Prediction

fofr/latent-consistency-model:92b45676

Model

fofr/latent-consistency-model:92b45676

ID

obmukldbteo4i6lzfulhs47fh4

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

2.5s

Created

about 2 years ago by @fofr

Input

image
width: 768
height: 768
prompt: Self-portrait oil painting, a beautiful cyborg with golden hair, 8k
num_images: 1
guidance_scale: 8
archive_outputs
prompt_strength: 0.45
lcm_origin_steps: 50
num_inference_steps: 4

{
  "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
  "width": 768,
  "height": 768,
  "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
  "num_images": 1,
  "guidance_scale": 8,
  "archive_outputs": false,
  "prompt_strength": 0.45,
  "lcm_origin_steps": 50,
  "num_inference_steps": 4
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
      width: 768,
      height: 768,
      prompt: "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
      num_images: 1,
      guidance_scale: 8,
      archive_outputs: false,
      prompt_strength: 0.45,
      lcm_origin_steps: 50,
      num_inference_steps: 4
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
    input={
        "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
        "width": 768,
        "height": 768,
        "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
        "num_images": 1,
        "guidance_scale": 8,
        "archive_outputs": False,
        "prompt_strength": 0.45,
        "lcm_origin_steps": 50,
        "num_inference_steps": 4
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/latent-consistency-model 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": "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
    "input": {
      "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
      "width": 768,
      "height": 768,
      "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
      "num_images": 1,
      "guidance_scale": 8,
      "archive_outputs": false,
      "prompt_strength": 0.45,
      "lcm_origin_steps": 50,
      "num_inference_steps": 4
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

2.5 seconds

Tweak it Iterate in playground Share Report

Prediction

fofr/latent-consistency-model:92b45676

Model

fofr/latent-consistency-model:92b45676

ID

rso4t4tbtafl3wjtpk7oc6hiie

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

2.4s

Created

about 2 years ago by @fofr

Input

image
width: 768
height: 768
prompt: A landscape painting
num_images: 1
guidance_scale: 8
archive_outputs
prompt_strength: 0.5
lcm_origin_steps: 50
num_inference_steps: 1

{
  "image": "https://replicate.delivery/pbxt/JlG9dpBLCzl4oXNeKInF70UBTZWgK1fxn3Qc1ukoWnpnyCJf/download-1.png",
  "width": 768,
  "height": 768,
  "prompt": "A landscape painting",
  "num_images": 1,
  "guidance_scale": 8,
  "archive_outputs": false,
  "prompt_strength": 0.5,
  "lcm_origin_steps": 50,
  "num_inference_steps": 1
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JlG9dpBLCzl4oXNeKInF70UBTZWgK1fxn3Qc1ukoWnpnyCJf/download-1.png",
      width: 768,
      height: 768,
      prompt: "A landscape painting",
      num_images: 1,
      guidance_scale: 8,
      archive_outputs: false,
      prompt_strength: 0.5,
      lcm_origin_steps: 50,
      num_inference_steps: 1
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
    input={
        "image": "https://replicate.delivery/pbxt/JlG9dpBLCzl4oXNeKInF70UBTZWgK1fxn3Qc1ukoWnpnyCJf/download-1.png",
        "width": 768,
        "height": 768,
        "prompt": "A landscape painting",
        "num_images": 1,
        "guidance_scale": 8,
        "archive_outputs": False,
        "prompt_strength": 0.5,
        "lcm_origin_steps": 50,
        "num_inference_steps": 1
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/latent-consistency-model 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": "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
    "input": {
      "image": "https://replicate.delivery/pbxt/JlG9dpBLCzl4oXNeKInF70UBTZWgK1fxn3Qc1ukoWnpnyCJf/download-1.png",
      "width": 768,
      "height": 768,
      "prompt": "A landscape painting",
      "num_images": 1,
      "guidance_scale": 8,
      "archive_outputs": false,
      "prompt_strength": 0.5,
      "lcm_origin_steps": 50,
      "num_inference_steps": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

