prompthero/openjourney – Run with an API on Replicate

Input

image

file

Optional Image to use for img2img guidance

mask

file

Optional Mask to use for legacy inpainting

prompt

string

Shift + Return to add a new line

mdjrny-v4 style portrait of female elf, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha, 8kmdjrny-v4 style portrait of female elf, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha, 8k

Input prompt

Default: "a photo of an astronaut riding a horse on mars"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

num_outputs

integer

(minimum: 1, maximum: 10)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

prompt_strength

number

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

scheduler

string

Choose a scheduler.

Default: "DPMSolverMultistep"

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=prompthero/openjourney

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

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

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

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

const output = await replicate.run(
  "prompthero/openjourney:ad59ca21177f9e217b9075e7300cf6e14f7e5b4505b87b9689dbd866e9768969",
  {
    input: {
      seed: null,
      width: 512,
      height: 512,
      prompt: "mdjrny-v4 style portrait of female elf, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha, 8k",
      scheduler: "DPMSolverMultistep",
      num_outputs: 1,
      guidance_scale: 7,
      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 prompthero/openjourney using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "prompthero/openjourney:ad59ca21177f9e217b9075e7300cf6e14f7e5b4505b87b9689dbd866e9768969",
    input={
        "seed": null,
        "width": 512,
        "height": 512,
        "prompt": "mdjrny-v4 style portrait of female elf, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha, 8k",
        "scheduler": "DPMSolverMultistep",
        "num_outputs": 1,
        "guidance_scale": 7,
        "prompt_strength": 0.8,
        "num_inference_steps": 50
    }
)

# The prompthero/openjourney model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/prompthero/openjourney/api#output-schema
    print(item)

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 prompthero/openjourney 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": "ad59ca21177f9e217b9075e7300cf6e14f7e5b4505b87b9689dbd866e9768969",
    "input": {
      "seed": null,
      "width": 512,
      "height": 512,
      "prompt": "mdjrny-v4 style portrait of female elf, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha, 8k",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 7,
      "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/prompthero/openjourney@sha256:ad59ca21177f9e217b9075e7300cf6e14f7e5b4505b87b9689dbd866e9768969 \
  -i 'seed=null' \
  -i 'width=512' \
  -i 'height=512' \
  -i 'prompt="mdjrny-v4 style portrait of female elf, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha, 8k"' \
  -i 'scheduler="DPMSolverMultistep"' \
  -i 'num_outputs=1' \
  -i 'guidance_scale=7' \
  -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/prompthero/openjourney@sha256:ad59ca21177f9e217b9075e7300cf6e14f7e5b4505b87b9689dbd866e9768969
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": null,
      "width": 512,
      "height": 512,
      "prompt": "mdjrny-v4 style portrait of female elf, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha, 8k",
      "scheduler": "DPMSolverMultistep",
      "num_outputs": 1,
      "guidance_scale": 7,
      "prompt_strength": 0.8,
      "num_inference_steps": 50
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2022-11-15T02:17:31Z",
  "created_at": "2022-11-15T02:17:27.218186Z",
  "data_removed": false,
  "error": "",
  "id": "hnv34qbn5nc2fkhfgxa2nhe5ka",
  "input": {
    "seed": null,
    "width": 512,
    "height": 512,
    "prompt": "mdjrny-v4 style portrait of female elf, intricate, elegant, highly detailed, digital painting, artstation, concept art, smooth, sharp focus, illustration, art by artgerm and greg rutkowski and alphonse mucha, 8k",
    "num_outputs": 1,
    "guidance_scale": "7",
    "num_inference_steps": 50
  },
  "logs": "Using seed: 46041\r\nGlobal seed set to 46041\r\n  0%|          | 0/50 [00:00<?, ?it/s]\r\n  4%|▍         | 2/50 [00:00<00:03, 13.23it/s]\r\n  8%|▊         | 4/50 [00:00<00:03, 13.55it/s]\r\n 12%|█▏        | 6/50 [00:00<00:03, 13.93it/s]\r\n 16%|█▌        | 8/50 [00:00<00:02, 14.09it/s]\r\n 20%|██        | 10/50 [00:00<00:02, 14.08it/s]\r\n 24%|██▍       | 12/50 [00:00<00:02, 13.94it/s]\r\n 28%|██▊       | 14/50 [00:01<00:02, 14.03it/s]\r\n 32%|███▏      | 16/50 [00:01<00:02, 14.05it/s]\r\n 36%|███▌      | 18/50 [00:01<00:02, 14.11it/s]\r\n 40%|████      | 20/50 [00:01<00:02, 14.17it/s]\r\n 44%|████▍     | 22/50 [00:01<00:01, 14.22it/s]\r\n 48%|████▊     | 24/50 [00:01<00:01, 14.27it/s]\r\n 52%|█████▏    | 26/50 [00:01<00:01, 14.30it/s]\r\n 56%|█████▌    | 28/50 [00:01<00:01, 14.32it/s]\r\n 60%|██████    | 30/50 [00:02<00:01, 14.31it/s]\r\n 64%|██████▍   | 32/50 [00:02<00:01, 14.30it/s]\r\n 68%|██████▊   | 34/50 [00:02<00:01, 14.29it/s]\r\n 72%|███████▏  | 36/50 [00:02<00:00, 14.29it/s]\r\n 76%|███████▌  | 38/50 [00:02<00:00, 14.33it/s]\r\n 80%|████████  | 40/50 [00:02<00:00, 14.04it/s]\r\n 84%|████████▍ | 42/50 [00:02<00:00, 14.09it/s]\r\n 88%|████████▊ | 44/50 [00:03<00:00, 14.15it/s]\r\n 92%|█████████▏| 46/50 [00:03<00:00, 14.20it/s]\r\n 96%|█████████▌| 48/50 [00:03<00:00, 14.18it/s]\r\n100%|██████████| 50/50 [00:03<00:00, 14.18it/s]\r\n100%|██████████| 50/50 [00:03<00:00, 14.15it/s]",
  "metrics": {
    "predict_time": 4,
    "total_time": 3.781814
  },
  "output": [
    "https://replicate.delivery/pbxt/LHh12rAtngYkItdmraLbWntEODUjeCI4g9wn9pXfiMO7iKAQA/out-0.png"
  ],
  "started_at": "2022-11-15T02:17:27Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/hnv34qbn5nc2fkhfgxa2nhe5ka",
    "cancel": "https://api.replicate.com/v1/predictions/hnv34qbn5nc2fkhfgxa2nhe5ka/cancel"
  },
  "version": "9936c2001faa2194a261c01381f90e65261879985476014a0a37a334593a05eb"
}

Generated in

4.0 seconds

Tweak itReport

This example was created by a different version, prompthero/openjourney:9936c200.

Run time and cost

This model costs approximately $0.0034 to run on Replicate, or 294 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 3 seconds.