Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

m6thhftbrlrtzcya7y43vl7bom

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.2s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: A photo of the beach in the style of TOK
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "A photo of the beach in the style of TOK",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "A photo of the beach in the style of TOK",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "A photo of the beach in the style of TOK",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A photo of the beach in the style of TOK",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

19.0 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

zoo2rjlbnbrvqlmsfxebskwpku

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.5s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: the beach in the style of TOK
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "the beach in the style of TOK",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "the beach in the style of TOK",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "the beach in the style of TOK",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "the beach in the style of TOK",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

19.0 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

hmwfbclbyavah3wjoxwtdg4jv4

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.4s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: the classroom in the style of TOK
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "the classroom in the style of TOK",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "the classroom in the style of TOK",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "the classroom in the style of TOK",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "the classroom in the style of TOK",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

2wjvkztb6di57onigszucvdr7y

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.8s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: the classroom in the style of TOK
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "the classroom in the style of TOK",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "the classroom in the style of TOK",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "the classroom in the style of TOK",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "the classroom in the style of TOK",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.1 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

xuwd4u3b5aasq5g2mbhhb5zkiq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.0s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: kissing in the style of TOK
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.7
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "kissing in the style of TOK",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.7,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "kissing in the style of TOK",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.7,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "kissing in the style of TOK",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.7,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "kissing in the style of TOK",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.7,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

xceqnv3b3wsjekutoxf2o2dahi

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

20.7s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: kissing in the style of TOK
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.7
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "kissing in the style of TOK",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.7,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "kissing in the style of TOK",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.7,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "kissing in the style of TOK",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.7,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "kissing in the style of TOK",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.7,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

19.1 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

qaype7lbbk2ownlhieg6mcoxbm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.6s

Created

about 2 years ago

Input

width: 1024
height: 1024
prompt: two men kissing in the locker room, in the style of TOK
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.7
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "two men kissing in the locker room, in the style of TOK",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.7,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "two men kissing in the locker room, in the style of TOK",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.7,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "two men kissing in the locker room, in the style of TOK",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.7,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "two men kissing in the locker room, in the style of TOK",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.7,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

19.0 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

qzoqn53bbdd35jncqoggjofudm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.4s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, kissing in the locker room,
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw, three men
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, kissing in the locker room, ",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, kissing in the locker room, ",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw, three men",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, kissing in the locker room, ",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, kissing in the locker room, ",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.1 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

xzirwadbxpqov25wfjfnzlej7q

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.7s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, kissing in the locker room,
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw, three men
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, kissing in the locker room, ",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, kissing in the locker room, ",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw, three men",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, kissing in the locker room, ",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, kissing in the locker room, ",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.1 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

nnmhltdbwtlvgyqd2e3vdyps3y

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.2s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, bar
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw, three men
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, bar",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, bar",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw, three men",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, bar",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, bar",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw, three men",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

ve7pkotb3lt57r5svb5ebywuta

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.5s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, restaurant, people, crowd
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, restaurant, people, crowd",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, restaurant, people, crowd",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, restaurant, people, crowd",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, restaurant, people, crowd",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

5zr4ds3bvl2mpdxarzvnpb43im

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.1s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, restaurant, people, crowd
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, restaurant, people, crowd",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, restaurant, people, crowd",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, restaurant, people, crowd",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, restaurant, people, crowd",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

qus3a4tbcdnmiiktytb4qskbvm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.3s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, train, people, crowd
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, train, people, crowd",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, train, people, crowd",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, train, people, crowd",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, train, people, crowd",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

19.0 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

3wa4tulbgk6bmwk5iefwkahbyu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.4s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, train, people, crowd
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, train, people, crowd",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, train, people, crowd",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, train, people, crowd",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, train, people, crowd",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

19.0 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

53kxtldb6lhmlvc6y7mgdan6xq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.4s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, living room, people, party
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, living room, people, party",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, living room, people, party",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, living room, people, party",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, living room, people, party",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

zne3sa3b5ddagmj7eahznqvn7a

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.8s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, living room, people, party
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, living room, people, party",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, living room, people, party",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, living room, people, party",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, living room, people, party",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

bqqcbylbqmnqlv3acc26uo7rii

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.3s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, living room, people, party, muscular
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, living room, people, party, muscular",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, living room, people, party, muscular",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, living room, people, party, muscular",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, living room, people, party, muscular",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.9 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

