fofr/face-to-sticker – Run with an API on Replicate

fofr / face-to-sticker

Turn a face into a sticker

Warm

Public
1.4M runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

image

file

An image of a person to be converted to a sticker

prompt

string

Shift + Return to add a new line

Default: "a person"

negative_prompt

string

Shift + Return to add a new line

Things you do not want in the image

Default: ""

width

integer

Default: 1024

height

integer

Default: 1024

steps

integer

Default: 20

seed

integer

Fix the random seed for reproducibility

prompt_strength

number

Strength of the prompt. This is the CFG scale, higher numbers lead to stronger prompt, lower numbers will keep more of a likeness to the original.

Default: 7

instant_id_strength

number

(minimum: 0, maximum: 1)

How strong the InstantID will be.

Default: 1

ip_adapter_weight

number

(minimum: 0, maximum: 1)

How much the IP adapter will influence the image

Default: 0.2

ip_adapter_noise

number

(minimum: 0, maximum: 1)

How much noise is added to the IP adapter input

Default: 0.5

upscale

boolean

2x upscale the sticker

Default: false

upscale_steps

integer

Number of steps to upscale

Default: 10

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

npx create-replicate --model=fofr/face-to-sticker

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

const output = await replicate.run(
  "fofr/face-to-sticker:764d4827ea159608a07cdde8ddf1c6000019627515eb02b6b449695fd547e5ef",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KU1AG0cit5nc3xIG1BBZ6DKkhunvvGsZXmEZzuW9HPYVkj8o/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
      steps: 20,
      width: 1024,
      height: 1024,
      prompt: "arnold",
      upscale: false,
      upscale_steps: 10,
      negative_prompt: "",
      prompt_strength: 4.5,
      ip_adapter_noise: 0.5,
      ip_adapter_weight: 0.2,
      instant_id_strength: 0.7
    }
  }
);
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/face-to-sticker using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/face-to-sticker:764d4827ea159608a07cdde8ddf1c6000019627515eb02b6b449695fd547e5ef",
    input={
        "image": "https://replicate.delivery/pbxt/KU1AG0cit5nc3xIG1BBZ6DKkhunvvGsZXmEZzuW9HPYVkj8o/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
        "steps": 20,
        "width": 1024,
        "height": 1024,
        "prompt": "arnold",
        "upscale": False,
        "upscale_steps": 10,
        "negative_prompt": "",
        "prompt_strength": 4.5,
        "ip_adapter_noise": 0.5,
        "ip_adapter_weight": 0.2,
        "instant_id_strength": 0.7
    }
)
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/face-to-sticker 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": "764d4827ea159608a07cdde8ddf1c6000019627515eb02b6b449695fd547e5ef",
    "input": {
      "image": "https://replicate.delivery/pbxt/KU1AG0cit5nc3xIG1BBZ6DKkhunvvGsZXmEZzuW9HPYVkj8o/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "arnold",
      "upscale": false,
      "upscale_steps": 10,
      "negative_prompt": "",
      "prompt_strength": 4.5,
      "ip_adapter_noise": 0.5,
      "ip_adapter_weight": 0.2,
      "instant_id_strength": 0.7
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-11-28T11:23:50.624336Z",
  "created_at": "2024-11-28T11:23:45.790000Z",
  "data_removed": false,
  "error": null,
  "id": "zwtetfa4zsrma0ckea1szb2pdm",
  "input": {
    "image": "https://replicate.delivery/pbxt/KU1AG0cit5nc3xIG1BBZ6DKkhunvvGsZXmEZzuW9HPYVkj8o/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
    "steps": 20,
    "width": 1024,
    "height": 1024,
    "prompt": "arnold",
    "upscale": false,
    "upscale_steps": 10,
    "negative_prompt": "",
    "prompt_strength": 4.5,
    "ip_adapter_noise": 0.5,
    "ip_adapter_weight": 0.2,
    "instant_id_strength": 0.7
  },
  "logs": "Random seed set to: 627633395\nChecking inputs\n✅ /tmp/inputs/input.webp\n====================================\nRunning workflow\ngot prompt\nExecuting node 4, title: KSampler (Efficient), class type: KSampler (Efficient)\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:04,  4.13it/s]\n 10%|█         | 2/20 [00:00<00:04,  4.05it/s]\n 15%|█▌        | 3/20 [00:00<00:04,  4.04it/s]\n 20%|██        | 4/20 [00:00<00:03,  4.04it/s]\n 25%|██▌       | 5/20 [00:01<00:03,  4.06it/s]\n 30%|███       | 6/20 [00:01<00:03,  4.10it/s]\n 35%|███▌      | 7/20 [00:01<00:03,  4.14it/s]\n 40%|████      | 8/20 [00:01<00:02,  4.15it/s]\n 45%|████▌     | 9/20 [00:02<00:02,  4.16it/s]\n 50%|█████     | 10/20 [00:02<00:02,  4.16it/s]\n 55%|█████▌    | 11/20 [00:02<00:02,  4.16it/s]\n 60%|██████    | 12/20 [00:02<00:01,  4.47it/s]\n 65%|██████▌   | 13/20 [00:03<00:01,  4.70it/s]\n 70%|███████   | 14/20 [00:03<00:01,  4.87it/s]\n 75%|███████▌  | 15/20 [00:03<00:01,  5.00it/s]\n 80%|████████  | 16/20 [00:03<00:00,  5.09it/s]\n 85%|████████▌ | 17/20 [00:03<00:00,  5.16it/s]\n 90%|█████████ | 18/20 [00:03<00:00,  5.22it/s]\n 95%|█████████▌| 19/20 [00:04<00:00,  5.42it/s]\n100%|██████████| 20/20 [00:04<00:00,  5.58it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.64it/s]\nExecuting node 5, title: Save Image, class type: SaveImage\nExecuting node 9, title: 🧹BRIA RMBG, class type: BRIA_RMBG_Zho\nExecuting node 10, title: Save Image, class type: SaveImage\nPrompt executed in 4.72 seconds\noutputs:  {'47': {'images': [{'filename': 'ComfyUI_temp_zjblz_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '4': {'images': []}, '5': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}, '10': {'images': [{'filename': 'ComfyUI_00002_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png\nComfyUI_00002_.png",
  "metrics": {
    "predict_time": 4.825940794,
    "total_time": 4.834336
  },
  "output": [
    "https://replicate.delivery/xezq/GYZ115u3skagJdL7xC3PjthXhR4yNGHrSPO8YOyJtGtxEY9E/ComfyUI_00001_.png",
    "https://replicate.delivery/xezq/vvHSs2p5vPJtPRNW7ffCYt54fwP43r8I3kG4LPfoCCMaMBWPB/ComfyUI_00002_.png"
  ],
  "started_at": "2024-11-28T11:23:45.798396Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-75rjrjac6amtotfrvft2qnfruke53vlihtdmuomvhobkozhpjxtq",
    "get": "https://api.replicate.com/v1/predictions/zwtetfa4zsrma0ckea1szb2pdm",
    "cancel": "https://api.replicate.com/v1/predictions/zwtetfa4zsrma0ckea1szb2pdm/cancel"
  },
  "version": "764d4827ea159608a07cdde8ddf1c6000019627515eb02b6b449695fd547e5ef"
}

