melgor/stabledesign_interiordesign – Run with an API on Replicate

melgor / stabledesign_interiordesign

Transfer empty room into fabulous interior design

Cold

Public
6.5K runs
L40S
GitHub
Paper
License

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=melgor/stabledesign_interiordesign

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

const output = await replicate.run(
  "melgor/stabledesign_interiordesign:5e13482ea317670bfc797bb18bace359860a721a39b5bbcaa1ffcd241d62bca0",
  {
    input: {
      seed: 35853,
      prompt: "A glamorous master bedroom in Hollywood Regency style, boasting a plush tufted headboard, mirrored furniture reflecting elegance, luxurious fabrics in rich textures, and opulent gold accents for a touch of luxury.",
      img_size: 640,
      strength: 0.9,
      num_steps: 50,
      image_base: "https://replicate.delivery/pbxt/L71nWgMUQvH7zKHG3U9YYdfREv1ybOfO1Q5ntak3YmUJizSR/image_0.jpg",
      guidance_scale: 10
    }
  }
);
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 melgor/stabledesign_interiordesign using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "melgor/stabledesign_interiordesign:5e13482ea317670bfc797bb18bace359860a721a39b5bbcaa1ffcd241d62bca0",
    input={
        "seed": 35853,
        "prompt": "A glamorous master bedroom in Hollywood Regency style, boasting a plush tufted headboard, mirrored furniture reflecting elegance, luxurious fabrics in rich textures, and opulent gold accents for a touch of luxury.",
        "img_size": 640,
        "strength": 0.9,
        "num_steps": 50,
        "image_base": "https://replicate.delivery/pbxt/L71nWgMUQvH7zKHG3U9YYdfREv1ybOfO1Q5ntak3YmUJizSR/image_0.jpg",
        "guidance_scale": 10
    }
)
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 melgor/stabledesign_interiordesign 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": "5e13482ea317670bfc797bb18bace359860a721a39b5bbcaa1ffcd241d62bca0",
    "input": {
      "seed": 35853,
      "prompt": "A glamorous master bedroom in Hollywood Regency style, boasting a plush tufted headboard, mirrored furniture reflecting elegance, luxurious fabrics in rich textures, and opulent gold accents for a touch of luxury.",
      "img_size": 640,
      "strength": 0.9,
      "num_steps": 50,
      "image_base": "https://replicate.delivery/pbxt/L71nWgMUQvH7zKHG3U9YYdfREv1ybOfO1Q5ntak3YmUJizSR/image_0.jpg",
      "guidance_scale": 10
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-06-17T13:37:22.508770Z",
  "created_at": "2024-06-17T13:30:54.561000Z",
  "data_removed": false,
  "error": null,
  "id": "z6b9q5dww5rgp0cg4sj91cnv1r",
  "input": {
    "seed": 35853,
    "prompt": "A glamorous master bedroom in Hollywood Regency style, boasting a plush tufted headboard, mirrored furniture reflecting elegance, luxurious fabrics in rich textures, and opulent gold accents for a touch of luxury.",
    "img_size": 640,
