/pbxt/JouAO2zaHgb66YVChJagSYz0LcGqv3QgG4BS71mioFbBHWTZ/spiral_black_transparent-2513050263.jpg",
    "controlnet_end": 1,
    "guidance_scale": 7.5,
    "negative_prompt": "ugly, disfigured, low quality, blurry, nsfw",
    "prompt_strength": 0.75,
    "sizing_strategy": "width/height",
    "controlnet_start": 0,
    "num_inference_steps": 40,
    "controlnet_conditioning_scale": 0.75
  },
  "logs": "Using seed: 3311311052\nimg2img mode\nUsing given dimensions\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:03,  8.15it/s]\n 10%|█         | 3/30 [00:00<00:02, 12.79it/s]\n 17%|█▋        | 5/30 [00:00<00:01, 14.25it/s]\n 23%|██▎       | 7/30 [00:00<00:01, 14.90it/s]\n 30%|███       | 9/30 [00:00<00:01, 15.31it/s]\n 37%|███▋      | 11/30 [00:00<00:01, 15.55it/s]\n 43%|████▎     | 13/30 [00:00<00:01, 15.67it/s]\n 50%|█████     | 15/30 [00:00<00:00, 15.76it/s]\n 57%|█████▋    | 17/30 [00:01<00:00, 15.83it/s]\n 63%|██████▎   | 19/30 [00:01<00:00, 15.86it/s]\n 70%|███████   | 21/30 [00:01<00:00, 15.88it/s]\n 77%|███████▋  | 23/30 [00:01<00:00, 15.89it/s]\n 83%|████████▎ | 25/30 [00:01<00:00, 15.90it/s]\n 90%|█████████ | 27/30 [00:01<00:00, 15.90it/s]\n 97%|█████████▋| 29/30 [00:01<00:00, 15.89it/s]\n100%|██████████| 30/30 [00:01<00:00, 15.45it/s]",
  "metrics": {
    "predict_time": 2.561864317,
    "total_time": 2.571072
  },
  "output": [
    "https://replicate.delivery/xezq/iA3MUV1f533LXqi4sHVlAerJhr03uES9OlBHAHrqaeq92ArnA/output-0.png"
  ],
  "started_at": "2024-11-28T11:32:43.668207Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-trpj5ikdlb3ons6twy3fo36eqpz4ciq4hgdk7xnfwv5kyvwjdqua",
    "get": "https://api.replicate.com/v1/predictions/tjnxcd3t1drm80ckea5t26p0g4",
    "cancel": "https://api.replicate.com/v1/predictions/tjnxcd3t1drm80ckea5t26p0g4/cancel"
  },
  "version": "579b32db82b24584c3c6155fe3ae12e8fce50ba28b575c23e8a1f5f3a5e99ed8"
}

Generated in

2.6 seconds

Tweak it Share Report

Examples

View more examples

Run time and cost

This model costs approximately $0.017 to run on Replicate, or 58 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 18 seconds. The predict time for this model varies significantly based on the inputs.

Readme

An updated version of https://replicate.com/andreasjansson/illusion

This model:

uses Deliberate v2 as a base model for better quality outputs
has img2img support
has inpainting support
has controlnet start and end support
allows resizing based on image or control image
logs seed