2.4 seconds

Tweak it Iterate in playground Share Report

Prediction

fofr/latent-consistency-model:92b45676

Model

fofr/latent-consistency-model:92b45676

ID

pgy5tztbuabr6iufud6xdsefgm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

6.8s

Created

about 2 years ago by @fofr

Input

image
width: 768
height: 768
prompt: detailed
num_images: 4
guidance_scale: 8
archive_outputs
prompt_strength: 0.3
lcm_origin_steps: 50
num_inference_steps: 8

{
  "image": "https://replicate.delivery/pbxt/JlGuQsJACihJI9TmPKfK0n4xaqQNpMkC31R7ffe3yGH4qJb4/out-0-31.png",
  "width": 768,
  "height": 768,
  "prompt": "detailed",
  "num_images": 4,
  "guidance_scale": 8,
  "archive_outputs": false,
  "prompt_strength": 0.3,
  "lcm_origin_steps": 50,
  "num_inference_steps": 8
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JlGuQsJACihJI9TmPKfK0n4xaqQNpMkC31R7ffe3yGH4qJb4/out-0-31.png",
      width: 768,
      height: 768,
      prompt: "detailed",
      num_images: 4,
      guidance_scale: 8,
      archive_outputs: false,
      prompt_strength: 0.3,
      lcm_origin_steps: 50,
      num_inference_steps: 8
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
    input={
        "image": "https://replicate.delivery/pbxt/JlGuQsJACihJI9TmPKfK0n4xaqQNpMkC31R7ffe3yGH4qJb4/out-0-31.png",
        "width": 768,
        "height": 768,
        "prompt": "detailed",
        "num_images": 4,
        "guidance_scale": 8,
        "archive_outputs": False,
        "prompt_strength": 0.3,
        "lcm_origin_steps": 50,
        "num_inference_steps": 8
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/latent-consistency-model 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": "fofr/latent-consistency-model:92b456763bbd035ef9dda7cc778c9cc8628cb4b48b8af813d541e78565342330",
    "input": {
      "image": "https://replicate.delivery/pbxt/JlGuQsJACihJI9TmPKfK0n4xaqQNpMkC31R7ffe3yGH4qJb4/out-0-31.png",
      "width": 768,
      "height": 768,
      "prompt": "detailed",
      "num_images": 4,
      "guidance_scale": 8,
      "archive_outputs": false,
      "prompt_strength": 0.3,
      "lcm_origin_steps": 50,
      "num_inference_steps": 8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

6.9 seconds

Tweak it Iterate in playground Share Report

Prediction

fofr/latent-consistency-model:d6ea4b06

Model

fofr/latent-consistency-model:d6ea4b06

ID

nnhfewdbjde7sphjmzl3k2avmu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

1m 36s

Created

almost 2 years ago by @fofr

Input

width: 768
height: 768
prompt: Self-portrait oil painting, a beautiful cyborg with golden hair, 8k Self-portrait oil painting, a beautiful cyborg with purple hair, 8k Self-portrait oil painting, a beautiful cyborg with ginger hair, 8k Self-portrait oil painting, a beautiful cyborg with green hair, 8k
num_images: 1
guidance_scale: 8
archive_outputs
prompt_strength: 0.45
sizing_strategy: width/height
lcm_origin_steps: 50
canny_low_threshold: 100
num_inference_steps: 4
canny_high_threshold: 200
control_guidance_end: 1
control_guidance_start: 0
controlnet_conditioning_scale: 2