Generated in

4.8 seconds

Tweak it ShareReport

Random seed set to: 627633395
Checking inputs
✅ /tmp/inputs/input.webp
====================================
Running workflow
got prompt
Executing node 4, title: KSampler (Efficient), class type: KSampler (Efficient)
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:04,  4.13it/s]
 10%|█         | 2/20 [00:00<00:04,  4.05it/s]
 15%|█▌        | 3/20 [00:00<00:04,  4.04it/s]
 20%|██        | 4/20 [00:00<00:03,  4.04it/s]
 25%|██▌       | 5/20 [00:01<00:03,  4.06it/s]
 30%|███       | 6/20 [00:01<00:03,  4.10it/s]
 35%|███▌      | 7/20 [00:01<00:03,  4.14it/s]
 40%|████      | 8/20 [00:01<00:02,  4.15it/s]
 45%|████▌     | 9/20 [00:02<00:02,  4.16it/s]
 50%|█████     | 10/20 [00:02<00:02,  4.16it/s]
 55%|█████▌    | 11/20 [00:02<00:02,  4.16it/s]
 60%|██████    | 12/20 [00:02<00:01,  4.47it/s]
 65%|██████▌   | 13/20 [00:03<00:01,  4.70it/s]
 70%|███████   | 14/20 [00:03<00:01,  4.87it/s]
 75%|███████▌  | 15/20 [00:03<00:01,  5.00it/s]
 80%|████████  | 16/20 [00:03<00:00,  5.09it/s]
 85%|████████▌ | 17/20 [00:03<00:00,  5.16it/s]
 90%|█████████ | 18/20 [00:03<00:00,  5.22it/s]
 95%|█████████▌| 19/20 [00:04<00:00,  5.42it/s]
100%|██████████| 20/20 [00:04<00:00,  5.58it/s]
100%|██████████| 20/20 [00:04<00:00,  4.64it/s]
Executing node 5, title: Save Image, class type: SaveImage
Executing node 9, title: 🧹BRIA RMBG, class type: BRIA_RMBG_Zho
Executing node 10, title: Save Image, class type: SaveImage
Prompt executed in 4.72 seconds
outputs:  {'47': {'images': [{'filename': 'ComfyUI_temp_zjblz_00001_.png', 'subfolder': '', 'type': 'temp'}]}, '4': {'images': []}, '5': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}, '10': {'images': [{'filename': 'ComfyUI_00002_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
Contents of /tmp/outputs:
ComfyUI_00001_.png
ComfyUI_00002_.png

Examples

View more examples

Run time and cost

This model costs approximately $0.027 to run on Replicate, or 37 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 28 seconds.

Readme

Non-commercial use only.

It uses the following weights which are non-commercial:

BRIA AI RMBG
InsightFace antelopev2 (which is used by InstantID)

Follow me on Twitter @fofrAI

Loras

Loras are all made by artificialguybr. If you like them you can make a donation to their Patreon or Ko-fi:

Or follow them on Twitter:

https://twitter.com/artificialguybr