    "strength": 0.9,
    "num_steps": 50,
    "image_base": "https://replicate.delivery/pbxt/L71nWgMUQvH7zKHG3U9YYdfREv1ybOfO1Q5ntak3YmUJizSR/image_0.jpg",
    "guidance_scale": 10
  },
  "logs": "/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)\nreturn F.conv2d(input, weight, bias, self.stride,\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:00<00:07,  6.68it/s]\n  8%|▊         | 4/50 [00:00<00:02, 15.39it/s]\n 14%|█▍        | 7/50 [00:00<00:02, 18.52it/s]\n 20%|██        | 10/50 [00:00<00:02, 19.84it/s]\n 26%|██▌       | 13/50 [00:00<00:01, 20.74it/s]\n 32%|███▏      | 16/50 [00:00<00:01, 21.31it/s]\n 38%|███▊      | 19/50 [00:00<00:01, 21.66it/s]\n 44%|████▍     | 22/50 [00:01<00:01, 21.90it/s]\n 50%|█████     | 25/50 [00:01<00:01, 22.06it/s]\n 56%|█████▌    | 28/50 [00:01<00:00, 22.17it/s]\n 62%|██████▏   | 31/50 [00:01<00:00, 22.22it/s]\n 68%|██████▊   | 34/50 [00:01<00:00, 22.03it/s]\n 74%|███████▍  | 37/50 [00:01<00:00, 22.10it/s]\n 80%|████████  | 40/50 [00:01<00:00, 22.11it/s]\n 86%|████████▌ | 43/50 [00:02<00:00, 22.17it/s]\n 92%|█████████▏| 46/50 [00:02<00:00, 22.21it/s]\n 98%|█████████▊| 49/50 [00:02<00:00, 22.19it/s]\n100%|██████████| 50/50 [00:02<00:00, 21.25it/s]\n  0%|          | 0/45 [00:00<?, ?it/s]\n  2%|▏         | 1/45 [00:00<00:07,  6.14it/s]\n  7%|▋         | 3/45 [00:00<00:04,  9.30it/s]\n 11%|█         | 5/45 [00:00<00:03, 10.74it/s]\n 16%|█▌        | 7/45 [00:00<00:03, 11.46it/s]\n 20%|██        | 9/45 [00:00<00:03, 11.86it/s]\n 24%|██▍       | 11/45 [00:00<00:02, 12.11it/s]\n 29%|██▉       | 13/45 [00:01<00:02, 12.25it/s]\n 33%|███▎      | 15/45 [00:01<00:02, 12.35it/s]\n 38%|███▊      | 17/45 [00:01<00:02, 12.42it/s]\n 42%|████▏     | 19/45 [00:01<00:02, 12.45it/s]\n 47%|████▋     | 21/45 [00:01<00:01, 12.48it/s]\n 51%|█████     | 23/45 [00:01<00:01, 12.50it/s]\n 56%|█████▌    | 25/45 [00:02<00:01, 12.52it/s]\n 60%|██████    | 27/45 [00:02<00:01, 12.54it/s]\n 64%|██████▍   | 29/45 [00:02<00:01, 12.55it/s]\n 69%|██████▉   | 31/45 [00:02<00:01, 12.56it/s]\n 73%|███████▎  | 33/45 [00:02<00:00, 12.56it/s]\n 78%|███████▊  | 35/45 [00:02<00:00, 12.57it/s]\n 82%|████████▏ | 37/45 [00:03<00:00, 12.58it/s]\n 87%|████████▋ | 39/45 [00:03<00:00, 12.57it/s]\n 91%|█████████ | 41/45 [00:03<00:00, 12.58it/s]\n 96%|█████████▌| 43/45 [00:03<00:00, 12.61it/s]\n100%|██████████| 45/45 [00:03<00:00, 12.62it/s]\n100%|██████████| 45/45 [00:03<00:00, 12.24it/s]",
  "metrics": {
    "predict_time": 11.483450089,
    "total_time": 387.94777
  },
  "output": "https://replicate.delivery/pbxt/xyCGKiWjs04hKRFZaGOfSqgTCsO1spe53eMr5OBbcenHh79LB/design.png",
  "started_at": "2024-06-17T13:37:11.025319Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/z6b9q5dww5rgp0cg4sj91cnv1r",
    "cancel": "https://api.replicate.com/v1/predictions/z6b9q5dww5rgp0cg4sj91cnv1r/cancel"
  },
  "version": "5e13482ea317670bfc797bb18bace359860a721a39b5bbcaa1ffcd241d62bca0"
}