{
  "width": 768,
  "height": 768,
  "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with purple hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with ginger hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with green hair, 8k",
  "num_images": 1,
  "guidance_scale": 8,
  "archive_outputs": false,
  "prompt_strength": 0.45,
  "sizing_strategy": "width/height",
  "lcm_origin_steps": 50,
  "canny_low_threshold": 100,
  "num_inference_steps": 4,
  "canny_high_threshold": 200,
  "control_guidance_end": 1,
  "control_guidance_start": 0,
  "controlnet_conditioning_scale": 2
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "fofr/latent-consistency-model:d6ea4b0610c9121f3dd0fcbb1d47eb1b10f8d944b6ce4ac3d8aadcec9695dd53",
  {
    input: {
      width: 768,
      height: 768,
      prompt: "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with purple hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with ginger hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with green hair, 8k",
      num_images: 1,
      guidance_scale: 8,
      archive_outputs: false,
      prompt_strength: 0.45,
      sizing_strategy: "width/height",
      lcm_origin_steps: 50,
      canny_low_threshold: 100,
      num_inference_steps: 4,
      canny_high_threshold: 200,
      control_guidance_end: 1,
      control_guidance_start: 0,
      controlnet_conditioning_scale: 2
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "fofr/latent-consistency-model:d6ea4b0610c9121f3dd0fcbb1d47eb1b10f8d944b6ce4ac3d8aadcec9695dd53",
    input={
        "width": 768,
        "height": 768,
        "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with purple hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with ginger hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with green hair, 8k",
        "num_images": 1,
        "guidance_scale": 8,
        "archive_outputs": False,
        "prompt_strength": 0.45,
        "sizing_strategy": "width/height",
        "lcm_origin_steps": 50,
        "canny_low_threshold": 100,
        "num_inference_steps": 4,
        "canny_high_threshold": 200,
        "control_guidance_end": 1,
        "control_guidance_start": 0,
        "controlnet_conditioning_scale": 2
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/latent-consistency-model 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": "fofr/latent-consistency-model:d6ea4b0610c9121f3dd0fcbb1d47eb1b10f8d944b6ce4ac3d8aadcec9695dd53",
    "input": {
      "width": 768,
      "height": 768,
      "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k\\nSelf-portrait oil painting, a beautiful cyborg with purple hair, 8k\\nSelf-portrait oil painting, a beautiful cyborg with ginger hair, 8k\\nSelf-portrait oil painting, a beautiful cyborg with green hair, 8k",
      "num_images": 1,
      "guidance_scale": 8,
      "archive_outputs": false,
      "prompt_strength": 0.45,
      "sizing_strategy": "width/height",
      "lcm_origin_steps": 50,
      "canny_low_threshold": 100,
      "num_inference_steps": 4,
      "canny_high_threshold": 200,
      "control_guidance_end": 1,
      "control_guidance_start": 0,
      "controlnet_conditioning_scale": 2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-11-16T10:45:02.316006Z",
  "created_at": "2023-11-16T10:43:26.640869Z",
  "data_removed": false,
  "error": null,
  "id": "nnhfewdbjde7sphjmzl3k2avmu",
  "input": {
    "width": 768,
    "height": 768,
    "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with purple hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with ginger hair, 8k\nSelf-portrait oil painting, a beautiful cyborg with green hair, 8k",
    "num_images": 1,
    "guidance_scale": 8,
    "archive_outputs": false,
    "prompt_strength": 0.45,
    "sizing_strategy": "width/height",
    "lcm_origin_steps": 50,
    "canny_low_threshold": 100,
    "num_inference_steps": 4,
    "canny_high_threshold": 200,
    "control_guidance_end": 1,
    "control_guidance_start": 0,
    "controlnet_conditioning_scale": 2
  },
  "logs": "Using seed: 32287\nFound 4 prompts:\n- Self-portrait oil painting, a beautiful cyborg with golden hair, 8k\n- Self-portrait oil painting, a beautiful cyborg with purple hair, 8k\n- Self-portrait oil painting, a beautiful cyborg with ginger hair, 8k\n- Self-portrait oil painting, a beautiful cyborg with green hair, 8k\nMaking 4 images\ntxt2img mode\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.52it/s]\n 50%|█████     | 2/4 [00:00<00:00,  4.37it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  4.73it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.92it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.67it/s]",
  "metrics": {
    "predict_time": 5.59005,
    "total_time": 95.675137
  },
  "output": [
    "https://replicate.delivery/pbxt/eTbeue6ymKb3YIkWA48CfvePUfjK6W7GPucK7YTIeNs0VJd8IA/out-0.png",
    "https://replicate.delivery/pbxt/DsOPJafrjt24L65eY3yAFq8rLiaNE8UCscqaznqTLthsS64RA/out-1.png",
    "https://replicate.delivery/pbxt/kB9ELGAmN8YfXqtNHtjB7lpdohOh2kGZj7tA743fBQutS64RA/out-2.png",
    "https://replicate.delivery/pbxt/iffO9dQXPphT9kp6zhS1yFIDiFp0rNMyR37ygXsJuNjtS64RA/out-3.png"
  ],
  "started_at": "2023-11-16T10:44:56.725956Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/nnhfewdbjde7sphjmzl3k2avmu",
    "cancel": "https://api.replicate.com/v1/predictions/nnhfewdbjde7sphjmzl3k2avmu/cancel"
  },
  "version": "d6ea4b0610c9121f3dd0fcbb1d47eb1b10f8d944b6ce4ac3d8aadcec9695dd53"
}

