pwntus/material-diffusion-sdxl – Run with an API on Replicate

Input

prompt

string

Shift + Return to add a new line

Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4kMossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k

Input prompt

Default: "grass"

negative_prompt

string

Shift + Return to add a new line

Input Negative Prompt

Default: ""

width

integer

Width of output image.

Default: 768

height

integer

Height of output image.

Default: 768

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

scheduler

string

scheduler

Default: "DDIM"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 7.5

seed

integer

Random seed. Leave blank to randomize the seed

refine

string

Which refine style to use

Default: "no_refiner"

high_noise_frac

number

(minimum: 0, maximum: 1)

for expert_ensemble_refiner, the fraction of noise to use

Default: 0.8

refine_steps

integer

for base_image_refiner, the number of steps to refine, defaults to num_inference_steps

apply_watermark

boolean

Applies a watermark to enable determining if an image is generated in downstream applications. If you have other provisions for generating or deploying images safely, you can use this to disable watermarking.

Default: true

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

npx create-replicate --model=pwntus/material-diffusion-sdxl

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 pwntus/material-diffusion-sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "pwntus/material-diffusion-sdxl:ce888cbe17a7c04d4b9c4cbd2b576715d480c55b2ba8f9f3d33f2ad70a26cd99",
  {
    input: {
      width: 768,
      height: 768,
      prompt: "Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k",
      refine: "expert_ensemble_refiner",
      scheduler: "DDIM",
      num_outputs: 1,
      guidance_scale: 7.5,
      apply_watermark: true,
      high_noise_frac: 0.8,
      negative_prompt: "",
      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

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 pwntus/material-diffusion-sdxl using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "pwntus/material-diffusion-sdxl:ce888cbe17a7c04d4b9c4cbd2b576715d480c55b2ba8f9f3d33f2ad70a26cd99",
    input={
        "width": 768,
        "height": 768,
        "prompt": "Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k",
        "refine": "expert_ensemble_refiner",
        "scheduler": "DDIM",
        "num_outputs": 1,
        "guidance_scale": 7.5,
        "apply_watermark": True,
        "high_noise_frac": 0.8,
        "negative_prompt": "",
        "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 pwntus/material-diffusion-sdxl 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": "pwntus/material-diffusion-sdxl:ce888cbe17a7c04d4b9c4cbd2b576715d480c55b2ba8f9f3d33f2ad70a26cd99",
    "input": {
      "width": 768,
      "height": 768,
      "prompt": "Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k",
      "refine": "expert_ensemble_refiner",
      "scheduler": "DDIM",
      "num_outputs": 1,
      "guidance_scale": 7.5,
      "apply_watermark": true,
      "high_noise_frac": 0.8,
      "negative_prompt": "",
      "num_inference_steps": 50
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2023-08-07T18:13:07.429490Z",
  "created_at": "2023-08-07T18:13:02.314225Z",
  "data_removed": false,
  "error": null,
  "id": "ryowfydbtgzz3bxsqnpvfjuhli",
  "input": {
    "width": 768,
    "height": 768,
    "prompt": "Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k",
    "refine": "expert_ensemble_refiner",
    "scheduler": "DDIM",
    "num_outputs": 1,
    "guidance_scale": 7.5,
    "apply_watermark": true,
    "high_noise_frac": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 21776\nPrompt: Mossy Runic Bricks seamless texture, trending on artstation, stone, moss, base color, albedo, 4k\ntxt2img mode\n  0%|          | 0/40 [00:00<?, ?it/s]\n  5%|▌         | 2/40 [00:00<00:02, 14.41it/s]\n 10%|█         | 4/40 [00:00<00:02, 14.42it/s]\n 15%|█▌        | 6/40 [00:00<00:02, 14.43it/s]\n 20%|██        | 8/40 [00:00<00:02, 14.42it/s]\n 25%|██▌       | 10/40 [00:00<00:02, 14.41it/s]\n 30%|███       | 12/40 [00:00<00:01, 14.42it/s]\n 35%|███▌      | 14/40 [00:00<00:01, 14.42it/s]\n 40%|████      | 16/40 [00:01<00:01, 14.43it/s]\n 45%|████▌     | 18/40 [00:01<00:01, 14.43it/s]\n 50%|█████     | 20/40 [00:01<00:01, 14.42it/s]\n 55%|█████▌    | 22/40 [00:01<00:01, 14.42it/s]\n 60%|██████    | 24/40 [00:01<00:01, 14.43it/s]\n 65%|██████▌   | 26/40 [00:01<00:00, 14.42it/s]\n 70%|███████   | 28/40 [00:01<00:00, 14.41it/s]\n 75%|███████▌  | 30/40 [00:02<00:00, 14.42it/s]\n 80%|████████  | 32/40 [00:02<00:00, 14.43it/s]\n 85%|████████▌ | 34/40 [00:02<00:00, 14.43it/s]\n 90%|█████████ | 36/40 [00:02<00:00, 14.44it/s]\n 95%|█████████▌| 38/40 [00:02<00:00, 14.43it/s]\n100%|██████████| 40/40 [00:02<00:00, 14.43it/s]\n100%|██████████| 40/40 [00:02<00:00, 14.42it/s]\n  0%|          | 0/10 [00:00<?, ?it/s]\n 10%|█         | 1/10 [00:00<00:01,  8.16it/s]\n 30%|███       | 3/10 [00:00<00:00, 12.29it/s]\n 50%|█████     | 5/10 [00:00<00:00, 13.45it/s]\n 70%|███████   | 7/10 [00:00<00:00, 13.99it/s]\n 90%|█████████ | 9/10 [00:00<00:00, 14.28it/s]\n100%|██████████| 10/10 [00:00<00:00, 13.70it/s]",
  "metrics": {
    "predict_time": 5.136958,
    "total_time": 5.115265
  },
  "output": [
    "https://replicate.delivery/pbxt/7gJ7y5PLGEbed6g44CD624HjmMdXDjK0MUloxlT9fKcyYuXRA/out-0.png"
  ],
  "started_at": "2023-08-07T18:13:02.292532Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/ryowfydbtgzz3bxsqnpvfjuhli",
    "cancel": "https://api.replicate.com/v1/predictions/ryowfydbtgzz3bxsqnpvfjuhli/cancel"
  },
  "version": "ce888cbe17a7c04d4b9c4cbd2b576715d480c55b2ba8f9f3d33f2ad70a26cd99"
}

Generated in

5.1 seconds

Tweak itReport

Run time and cost

This model costs approximately $0.011 to run on Replicate, or 90 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 9 seconds. The predict time for this model varies significantly based on the inputs.