dribnet/pixray-genesis – Run with an API on Replicate

Input

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

npx create-replicate --model=dribnet/pixray-genesis

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 dribnet/pixray-genesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "dribnet/pixray-genesis:2556070ce036747c9faf76b9c2c388046348f8d50cf33ba825e0eb7f62ff37ff",
  {
    input: {
      title: "gradients",
      quality: "draft",
      optional_settings: "\n"
    }
  }
);

// 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

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 dribnet/pixray-genesis using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "dribnet/pixray-genesis:2556070ce036747c9faf76b9c2c388046348f8d50cf33ba825e0eb7f62ff37ff",
    input={
        "title": "gradients",
        "quality": "draft",
        "optional_settings": "\n"
    }
)

# The dribnet/pixray-genesis 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/dribnet/pixray-genesis/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 dribnet/pixray-genesis 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": "dribnet/pixray-genesis:2556070ce036747c9faf76b9c2c388046348f8d50cf33ba825e0eb7f62ff37ff",
    "input": {
      "title": "gradients",
      "quality": "draft",
      "optional_settings": "\\n"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2021-11-02T02:50:25.757826Z",
  "created_at": "2021-11-02T02:49:28.628053Z",
  "data_removed": false,
  "error": null,
  "id": "swsda6i43zevhk3zca75bstrwa",
  "input": {
    "title": "gradients",
    "quality": "draft",
    "optional_settings": "\n"
  },
  "logs": "---> Pixray Genesis Init\nUsing seed:\n5563025599011693809\nWorking with z of shape (1, 256, 16, 16) = 65536 dimensions.\nloaded pretrained LPIPS loss from taming/modules/autoencoder/lpips/vgg.pth\nVQLPIPSWithDiscriminator running with hinge loss.\nRestored from models/vqgan_imagenet_f16_16384.ckpt\nUsing device:\ncuda:0\nOptimising using:\nAdam\nUsing text prompts:\n['gradients']\n\n0it [00:00, ?it/s]\n/root/.pyenv/versions/3.8.12/lib/python3.8/site-packages/torch/nn/functional.py:3609: UserWarning: Default upsampling behavior when mode=bilinear is changed to align_corners=False since 0.4.0. Please specify align_corners=True if the old behavior is desired. See the documentation of nn.Upsample for details.\n  warnings.warn(\niter: 0, loss: 0.906, losses: 0.86, 0.0459 (-0=>0.9061)\n\n0it [00:00, ?it/s]\niter: 10, loss: 0.859, losses: 0.815, 0.0443 (-1=>0.8542)\n\n0it [00:04, ?it/s]\n\n0it [00:08, ?it/s]\n\n0it [00:00, ?it/s]\niter: 20, loss: 0.84, losses: 0.795, 0.0444 (-3=>0.8383)\n\n0it [00:00, ?it/s]\niter: 30, loss: 0.831, losses: 0.787, 0.044 (-1=>0.8276)\n\n0it [00:05, ?it/s]\n\n0it [00:08, ?it/s]\n\n0it [00:00, ?it/s]\niter: 40, loss: 0.821, losses: 0.777, 0.0439 (-0=>0.8214)\n\n0it [00:00, ?it/s]\niter: 50, loss: 0.817, losses: 0.774, 0.0434 (-1=>0.8086)\n\n0it [00:05, ?it/s]\n\n0it [00:08, ?it/s]\n\n0it [00:00, ?it/s]\niter: 60, loss: 0.806, losses: 0.762, 0.0437 (-5=>0.804)\n\n0it [00:00, ?it/s]\niter: 70, loss: 0.807, losses: 0.763, 0.044 (-1=>0.7982)\n\n0it [00:05, ?it/s]\nDropping learning rate\n\n0it [00:09, ?it/s]\n\n0it [00:00, ?it/s]\niter: 80, loss: 0.802, losses: 0.757, 0.0446 (-3=>0.7963)\n\n0it [00:00, ?it/s]\niter: 90, loss: 0.8, losses: 0.756, 0.0443 (-13=>0.7963)\n\n0it [00:05, ?it/s]\n\n0it [00:09, ?it/s]\n\n0it [00:00, ?it/s]\niter: 100, finished (-1=>0.7956)\n\n0it [00:00, ?it/s]\n\n0it [00:00, ?it/s]",
  "metrics": {
    "total_time": 57.129773
  },
  "output": [
    {
      "file": "https://replicate.delivery/mgxm/fd99bff6-e0b9-4e27-b8c7-52bb3dfce43d/tempfile.png"
    },
    {
      "file": "https://replicate.delivery/mgxm/da12d566-529d-46a2-82c0-680984fe522d/tempfile.png"
    },
    {
      "file": "https://replicate.delivery/mgxm/42333e12-1c95-4348-b685-17d51ee553f4/tempfile.png"
    },
    {
      "file": "https://replicate.delivery/mgxm/c6d39d49-2291-479b-98a3-f39e9b02c39d/tempfile.png"
    }
  ],
  "started_at": "2021-11-30T11:01:25.573479Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/swsda6i43zevhk3zca75bstrwa",
    "cancel": "https://api.replicate.com/v1/predictions/swsda6i43zevhk3zca75bstrwa/cancel"
  },
  "version": "2027157f7e0661133093a4dacda67607e5fe49647718300fe6403fe1960748e3"
}

Tweak itReport

This output was created using a different version of the model, dribnet/pixray-genesis:2027157f.

Run time and cost

This model costs approximately $0.053 to run on Replicate, or 18 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 T4 GPU hardware. Predictions typically complete within 4 minutes. The predict time for this model varies significantly based on the inputs.