fofr/sticker-maker – Run with an API on Replicate

fofr / sticker-maker

Make stickers with AI. Generates graphics with transparent backgrounds.

Warm

Public
895.8K runs
L40S
GitHub
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=fofr/sticker-maker

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

const output = await replicate.run(
  "fofr/sticker-maker:4acb778eb059772225ec213948f0660867b2e03f277448f18cf1800b96a65a1a",
  {
    input: {
      steps: 17,
      width: 1152,
      height: 1152,
      prompt: "a cute cat",
      output_format: "webp",
      output_quality: 100,
      negative_prompt: "",
      number_of_images: 1
    }
  }
);
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 fofr/sticker-maker using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/sticker-maker:4acb778eb059772225ec213948f0660867b2e03f277448f18cf1800b96a65a1a",
    input={
        "steps": 17,
        "width": 1152,
        "height": 1152,
        "prompt": "a cute cat",
        "output_format": "webp",
        "output_quality": 100,
        "negative_prompt": "",
        "number_of_images": 1
    }
)
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/sticker-maker 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": "4acb778eb059772225ec213948f0660867b2e03f277448f18cf1800b96a65a1a",
    "input": {
      "steps": 17,
      "width": 1152,
      "height": 1152,
      "prompt": "a cute cat",
      "output_format": "webp",
      "output_quality": 100,
      "negative_prompt": "",
      "number_of_images": 1
    }
  }' \
  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/fofr/sticker-maker@sha256:4acb778eb059772225ec213948f0660867b2e03f277448f18cf1800b96a65a1a \
  -i 'steps=17' \
  -i 'width=1152' \
  -i 'height=1152' \
  -i 'prompt="a cute cat"' \
  -i 'output_format="webp"' \
  -i 'output_quality=100' \
  -i 'negative_prompt=""' \
  -i 'number_of_images=1'

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/fofr/sticker-maker@sha256:4acb778eb059772225ec213948f0660867b2e03f277448f18cf1800b96a65a1a
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "steps": 17,
      "width": 1152,
      "height": 1152,
      "prompt": "a cute cat",
      "output_format": "webp",
      "output_quality": 100,
      "negative_prompt": "",
      "number_of_images": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-11-28T11:14:33.380853Z",
  "created_at": "2024-11-28T11:14:28.750000Z",
  "data_removed": false,
  "error": null,
  "id": "emmfw2e51srma0cke9x8a31zxm",
  "input": {
    "steps": 17,
    "width": 1152,
    "height": 1152,
    "prompt": "a cute cat",
    "output_format": "webp",
    "output_quality": 100,
    "negative_prompt": "",
    "number_of_images": 1
  },
  "logs": "Random seed set to: 4001634075\nChecking inputs\n====================================\nChecking weights\n✅ albedobaseXL_v13.safetensors\n✅ layer_xl_transparent_attn.safetensors\n✅ artificialguybr/StickersRedmond.safetensors\n✅ vae_transparent_decoder.safetensors\n====================================\nRunning workflow\ngot prompt\nRequested to load SDXLClipModel\nLoading 1 new model\nExecuting node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 5, title: Empty Latent Image, class type: EmptyLatentImage\nExecuting node 3, title: KSampler, class type: KSampler\n  0%|          | 0/17 [00:00<?, ?it/s]\n  6%|▌         | 1/17 [00:00<00:02,  6.59it/s]\n 12%|█▏        | 2/17 [00:00<00:02,  6.81it/s]\n 18%|█▊        | 3/17 [00:00<00:02,  6.89it/s]\n 24%|██▎       | 4/17 [00:00<00:01,  6.93it/s]\n 29%|██▉       | 5/17 [00:00<00:01,  6.93it/s]\n 35%|███▌      | 6/17 [00:00<00:01,  6.95it/s]\n 41%|████      | 7/17 [00:01<00:01,  6.96it/s]\n 47%|████▋     | 8/17 [00:01<00:01,  6.97it/s]\n 53%|█████▎    | 9/17 [00:01<00:01,  6.97it/s]\n 59%|█████▉    | 10/17 [00:01<00:01,  6.97it/s]\n 65%|██████▍   | 11/17 [00:01<00:00,  6.98it/s]\n 71%|███████   | 12/17 [00:01<00:00,  6.99it/s]\n 76%|███████▋  | 13/17 [00:01<00:00,  6.99it/s]\n 82%|████████▏ | 14/17 [00:02<00:00,  6.99it/s]\n 88%|████████▊ | 15/17 [00:02<00:00,  7.00it/s]\n 94%|█████████▍| 16/17 [00:02<00:00,  7.03it/s]\n100%|██████████| 17/17 [00:02<00:00,  7.04it/s]\n100%|██████████| 17/17 [00:02<00:00,  6.97it/s]\nExecuting node 14, title: VAE Decode, class type: VAEDecode\nExecuting node 20, title: Preview Image, class type: PreviewImage\nExecuting node 36, title: Layer Diffuse Decode (RGBA), class type: LayeredDiffusionDecodeRGBA\n  0%|          | 0/8 [00:00<?, ?it/s]\n 12%|█▎        | 1/8 [00:00<00:01,  6.03it/s]\n 38%|███▊      | 3/8 [00:00<00:00,  7.85it/s]\n 50%|█████     | 4/8 [00:00<00:00,  7.69it/s]\n 62%|██████▎   | 5/8 [00:00<00:00,  7.60it/s]\n 75%|███████▌  | 6/8 [00:00<00:00,  7.54it/s]\n 88%|████████▊ | 7/8 [00:00<00:00,  7.50it/s]\n100%|██████████| 8/8 [00:01<00:00,  7.48it/s]\n100%|██████████| 8/8 [00:01<00:00,  7.49it/s]\nExecuting node 48, title: Save Image, class type: SaveImage\nPrompt executed in 4.10 seconds\noutputs:  {'20': {'images': [{'filename': 'ComfyUI_temp_kmlpk_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '48': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 4.622765286,
    "total_time": 4.630853
  },
  "output": [
    "https://replicate.delivery/xezq/ed6kMmOhNz2YfEaGJwmUeSAmzKDFeCPQP8buewJzffMrMFw6JA/ComfyUI_00001_.webp"
  ],
  "started_at": "2024-11-28T11:14:28.758087Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-or2ov7sc7dnal2sp3p53rrtqxnwc2yehb6v2b6zrxtzy6igu3w4q",
    "get": "https://api.replicate.com/v1/predictions/emmfw2e51srma0cke9x8a31zxm",
    "cancel": "https://api.replicate.com/v1/predictions/emmfw2e51srma0cke9x8a31zxm/cancel"
  },
  "version": "4acb778eb059772225ec213948f0660867b2e03f277448f18cf1800b96a65a1a"
}