Generated in

11.5 seconds

Tweak it ShareReport

/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
return F.conv2d(input, weight, bias, self.stride,
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:07,  6.68it/s]
  8%|▊         | 4/50 [00:00<00:02, 15.39it/s]
 14%|█▍        | 7/50 [00:00<00:02, 18.52it/s]
 20%|██        | 10/50 [00:00<00:02, 19.84it/s]
 26%|██▌       | 13/50 [00:00<00:01, 20.74it/s]
 32%|███▏      | 16/50 [00:00<00:01, 21.31it/s]
 38%|███▊      | 19/50 [00:00<00:01, 21.66it/s]
 44%|████▍     | 22/50 [00:01<00:01, 21.90it/s]
 50%|█████     | 25/50 [00:01<00:01, 22.06it/s]
 56%|█████▌    | 28/50 [00:01<00:00, 22.17it/s]
 62%|██████▏   | 31/50 [00:01<00:00, 22.22it/s]
 68%|██████▊   | 34/50 [00:01<00:00, 22.03it/s]
 74%|███████▍  | 37/50 [00:01<00:00, 22.10it/s]
 80%|████████  | 40/50 [00:01<00:00, 22.11it/s]
 86%|████████▌ | 43/50 [00:02<00:00, 22.17it/s]
 92%|█████████▏| 46/50 [00:02<00:00, 22.21it/s]
 98%|█████████▊| 49/50 [00:02<00:00, 22.19it/s]
100%|██████████| 50/50 [00:02<00:00, 21.25it/s]
  0%|          | 0/45 [00:00<?, ?it/s]
  2%|▏         | 1/45 [00:00<00:07,  6.14it/s]
  7%|▋         | 3/45 [00:00<00:04,  9.30it/s]
 11%|█         | 5/45 [00:00<00:03, 10.74it/s]
 16%|█▌        | 7/45 [00:00<00:03, 11.46it/s]
 20%|██        | 9/45 [00:00<00:03, 11.86it/s]
 24%|██▍       | 11/45 [00:00<00:02, 12.11it/s]
 29%|██▉       | 13/45 [00:01<00:02, 12.25it/s]
 33%|███▎      | 15/45 [00:01<00:02, 12.35it/s]
 38%|███▊      | 17/45 [00:01<00:02, 12.42it/s]
 42%|████▏     | 19/45 [00:01<00:02, 12.45it/s]
 47%|████▋     | 21/45 [00:01<00:01, 12.48it/s]
 51%|█████     | 23/45 [00:01<00:01, 12.50it/s]
 56%|█████▌    | 25/45 [00:02<00:01, 12.52it/s]
 60%|██████    | 27/45 [00:02<00:01, 12.54it/s]
 64%|██████▍   | 29/45 [00:02<00:01, 12.55it/s]
 69%|██████▉   | 31/45 [00:02<00:01, 12.56it/s]
 73%|███████▎  | 33/45 [00:02<00:00, 12.56it/s]
 78%|███████▊  | 35/45 [00:02<00:00, 12.57it/s]
 82%|████████▏ | 37/45 [00:03<00:00, 12.58it/s]
 87%|████████▋ | 39/45 [00:03<00:00, 12.57it/s]
 91%|█████████ | 41/45 [00:03<00:00, 12.58it/s]
 96%|█████████▌| 43/45 [00:03<00:00, 12.61it/s]
100%|██████████| 45/45 [00:03<00:00, 12.62it/s]
100%|██████████| 45/45 [00:03<00:00, 12.24it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.014 to run on Replicate, or 71 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 L40S GPU hardware. Predictions typically complete within 15 seconds. The predict time for this model varies significantly based on the inputs.

Readme

StableDesign

Mykola Lavreniuk, Bartosz Ludwiczuk

Official demo for StableDesign: 2nd place solution for the Generative Interior Design 2024 competition. StableDesign is a deep learning model designed to harness the power of AI, providing innovative and creative tools for designers. Using our algorithms, images of empty rooms can be transformed into fully furnished spaces based on text descriptions.