7ftuqpdbfjk6ewnc4ytypuaw7e

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.5s

Created

about 2 years ago

Input

width: 1024
height: 1024
prompt: in the style of TOK, class room, people, party, muscular
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 0.56
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, class room, people, party, muscular",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 0.56,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, class room, people, party, muscular",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 0.56,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, class room, people, party, muscular",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 0.56,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, class room, people, party, muscular",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 0.56,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.1 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

mob66gtbigtlbpx6t5gzjekd5y

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.7s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, man in wrestling singlet
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw, signature, three men, four men
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, man in wrestling singlet",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, man in wrestling singlet",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw, signature, three men, four men",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, man in wrestling singlet",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, man in wrestling singlet",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.1 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

beebjodbi4xg2kwr74cio7husm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.9s

Created

about 2 years ago

Input

width: 1024
height: 1024
prompt: in the style of TOK, two men in wrestling singlet hug each other by the docks, perfect eyes, perfect hands, perfect feet, handsome face
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, two men in wrestling singlet hug each other by the docks, perfect eyes, perfect hands, perfect feet, handsome face",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, two men in wrestling singlet hug each other by the docks, perfect eyes, perfect hands, perfect feet, handsome face",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, two men in wrestling singlet hug each other by the docks, perfect eyes, perfect hands, perfect feet, handsome face",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, two men in wrestling singlet hug each other by the docks, perfect eyes, perfect hands, perfect feet, handsome face",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

li6cjalbyfrppmqxduhxzehxoq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.4s

Created

about 2 years ago

Input

width: 1024
height: 1024
prompt: in the style of TOK, a man gardening, perfect face, perfect eye, perfect hands, big feet, shirtless
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, a man gardening, perfect face, perfect eye, perfect hands, big feet, shirtless",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, a man gardening, perfect face, perfect eye, perfect hands, big feet, shirtless",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, a man gardening, perfect face, perfect eye, perfect hands, big feet, shirtless",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, a man gardening, perfect face, perfect eye, perfect hands, big feet, shirtless",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

r6dozcdb3e5qxbuehaigolrbgm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.2s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, composition of a male figure with chaos
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, composition of a male figure with chaos",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, composition of a male figure with chaos",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, composition of a male figure with chaos",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, composition of a male figure with chaos",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

18.2 seconds

Tweak it Iterate in playground Share Report

Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

ID

afnfscdbeledk4tjlzmmt2mzfm

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

19.7s

Created

about 2 years ago by @gymdreams8

Input

width: 1024
height: 1024
prompt: in the style of TOK, composition of a man with chaos, imaginative, surreal, creative, artistic, grit
refine: base_image_refiner
scheduler: KarrasDPM
lora_scale: 1
num_outputs: 1
guidance_scale: 7.5
apply_watermark
high_noise_frac: 0.8
negative_prompt: monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids
prompt_strength: 0.8
num_inference_steps: 50

{
  "width": 1024,
  "height": 1024,
  "prompt": "in the style of TOK, composition of a man with chaos, imaginative, surreal, creative, artistic, grit",
  "refine": "base_image_refiner",
  "scheduler": "KarrasDPM",
  "lora_scale": 1,
  "num_outputs": 1,
  "guidance_scale": 7.5,
  "apply_watermark": false,
  "high_noise_frac": 0.8,
  "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "in the style of TOK, composition of a man with chaos, imaginative, surreal, creative, artistic, grit",
      refine: "base_image_refiner",
      scheduler: "KarrasDPM",
      lora_scale: 1,
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: false,
      high_noise_frac: 0.8,
      negative_prompt: "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);

// 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 gymdreams8/gdmjp4 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "in the style of TOK, composition of a man with chaos, imaginative, surreal, creative, artistic, grit",
        "refine": "base_image_refiner",
        "scheduler": "KarrasDPM",
        "lora_scale": 1,
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": False,
        "high_noise_frac": 0.8,
        "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# 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 gymdreams8/gdmjp4 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": "gymdreams8/gdmjp4:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, composition of a man with chaos, imaginative, surreal, creative, artistic, grit",
      "refine": "base_image_refiner",
      "scheduler": "KarrasDPM",
      "lora_scale": 1,
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": false,
      "high_noise_frac": 0.8,
      "negative_prompt": "monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

Generated in

19.0 seconds

Tweak it Iterate in playground Share Report