Generated in

5.6 seconds

Tweak it Iterate in playground Share Report

Prediction

fofr/latent-consistency-model:fd0f0275

Model

fofr/latent-consistency-model:fd0f0275

ID

gzba3qzb6emol5pofnorirzxoe

Status

Succeeded

Source

Web

Hardware

A100 (40GB)

Total duration

1.0s

Created

almost 2 years ago by @fofr

Input

image
width: 768
height: 768
prompt: Self-portrait oil painting, a beautiful cyborg with golden hair, 8k
num_images: 1
guidance_scale: 8
archive_outputs
prompt_strength: 0.45
sizing_strategy: width/height
lcm_origin_steps: 50
canny_low_threshold: 100
num_inference_steps: 4
canny_high_threshold: 200
control_guidance_end: 1
control_guidance_start: 0
controlnet_conditioning_scale: 2

{
  "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
  "width": 768,
  "height": 768,
  "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
  "num_images": 1,
  "guidance_scale": 8,
  "archive_outputs": false,
  "prompt_strength": 0.45,
  "sizing_strategy": "width/height",
  "lcm_origin_steps": 50,
  "canny_low_threshold": 100,
  "num_inference_steps": 4,
  "canny_high_threshold": 200,
  "control_guidance_end": 1,
  "control_guidance_start": 0,
  "controlnet_conditioning_scale": 2
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "fofr/latent-consistency-model:fd0f02756ae5c3244cfb45c0603296e7418c07d1501bc6e9463ea2d215d5e38f",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
      width: 768,
      height: 768,
      prompt: "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
      num_images: 1,
      guidance_scale: 8,
      archive_outputs: false,
      prompt_strength: 0.45,
      sizing_strategy: "width/height",
      lcm_origin_steps: 50,
      canny_low_threshold: 100,
      num_inference_steps: 4,
      canny_high_threshold: 200,
      control_guidance_end: 1,
      control_guidance_start: 0,
      controlnet_conditioning_scale: 2
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "fofr/latent-consistency-model:fd0f02756ae5c3244cfb45c0603296e7418c07d1501bc6e9463ea2d215d5e38f",
    input={
        "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
        "width": 768,
        "height": 768,
        "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
        "num_images": 1,
        "guidance_scale": 8,
        "archive_outputs": False,
        "prompt_strength": 0.45,
        "sizing_strategy": "width/height",
        "lcm_origin_steps": 50,
        "canny_low_threshold": 100,
        "num_inference_steps": 4,
        "canny_high_threshold": 200,
        "control_guidance_end": 1,
        "control_guidance_start": 0,
        "controlnet_conditioning_scale": 2
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/latent-consistency-model 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": "fofr/latent-consistency-model:fd0f02756ae5c3244cfb45c0603296e7418c07d1501bc6e9463ea2d215d5e38f",
    "input": {
      "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
      "width": 768,
      "height": 768,
      "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
      "num_images": 1,
      "guidance_scale": 8,
      "archive_outputs": false,
      "prompt_strength": 0.45,
      "sizing_strategy": "width/height",
      "lcm_origin_steps": 50,
      "canny_low_threshold": 100,
      "num_inference_steps": 4,
      "canny_high_threshold": 200,
      "control_guidance_end": 1,
      "control_guidance_start": 0,
      "controlnet_conditioning_scale": 2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

