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

fofr / face-to-many

Turn a face into 3D, emoji, pixel art, video game, claymation or toy

Warm

Public
12.9M runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

image

file

An image of a person to be converted

style

string

Style to convert to

Default: "3D"

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: ""

denoising_strength

number

(minimum: 0, maximum: 1)

How much of the original image to keep. 1 is the complete destruction of the original image, 0 is the original image

Default: 0.65

prompt_strength

number

(minimum: 0, maximum: 20)

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: 4.5

control_depth_strength

number

(minimum: 0, maximum: 1)

Strength of depth controlnet. The bigger this is, the more controlnet affects the output.

Default: 0.8

instant_id_strength

number

(minimum: 0, maximum: 1)

How strong the InstantID will be.

Default: 1

seed

integer

Fix the random seed for reproducibility

custom_lora_url

string

Shift + Return to add a new line

URL to a Replicate custom LoRA. Must be in the format https://replicate.delivery/pbxt/[id]/trained_model.tar or https://pbxt.replicate.delivery/[id]/trained_model.tar

lora_scale

number

(minimum: 0, maximum: 1)

How strong the LoRA will be

Default: 1

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

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

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-many 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-many:a07f252abbbd832009640b27f063ea52d87d7a23a185ca165bec23b5adc8deaf",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KW7Getr2zD5ECxySdBZtLmPa322lNkXrpkMdKcmxeaDmq2b1/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
      style: "Clay",
      prompt: "a person in a post apocalyptic war game",
      lora_scale: 1,
      negative_prompt: "",
      prompt_strength: 4.5,
      denoising_strength: 0.65,
      instant_id_strength: 0.8,
      control_depth_strength: 0.8
    }
  }
);
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-many using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/face-to-many:a07f252abbbd832009640b27f063ea52d87d7a23a185ca165bec23b5adc8deaf",
    input={
        "image": "https://replicate.delivery/pbxt/KW7Getr2zD5ECxySdBZtLmPa322lNkXrpkMdKcmxeaDmq2b1/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
        "style": "Clay",
        "prompt": "a person in a post apocalyptic war game",
        "lora_scale": 1,
        "negative_prompt": "",
        "prompt_strength": 4.5,
        "denoising_strength": 0.65,
        "instant_id_strength": 0.8,
        "control_depth_strength": 0.8
    }
)
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-many 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": "a07f252abbbd832009640b27f063ea52d87d7a23a185ca165bec23b5adc8deaf",
    "input": {
      "image": "https://replicate.delivery/pbxt/KW7Getr2zD5ECxySdBZtLmPa322lNkXrpkMdKcmxeaDmq2b1/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
      "style": "Clay",
      "prompt": "a person in a post apocalyptic war game",
      "lora_scale": 1,
      "negative_prompt": "",
      "prompt_strength": 4.5,
      "denoising_strength": 0.65,
      "instant_id_strength": 0.8,
      "control_depth_strength": 0.8
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-11-28T11:16:48.998121Z",
  "created_at": "2024-11-28T11:16:37.648000Z",
  "data_removed": false,
  "error": null,
  "id": "3hvtjcxwj1rme0cke9y8vmxrd0",
  "input": {
    "image": "https://replicate.delivery/pbxt/KW7Getr2zD5ECxySdBZtLmPa322lNkXrpkMdKcmxeaDmq2b1/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
    "style": "Clay",
    "prompt": "a person in a post apocalyptic war game",
    "lora_scale": 1,
    "negative_prompt": "",
    "prompt_strength": 4.5,
    "denoising_strength": 0.65,
    "instant_id_strength": 0.8,
    "control_depth_strength": 0.8
  },
  "logs": "Random seed set to: 2815191178\nChecking inputs\n✅ /tmp/inputs/input.webp\n====================================\nRunning workflow\ngot prompt\nExecuting node 22, title: Load Image, class type: LoadImage\nExecuting node 67, title: 🔧 Image Resize, class type: ImageResize+\nExecuting node 3, title: LoRA Stacker, class type: LoRA Stacker\nExecuting node 49, title: AIO Aux Preprocessor, class type: AIO_Preprocessor\nExecuting node 28, title: Control Net Stacker, class type: Control Net Stacker\nExecuting node 2, title: Efficient Loader, class type: Efficient Loader\nRequested to load SDXLClipModel\nLoading 1 new model\n----------------------------------------\n\u001b[36mEfficient Loader Models Cache:\u001b[0m\nCkpt:\n[1] albedobaseXL_v13\nLora:\n[1] base_ckpt: albedobaseXL_v13\nlora(mod,clip): ClayAnimationRedm(1.0,1.0)\nExecuting node 41, title: Apply InstantID, class type: ApplyInstantID\nExecuting node 51, title: VAE Encode, class type: VAEEncode\nExecuting node 4, title: KSampler (Efficient), class type: KSampler (Efficient)\nRequested to load SDXL\nRequested to load ControlNet\nRequested to load ControlNet\nLoading 3 new models\n  0%|          | 0/17 [00:00<?, ?it/s]\n  6%|▌         | 1/17 [00:00<00:02,  6.37it/s]\n 12%|█▏        | 2/17 [00:00<00:02,  6.37it/s]\n 18%|█▊        | 3/17 [00:00<00:02,  6.36it/s]\n 24%|██▎       | 4/17 [00:00<00:02,  6.37it/s]\n 29%|██▉       | 5/17 [00:00<00:01,  6.36it/s]\n 35%|███▌      | 6/17 [00:00<00:01,  6.36it/s]\n 41%|████      | 7/17 [00:01<00:01,  6.36it/s]\n 47%|████▋     | 8/17 [00:01<00:01,  6.34it/s]\n 53%|█████▎    | 9/17 [00:01<00:01,  6.35it/s]\n 59%|█████▉    | 10/17 [00:01<00:01,  6.36it/s]\n 65%|██████▍   | 11/17 [00:01<00:00,  6.37it/s]\n 71%|███████   | 12/17 [00:01<00:00,  6.37it/s]\n 76%|███████▋  | 13/17 [00:02<00:00,  6.36it/s]\n 82%|████████▏ | 14/17 [00:02<00:00,  6.37it/s]\n 88%|████████▊ | 15/17 [00:02<00:00,  6.36it/s]\n 94%|█████████▍| 16/17 [00:02<00:00,  6.38it/s]\n100%|██████████| 17/17 [00:02<00:00,  6.41it/s]\n100%|██████████| 17/17 [00:02<00:00,  6.37it/s]\nExecuting node 5, title: Save Image, class type: SaveImage\nPrompt executed in 6.08 seconds\noutputs:  {'4': {'images': []}, '5': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 6.523334466,
    "total_time": 11.350121
  },
  "output": [
    "https://replicate.delivery/xezq/QYCNMyAE6C7fd6GXc5Uy9KfqYKVTUfKpuGePXSFf2qLCkBseE/ComfyUI_00001_.png"
  ],
  "started_at": "2024-11-28T11:16:42.474787Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/3hvtjcxwj1rme0cke9y8vmxrd0",
    "cancel": "https://api.replicate.com/v1/predictions/3hvtjcxwj1rme0cke9y8vmxrd0/cancel"
  },
  "version": "a07f252abbbd832009640b27f063ea52d87d7a23a185ca165bec23b5adc8deaf"
}

