viktorfa/oot_diffusion – Run with an API on Replicate

Input

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

npx create-replicate --model=viktorfa/oot_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 viktorfa/oot_diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "viktorfa/oot_diffusion:9f8fa4956970dde99689af7488157a30aa152e23953526a605df1d77598343d7",
  {
    input: {
      seed: 0,
      steps: 20,
      model_image: "https://raw.githubusercontent.com/viktorfa/oot_diffusion/main/oot_diffusion/assets/model_1.png",
      garment_image: "https://replicate.delivery/pbxt/KTgyzr0WNtcgwN82xEEcc3zoydD8ooXPzMHC18fKZSWu9W5I/blue_jacket.webp",
      guidance_scale: 2
    }
  }
);
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 viktorfa/oot_diffusion using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "viktorfa/oot_diffusion:9f8fa4956970dde99689af7488157a30aa152e23953526a605df1d77598343d7",
    input={
        "seed": 0,
        "steps": 20,
        "model_image": "https://raw.githubusercontent.com/viktorfa/oot_diffusion/main/oot_diffusion/assets/model_1.png",
        "garment_image": "https://replicate.delivery/pbxt/KTgyzr0WNtcgwN82xEEcc3zoydD8ooXPzMHC18fKZSWu9W5I/blue_jacket.webp",
        "guidance_scale": 2
    }
)
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 viktorfa/oot_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": "9f8fa4956970dde99689af7488157a30aa152e23953526a605df1d77598343d7",
    "input": {
      "seed": 0,
      "steps": 20,
      "model_image": "https://raw.githubusercontent.com/viktorfa/oot_diffusion/main/oot_diffusion/assets/model_1.png",
      "garment_image": "https://replicate.delivery/pbxt/KTgyzr0WNtcgwN82xEEcc3zoydD8ooXPzMHC18fKZSWu9W5I/blue_jacket.webp",
      "guidance_scale": 2
    }
  }' \
  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/viktorfa/oot_diffusion@sha256:9f8fa4956970dde99689af7488157a30aa152e23953526a605df1d77598343d7 \
  -i 'seed=0' \
  -i 'steps=20' \
  -i 'model_image="https://raw.githubusercontent.com/viktorfa/oot_diffusion/main/oot_diffusion/assets/model_1.png"' \
  -i 'garment_image="https://replicate.delivery/pbxt/KTgyzr0WNtcgwN82xEEcc3zoydD8ooXPzMHC18fKZSWu9W5I/blue_jacket.webp"' \
  -i 'guidance_scale=2'

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/viktorfa/oot_diffusion@sha256:9f8fa4956970dde99689af7488157a30aa152e23953526a605df1d77598343d7
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 0,
      "steps": 20,
      "model_image": "https://raw.githubusercontent.com/viktorfa/oot_diffusion/main/oot_diffusion/assets/model_1.png",
      "garment_image": "https://replicate.delivery/pbxt/KTgyzr0WNtcgwN82xEEcc3zoydD8ooXPzMHC18fKZSWu9W5I/blue_jacket.webp",
      "guidance_scale": 2
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-02-27T17:55:47.707869Z",
  "created_at": "2024-02-27T17:52:16.491843Z",
  "data_removed": false,
  "error": null,
  "id": "y57hbk3bwo7och2ua4geso6uay",
  "input": {
    "seed": 0,
    "steps": 20,
    "model_image": "https://raw.githubusercontent.com/viktorfa/oot_diffusion/main/oot_diffusion/assets/model_1.png",
    "garment_image": "https://replicate.delivery/pbxt/KTgyzr0WNtcgwN82xEEcc3zoydD8ooXPzMHC18fKZSWu9W5I/blue_jacket.webp",
    "guidance_scale": 2
  },
  "logs": "0%|          | 0/1 [00:00<?, ?it/s]\n100%|██████████| 1/1 [00:21<00:00, 21.03s/it]\n100%|██████████| 1/1 [00:21<00:00, 21.03s/it]\n  0%|          | 0/1 [00:00<?, ?it/s]\n100%|██████████| 1/1 [00:00<00:00,  8.79it/s]\n100%|██████████| 1/1 [00:00<00:00,  8.77it/s]\nInitial seed: 0\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:01<00:19,  1.04s/it]\n 10%|█         | 2/20 [00:01<00:16,  1.10it/s]\n 15%|█▌        | 3/20 [00:02<00:14,  1.14it/s]\n 20%|██        | 4/20 [00:03<00:13,  1.17it/s]\n 25%|██▌       | 5/20 [00:04<00:12,  1.18it/s]\n 30%|███       | 6/20 [00:05<00:11,  1.19it/s]\n 35%|███▌      | 7/20 [00:06<00:10,  1.20it/s]\n 40%|████      | 8/20 [00:06<00:10,  1.20it/s]\n 45%|████▌     | 9/20 [00:07<00:09,  1.20it/s]\n 50%|█████     | 10/20 [00:08<00:08,  1.20it/s]\n 55%|█████▌    | 11/20 [00:09<00:07,  1.20it/s]\n 60%|██████    | 12/20 [00:10<00:06,  1.21it/s]\n 65%|██████▌   | 13/20 [00:10<00:05,  1.21it/s]\n 70%|███████   | 14/20 [00:11<00:04,  1.21it/s]\n 75%|███████▌  | 15/20 [00:12<00:04,  1.21it/s]\n 80%|████████  | 16/20 [00:13<00:03,  1.21it/s]\n 85%|████████▌ | 17/20 [00:14<00:02,  1.21it/s]\n 90%|█████████ | 18/20 [00:15<00:01,  1.21it/s]\n 95%|█████████▌| 19/20 [00:15<00:00,  1.21it/s]\n100%|██████████| 20/20 [00:16<00:00,  1.21it/s]\n100%|██████████| 20/20 [00:16<00:00,  1.19it/s]",
  "metrics": {
    "predict_time": 45.730068,
    "total_time": 211.216026
  },
  "output": [
    "https://replicate.delivery/pbxt/4sud5pjK9jq5IR62IgeeMWWoXOAZRnqUm06oB7AiAXZhQ9aSA/tmpuhhmk2xa.png",
    "https://replicate.delivery/pbxt/oKFffRhzCzs7UUXYn8tKwGFQUmzyuvUjEvOApIYqdsviQ9aSA/tmpx4zt_1lz.png",
    "https://replicate.delivery/pbxt/54MJUHeYnWTdLSgvEYXpwBb0RFkNNjLEthKlZxMWlqlRoeaSA/tmp6suyubk1.png",
    "https://replicate.delivery/pbxt/KFcLXaNuxeUbGaisZY7Klm3hgXEyCzfxMrgh2EK1PTrjQ9aSA/tmp8b6pfmrb.png"
  ],
  "started_at": "2024-02-27T17:55:01.977801Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/y57hbk3bwo7och2ua4geso6uay",
    "cancel": "https://api.replicate.com/v1/predictions/y57hbk3bwo7och2ua4geso6uay/cancel"
  },
  "version": "dbdb1a3bdc9730b31775d513b355fc88506d3f587ade7a2b1a82fe38c2a67880"
}

Generated in

45.7 seconds

Tweak itReport

This example was created by a different version, viktorfa/oot_diffusion:dbdb1a3b.

Run time and cost

This model costs approximately $0.090 to run on Replicate, or 11 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 92 seconds. The predict time for this model varies significantly based on the inputs.