prompthero/poolsuite-diffusion – Run with an API on Replicate

prompthero / poolsuite-diffusion

Reproduce Poolsuite vibes with a fine tuned Dreambooth model

Cold

Public
6.1K runs
A100 (80GB)
Paper

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=prompthero/poolsuite-diffusion

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

const output = await replicate.run(
  "prompthero/poolsuite-diffusion:29ee86a70122ac237ce8de9fa552e93e035ebef18dd4cd430774b9452aa5bf91",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "photography of a manor, poolsuite style",
      num_outputs: 1,
      guidance_scale: 7,
      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 prompthero/poolsuite-diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "prompthero/poolsuite-diffusion:29ee86a70122ac237ce8de9fa552e93e035ebef18dd4cd430774b9452aa5bf91",
    input={
        "width": 512,
        "height": 512,
        "prompt": "photography of a manor, poolsuite style",
        "num_outputs": 1,
        "guidance_scale": 7,
        "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 prompthero/poolsuite-diffusion 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": "29ee86a70122ac237ce8de9fa552e93e035ebef18dd4cd430774b9452aa5bf91",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "photography of a manor, poolsuite style",
      "num_outputs": 1,
      "guidance_scale": 7,
      "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": "2022-11-15T22:26:35.549130Z",
  "created_at": "2022-11-15T22:26:31.536167Z",
  "data_removed": false,
  "error": null,
  "id": "zcs6cpl4xzgahnxrxflaayqgr4",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "photography of a manor, poolsuite style",
    "num_outputs": "1",
    "guidance_scale": "7",
    "num_inference_steps": "50"
  },
  "logs": "Using seed: 59959\nGlobal seed set to 59959\n  0%|          | 0/50 [00:00<?, ?it/s]\n  4%|▍         | 2/50 [00:00<00:03, 12.78it/s]\n  8%|▊         | 4/50 [00:00<00:03, 13.58it/s]\n 12%|█▏        | 6/50 [00:00<00:03, 13.94it/s]\n 16%|█▌        | 8/50 [00:00<00:02, 14.13it/s]\n 20%|██        | 10/50 [00:00<00:02, 14.22it/s]\n 24%|██▍       | 12/50 [00:00<00:02, 14.26it/s]\n 28%|██▊       | 14/50 [00:00<00:02, 14.30it/s]\n 32%|███▏      | 16/50 [00:01<00:02, 14.27it/s]\n 36%|███▌      | 18/50 [00:01<00:02, 14.25it/s]\n 40%|████      | 20/50 [00:01<00:02, 14.28it/s]\n 44%|████▍     | 22/50 [00:01<00:01, 14.29it/s]\n 48%|████▊     | 24/50 [00:01<00:01, 14.07it/s]\n 52%|█████▏    | 26/50 [00:01<00:01, 14.14it/s]\n 56%|█████▌    | 28/50 [00:01<00:01, 14.16it/s]\n 60%|██████    | 30/50 [00:02<00:01, 14.20it/s]\n 64%|██████▍   | 32/50 [00:02<00:01, 14.21it/s]\n 68%|██████▊   | 34/50 [00:02<00:01, 14.25it/s]\n 72%|███████▏  | 36/50 [00:02<00:00, 14.27it/s]\n 76%|███████▌  | 38/50 [00:02<00:00, 14.30it/s]\n 80%|████████  | 40/50 [00:02<00:00, 14.33it/s]\n 84%|████████▍ | 42/50 [00:02<00:00, 14.33it/s]\n 88%|████████▊ | 44/50 [00:03<00:00, 14.24it/s]\n 92%|█████████▏| 46/50 [00:03<00:00, 14.22it/s]\n 96%|█████████▌| 48/50 [00:03<00:00, 14.23it/s]\n100%|██████████| 50/50 [00:03<00:00, 14.22it/s]\n100%|██████████| 50/50 [00:03<00:00, 14.19it/s]",
  "metrics": {
    "predict_time": 3.979455,
    "total_time": 4.012963
  },
  "output": [
    "https://replicate.delivery/pbxt/E6hztf2wfEq1DUaIzTnLHl0bS5SJpdFoTlY64wnX6TlbQcAQA/out-0.png"
  ],
  "started_at": "2022-11-15T22:26:31.569675Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zcs6cpl4xzgahnxrxflaayqgr4",
    "cancel": "https://api.replicate.com/v1/predictions/zcs6cpl4xzgahnxrxflaayqgr4/cancel"
  },
  "version": "e1450d9d6feddf74dd03f61ad1be0a002c1a4bef4075d447452f774d7cd79814"
}

Generated in

4.0 seconds

Tweak itReport

This output was created using a different version of the model, prompthero/poolsuite-diffusion:e1450d9d.

Examples

View more examples

Run time and cost

This model costs approximately $0.25 to run on Replicate, or 4 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 minutes. The predict time for this model varies significantly based on the inputs.

Readme

Stable Diffusion fine tuned on Poolsuite images, by PromptHero.

Use prompt: poolsuite style

Sample outputs:

Prompt: “35mm photography of a living room, poolsuite style“

Prompt: “clothing design collection, poolsuite style”

Prompt: “photography of a car poolsuite style”

Click here for more Poolsuite prompts and inspiration.