fofr/replicate-tshirt – Run with an API on Replicate

fofr / replicate-tshirt

Tshirt designs with a hidden Replicate logo

Cold

Public
777 runs
L40S

Iterate in the playground

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=fofr/replicate-tshirt

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

const output = await replicate.run(
  "fofr/replicate-tshirt:cbd108aa8d25f65873969b6ce626c9f7c60187882bdc9f8ea210380d1e1f7da7",
  {
    input: {
      prompt: "a mystical forest, black background, svg, design",
      negative_prompt: "text, words, cropped",
      number_of_images: 2,
      control_illusion_strength: 1.35
    }
  }
);

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

output = replicate.run(
    "fofr/replicate-tshirt:cbd108aa8d25f65873969b6ce626c9f7c60187882bdc9f8ea210380d1e1f7da7",
    input={
        "prompt": "a mystical forest, black background, svg, design",
        "negative_prompt": "text, words, cropped",
        "number_of_images": 2,
        "control_illusion_strength": 1.35
    }
)
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 fofr/replicate-tshirt 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": "fofr/replicate-tshirt:cbd108aa8d25f65873969b6ce626c9f7c60187882bdc9f8ea210380d1e1f7da7",
    "input": {
      "prompt": "a mystical forest, black background, svg, design",
      "negative_prompt": "text, words, cropped",
      "number_of_images": 2,
      "control_illusion_strength": 1.35
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-03-15T13:46:55.624534Z",
  "created_at": "2024-03-15T13:46:35.779775Z",
  "data_removed": false,
  "error": null,
  "id": "crzbsxdb4bclefyjnylbmqk3ii",
  "input": {
    "prompt": "a mystical forest, black background, svg, design",
    "negative_prompt": "text, words, cropped",
    "number_of_images": 2,
    "control_illusion_strength": 1.35
  },
  "logs": "Random seed set to: 3156845569\nChecking inputs\n✅ /tmp/inputs/replicate-logo.png\n====================================\nRunning workflow\ngot prompt\nExecuting node 69, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 66, title: Apply ControlNet, class type: ControlNetApply\nExecuting node 2, title: KSampler (Efficient), class type: KSampler (Efficient)\nRequested to load ControlNet\nLoading 1 new model\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:14,  1.31it/s]\n 10%|█         | 2/20 [00:01<00:13,  1.30it/s]\n 15%|█▌        | 3/20 [00:02<00:12,  1.31it/s]\n 20%|██        | 4/20 [00:03<00:12,  1.32it/s]\n 25%|██▌       | 5/20 [00:03<00:11,  1.33it/s]\n 30%|███       | 6/20 [00:04<00:10,  1.32it/s]\n 35%|███▌      | 7/20 [00:05<00:09,  1.33it/s]\n 40%|████      | 8/20 [00:06<00:08,  1.33it/s]\n 45%|████▌     | 9/20 [00:06<00:08,  1.34it/s]\n 50%|█████     | 10/20 [00:07<00:07,  1.34it/s]\n 55%|█████▌    | 11/20 [00:08<00:06,  1.35it/s]\n 60%|██████    | 12/20 [00:08<00:05,  1.35it/s]\n 65%|██████▌   | 13/20 [00:09<00:05,  1.35it/s]\n 70%|███████   | 14/20 [00:10<00:04,  1.33it/s]\n 75%|███████▌  | 15/20 [00:11<00:03,  1.33it/s]\n 80%|████████  | 16/20 [00:12<00:03,  1.33it/s]\n 85%|████████▌ | 17/20 [00:12<00:02,  1.34it/s]\n 90%|█████████ | 18/20 [00:13<00:01,  1.35it/s]\n 95%|█████████▌| 19/20 [00:14<00:00,  1.39it/s]\n100%|██████████| 20/20 [00:14<00:00,  1.41it/s]\n100%|██████████| 20/20 [00:14<00:00,  1.35it/s]\nExecuting node 6, title: Save Image, class type: SaveImage\nPrompt executed in 16.73 seconds\noutputs:  {'2': {'images': []}, '6': {'images': [{'filename': 'tshirt_00001_.png', 'subfolder': '', 'type': 'output'}, {'filename': 'tshirt_00002_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\ntshirt_00001_.png\ntshirt_00002_.png\n[Path('/tmp/outputs/tshirt_00001_.png'), Path('/tmp/outputs/tshirt_00002_.png')]",
  "metrics": {
    "predict_time": 19.803061,
    "total_time": 19.844759
  },
  "output": [
    "https://replicate.delivery/pbxt/3hofPHovWL36banK0H4rq50PiUtnZjBpN5HdM4ZGfkyNNggSA/tshirt_00001_.png",
    "https://replicate.delivery/pbxt/He9grTqSSn26VCTHSZeOxn1dXyiiDFZBJyMHxjB9HWHPNggSA/tshirt_00002_.png"
  ],
  "started_at": "2024-03-15T13:46:35.821473Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/crzbsxdb4bclefyjnylbmqk3ii",
    "cancel": "https://api.replicate.com/v1/predictions/crzbsxdb4bclefyjnylbmqk3ii/cancel"
  },
  "version": "cbd108aa8d25f65873969b6ce626c9f7c60187882bdc9f8ea210380d1e1f7da7"
}

