Prediction

gymdreams8/gdmjp4:396f5235

Model

gymdreams8/gdmjp4:396f5235

npwprgtbhfpr54qa3mt4l4kjnq

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.6s

Created

over 1 year 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, dancing, birth of a star, perfect eyes, perfect face, big feet, bare feet, big hands, 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, 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, dancing, birth of a star, perfect eyes, perfect face, big feet, bare feet, big hands, 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, children, kids",
  "prompt_strength": 0.8,
  "num_inference_steps": 50
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run 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, dancing, birth of a star, perfect eyes, perfect face, big feet, bare feet, big hands, 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, children, kids",
      prompt_strength: 0.8,
      num_inference_steps: 50
    }
  }
);
console.log(output);

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

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run 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, dancing, birth of a star, perfect eyes, perfect face, big feet, bare feet, big hands, 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, children, kids",
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)
print(output)

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

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run 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": "396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, composition of a man with chaos, imaginative, surreal, creative, artistic, grit, dancing, birth of a star, perfect eyes, perfect face, big feet, bare feet, big hands, 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, 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.

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/gymdreams8/gdmjp4@sha256:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2 \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="in the style of TOK, composition of a man with chaos, imaginative, surreal, creative, artistic, grit, dancing, birth of a star, perfect eyes, perfect face, big feet, bare feet, big hands, handsome face"' \
  -i 'refine="base_image_refiner"' \
  -i 'scheduler="KarrasDPM"' \
  -i 'lora_scale=1' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7.5' \
  -i 'apply_watermark=false' \
  -i 'high_noise_frac=0.8' \
  -i 'negative_prompt="monochrome, black and white, over saturation, nsfw, signature, three men, four men, too many hands, children, kids"' \
  -i 'prompt_strength=0.8' \
  -i 'num_inference_steps=50'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/gymdreams8/gdmjp4@sha256:396f5235412e4af69d4a5899ebe5c984dc6729590b461054da05bf57ac9d66c2
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "in the style of TOK, composition of a man with chaos, imaginative, surreal, creative, artistic, grit, dancing, birth of a star, perfect eyes, perfect face, big feet, bare feet, big hands, 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, children, kids",
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

Generated in

18.2 seconds

Tweak itReport