Generated in

6.5 seconds

Tweak it ShareReport

Random seed set to: 2815191178
Checking inputs
✅ /tmp/inputs/input.webp
====================================
Running workflow
got prompt
Executing node 22, title: Load Image, class type: LoadImage
Executing node 67, title: 🔧 Image Resize, class type: ImageResize+
Executing node 3, title: LoRA Stacker, class type: LoRA Stacker
Executing node 49, title: AIO Aux Preprocessor, class type: AIO_Preprocessor
Executing node 28, title: Control Net Stacker, class type: Control Net Stacker
Executing node 2, title: Efficient Loader, class type: Efficient Loader
Requested to load SDXLClipModel
Loading 1 new model
----------------------------------------
Efficient Loader Models Cache:
Ckpt:
[1] albedobaseXL_v13
Lora:
[1] base_ckpt: albedobaseXL_v13
lora(mod,clip): ClayAnimationRedm(1.0,1.0)
Executing node 41, title: Apply InstantID, class type: ApplyInstantID
Executing node 51, title: VAE Encode, class type: VAEEncode
Executing node 4, title: KSampler (Efficient), class type: KSampler (Efficient)
Requested to load SDXL
Requested to load ControlNet
Requested to load ControlNet
Loading 3 new models
  0%|          | 0/17 [00:00<?, ?it/s]
  6%|▌         | 1/17 [00:00<00:02,  6.37it/s]
 12%|█▏        | 2/17 [00:00<00:02,  6.37it/s]
 18%|█▊        | 3/17 [00:00<00:02,  6.36it/s]
 24%|██▎       | 4/17 [00:00<00:02,  6.37it/s]
 29%|██▉       | 5/17 [00:00<00:01,  6.36it/s]
 35%|███▌      | 6/17 [00:00<00:01,  6.36it/s]
 41%|████      | 7/17 [00:01<00:01,  6.36it/s]
 47%|████▋     | 8/17 [00:01<00:01,  6.34it/s]
 53%|█████▎    | 9/17 [00:01<00:01,  6.35it/s]
 59%|█████▉    | 10/17 [00:01<00:01,  6.36it/s]
 65%|██████▍   | 11/17 [00:01<00:00,  6.37it/s]
 71%|███████   | 12/17 [00:01<00:00,  6.37it/s]
 76%|███████▋  | 13/17 [00:02<00:00,  6.36it/s]
 82%|████████▏ | 14/17 [00:02<00:00,  6.37it/s]
 88%|████████▊ | 15/17 [00:02<00:00,  6.36it/s]
 94%|█████████▍| 16/17 [00:02<00:00,  6.38it/s]
100%|██████████| 17/17 [00:02<00:00,  6.41it/s]
100%|██████████| 17/17 [00:02<00:00,  6.37it/s]
Executing node 5, title: Save Image, class type: SaveImage
Prompt executed in 6.08 seconds
outputs:  {'4': {'images': []}, '5': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
Contents of /tmp/outputs:
ComfyUI_00001_.png

Examples

View more examples

Run time and cost

This model costs approximately $0.0078 to run on Replicate, or 128 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 9 seconds.

Readme

Non-commercial use only.

It uses the following weights which are non-commercial: InsightFace antelopev2 (which is used by InstantID)

Follow me on Twitter @fofrAI

Loras

Many of the loras are 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