Generated in

19.8 seconds

Tweak itReport

Random seed set to: 3156845569
Checking inputs
✅ /tmp/inputs/replicate-logo.png
====================================
Running workflow
got prompt
Executing node 69, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 66, title: Apply ControlNet, class type: ControlNetApply
Executing node 2, title: KSampler (Efficient), class type: KSampler (Efficient)
Requested to load ControlNet
Loading 1 new model
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:14,  1.31it/s]
 10%|█         | 2/20 [00:01<00:13,  1.30it/s]
 15%|█▌        | 3/20 [00:02<00:12,  1.31it/s]
 20%|██        | 4/20 [00:03<00:12,  1.32it/s]
 25%|██▌       | 5/20 [00:03<00:11,  1.33it/s]
 30%|███       | 6/20 [00:04<00:10,  1.32it/s]
 35%|███▌      | 7/20 [00:05<00:09,  1.33it/s]
 40%|████      | 8/20 [00:06<00:08,  1.33it/s]
 45%|████▌     | 9/20 [00:06<00:08,  1.34it/s]
 50%|█████     | 10/20 [00:07<00:07,  1.34it/s]
 55%|█████▌    | 11/20 [00:08<00:06,  1.35it/s]
 60%|██████    | 12/20 [00:08<00:05,  1.35it/s]
 65%|██████▌   | 13/20 [00:09<00:05,  1.35it/s]
 70%|███████   | 14/20 [00:10<00:04,  1.33it/s]
 75%|███████▌  | 15/20 [00:11<00:03,  1.33it/s]
 80%|████████  | 16/20 [00:12<00:03,  1.33it/s]
 85%|████████▌ | 17/20 [00:12<00:02,  1.34it/s]
 90%|█████████ | 18/20 [00:13<00:01,  1.35it/s]
 95%|█████████▌| 19/20 [00:14<00:00,  1.39it/s]
100%|██████████| 20/20 [00:14<00:00,  1.41it/s]
100%|██████████| 20/20 [00:14<00:00,  1.35it/s]
Executing node 6, title: Save Image, class type: SaveImage
Prompt executed in 16.73 seconds
outputs:  {'2': {'images': []}, '6': {'images': [{'filename': 'tshirt_00001_.png', 'subfolder': '', 'type': 'output'}, {'filename': 'tshirt_00002_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
Contents of /tmp/outputs:
tshirt_00001_.png
tshirt_00002_.png
[Path('/tmp/outputs/tshirt_00001_.png'), Path('/tmp/outputs/tshirt_00002_.png')]

Examples

View more examples

Run time and cost

This model costs approximately $0.086 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 89 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.