Generated in

4.6 seconds

Tweak it ShareReport

Random seed set to: 4001634075
Checking inputs
====================================
Checking weights
✅ albedobaseXL_v13.safetensors
✅ layer_xl_transparent_attn.safetensors
✅ artificialguybr/StickersRedmond.safetensors
✅ vae_transparent_decoder.safetensors
====================================
Running workflow
got prompt
Requested to load SDXLClipModel
Loading 1 new model
Executing node 6, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 5, title: Empty Latent Image, class type: EmptyLatentImage
Executing node 3, title: KSampler, class type: KSampler
  0%|          | 0/17 [00:00<?, ?it/s]
  6%|▌         | 1/17 [00:00<00:02,  6.59it/s]
 12%|█▏        | 2/17 [00:00<00:02,  6.81it/s]
 18%|█▊        | 3/17 [00:00<00:02,  6.89it/s]
 24%|██▎       | 4/17 [00:00<00:01,  6.93it/s]
 29%|██▉       | 5/17 [00:00<00:01,  6.93it/s]
 35%|███▌      | 6/17 [00:00<00:01,  6.95it/s]
 41%|████      | 7/17 [00:01<00:01,  6.96it/s]
 47%|████▋     | 8/17 [00:01<00:01,  6.97it/s]
 53%|█████▎    | 9/17 [00:01<00:01,  6.97it/s]
 59%|█████▉    | 10/17 [00:01<00:01,  6.97it/s]
 65%|██████▍   | 11/17 [00:01<00:00,  6.98it/s]
 71%|███████   | 12/17 [00:01<00:00,  6.99it/s]
 76%|███████▋  | 13/17 [00:01<00:00,  6.99it/s]
 82%|████████▏ | 14/17 [00:02<00:00,  6.99it/s]
 88%|████████▊ | 15/17 [00:02<00:00,  7.00it/s]
 94%|█████████▍| 16/17 [00:02<00:00,  7.03it/s]
100%|██████████| 17/17 [00:02<00:00,  7.04it/s]
100%|██████████| 17/17 [00:02<00:00,  6.97it/s]
Executing node 14, title: VAE Decode, class type: VAEDecode
Executing node 20, title: Preview Image, class type: PreviewImage
Executing node 36, title: Layer Diffuse Decode (RGBA), class type: LayeredDiffusionDecodeRGBA
  0%|          | 0/8 [00:00<?, ?it/s]
 12%|█▎        | 1/8 [00:00<00:01,  6.03it/s]
 38%|███▊      | 3/8 [00:00<00:00,  7.85it/s]
 50%|█████     | 4/8 [00:00<00:00,  7.69it/s]
 62%|██████▎   | 5/8 [00:00<00:00,  7.60it/s]
 75%|███████▌  | 6/8 [00:00<00:00,  7.54it/s]
 88%|████████▊ | 7/8 [00:00<00:00,  7.50it/s]
100%|██████████| 8/8 [00:01<00:00,  7.48it/s]
100%|██████████| 8/8 [00:01<00:00,  7.49it/s]
Executing node 48, title: Save Image, class type: SaveImage
Prompt executed in 4.10 seconds
outputs:  {'20': {'images': [{'filename': 'ComfyUI_temp_kmlpk_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '48': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png

Examples

View more examples

Run time and cost

This model costs approximately $0.0020 to run on Replicate, or 500 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 3 seconds.

Readme

Follow me on Twitter @fofrAI

Uses:

LayerDiffuse for transparency

ArtificialGuyBr’s awesome stickers lora: https://huggingface.co/artificialguybr/StickersRedmond

With the AlbedobaseXL model: https://civitai.com/models/140737/albedobase-xl