1.0 second

Tweak it Iterate in playground Share Report

Prediction

fofr/latent-consistency-model:fd0f0275

Model

fofr/latent-consistency-model:fd0f0275

ID

uzzsxzjb2sus5xl5jqnxpjlyoq

Status

Succeeded

Source

Web

Hardware

A100 (40GB)

Total duration

1.3s

Created

almost 2 years ago by @fofr

Input

image
width: 768
height: 768
prompt: Self-portrait oil painting, a beautiful cyborg with golden hair, 8k
num_images: 1
guidance_scale: 8
archive_outputs
prompt_strength: 0.45
sizing_strategy: width/height
lcm_origin_steps: 50
canny_low_threshold: 100
num_inference_steps: 4
canny_high_threshold: 200
control_guidance_end: 1
control_guidance_start: 0
controlnet_conditioning_scale: 2

{
  "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
  "width": 768,
  "height": 768,
  "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
  "num_images": 1,
  "guidance_scale": 8,
  "archive_outputs": false,
  "prompt_strength": 0.45,
  "sizing_strategy": "width/height",
  "lcm_origin_steps": 50,
  "canny_low_threshold": 100,
  "num_inference_steps": 4,
  "canny_high_threshold": 200,
  "control_guidance_end": 1,
  "control_guidance_start": 0,
  "controlnet_conditioning_scale": 2
}

Install Replicate’s Node.js client library:

npm install replicate

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

const output = await replicate.run(
  "fofr/latent-consistency-model:fd0f02756ae5c3244cfb45c0603296e7418c07d1501bc6e9463ea2d215d5e38f",
  {
    input: {
      image: "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
      width: 768,
      height: 768,
      prompt: "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
      num_images: 1,
      guidance_scale: 8,
      archive_outputs: false,
      prompt_strength: 0.45,
      sizing_strategy: "width/height",
      lcm_origin_steps: 50,
      canny_low_threshold: 100,
      num_inference_steps: 4,
      canny_high_threshold: 200,
      control_guidance_end: 1,
      control_guidance_start: 0,
      controlnet_conditioning_scale: 2
    }
  }
);

// 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

Import the client:

import replicate

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

output = replicate.run(
    "fofr/latent-consistency-model:fd0f02756ae5c3244cfb45c0603296e7418c07d1501bc6e9463ea2d215d5e38f",
    input={
        "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
        "width": 768,
        "height": 768,
        "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
        "num_images": 1,
        "guidance_scale": 8,
        "archive_outputs": False,
        "prompt_strength": 0.45,
        "sizing_strategy": "width/height",
        "lcm_origin_steps": 50,
        "canny_low_threshold": 100,
        "num_inference_steps": 4,
        "canny_high_threshold": 200,
        "control_guidance_end": 1,
        "control_guidance_start": 0,
        "controlnet_conditioning_scale": 2
    }
)

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

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/latent-consistency-model 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": "fofr/latent-consistency-model:fd0f02756ae5c3244cfb45c0603296e7418c07d1501bc6e9463ea2d215d5e38f",
    "input": {
      "image": "https://replicate.delivery/pbxt/JlG0Efd2ubBp9yGnlOi7I9Se2rXnJSrPFogLf0YieKgjnWN6/download-6.png",
      "width": 768,
      "height": 768,
      "prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
      "num_images": 1,
      "guidance_scale": 8,
      "archive_outputs": false,
      "prompt_strength": 0.45,
      "sizing_strategy": "width/height",
      "lcm_origin_steps": 50,
      "canny_low_threshold": 100,
      "num_inference_steps": 4,
      "canny_high_threshold": 200,
      "control_guidance_end": 1,
      "control_guidance_start": 0,
      "controlnet_conditioning_scale": 2
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

0.8 seconds

Tweak it Iterate in playground Share Report

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (obmukldbteo4i6lzfulhs47fh4)

Logs (rso4t4tbtafl3wjtpk7oc6hiie)

Logs (pgy5tztbuabr6iufud6xdsefgm)

Logs (nnhfewdbjde7sphjmzl3k2avmu)

Logs (gzba3qzb6emol5pofnorirzxoe)

Logs (uzzsxzjb2sus5xl5jqnxpjlyoq)