fofr/become-image – Run with an API on Replicate

fofr / become-image

Adapt any picture of a face into another image

Warm

Public
509.5K runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

image

file

Preview

An image of a person to be converted

image_to_become

file

Preview

Any image to convert the person to

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: ""

number_of_images

integer

(minimum: 1, maximum: 10)

Number of images to generate

Default: 2

denoising_strength

number

(minimum: 0, maximum: 1)

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

Default: 1

prompt_strength

number

(minimum: 0, maximum: 3)

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: 2

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

image_to_become_strength

number

(minimum: 0, maximum: 1)

How strong the style will be applied

Default: 0.75

image_to_become_noise

number

(minimum: 0, maximum: 1)

How much noise to add to the style image before processing. An alternative way of controlling stength.

Default: 0.3

seed

integer

Fix the random seed for reproducibility

disable_safety_checker

boolean

Disable safety checker for generated images

Default: false

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

npx create-replicate --model=fofr/become-image

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

const output = await replicate.run(
  "fofr/become-image:8d0b076a2aff3904dfcec3253c778e0310a68f78483c4699c7fd800f3051d2b3",
  {
    input: {
      image: "https://replicate.delivery/pbxt/KYEdDz93eyPMIR0zltb9SzZ4lLTQkH0CfMcmnaGD5wHbA7Dt/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
      prompt: "a person",
      image_to_become: "https://replicate.delivery/pbxt/KYEdDanJM7WAO228dBjJllUErGYq0ysQXgencMcVMDtNW9sf/cHJpdmF0ZS9sci9pbWFnZXMvd2Vic2l0ZS8yMDIyLTA1L2pvYjU4NS12MjE2LXRhbmctYXVtLTAxMC1leWUtYXJ0cHJpbnRzLmpwZw.webp",
      negative_prompt: "",
      prompt_strength: 2,
      number_of_images: 1,
      denoising_strength: 1,
      instant_id_strength: 1,
      image_to_become_noise: 0.3,
      control_depth_strength: 0.8,
      image_to_become_strength: 0.75
    }
  }
);
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/become-image using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/become-image:8d0b076a2aff3904dfcec3253c778e0310a68f78483c4699c7fd800f3051d2b3",
    input={
        "image": "https://replicate.delivery/pbxt/KYEdDz93eyPMIR0zltb9SzZ4lLTQkH0CfMcmnaGD5wHbA7Dt/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
        "prompt": "a person",
        "image_to_become": "https://replicate.delivery/pbxt/KYEdDanJM7WAO228dBjJllUErGYq0ysQXgencMcVMDtNW9sf/cHJpdmF0ZS9sci9pbWFnZXMvd2Vic2l0ZS8yMDIyLTA1L2pvYjU4NS12MjE2LXRhbmctYXVtLTAxMC1leWUtYXJ0cHJpbnRzLmpwZw.webp",
        "negative_prompt": "",
        "prompt_strength": 2,
        "number_of_images": 1,
        "denoising_strength": 1,
        "instant_id_strength": 1,
        "image_to_become_noise": 0.3,
        "control_depth_strength": 0.8,
        "image_to_become_strength": 0.75
    }
)
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/become-image 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": "8d0b076a2aff3904dfcec3253c778e0310a68f78483c4699c7fd800f3051d2b3",
    "input": {
      "image": "https://replicate.delivery/pbxt/KYEdDz93eyPMIR0zltb9SzZ4lLTQkH0CfMcmnaGD5wHbA7Dt/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
      "prompt": "a person",
      "image_to_become": "https://replicate.delivery/pbxt/KYEdDanJM7WAO228dBjJllUErGYq0ysQXgencMcVMDtNW9sf/cHJpdmF0ZS9sci9pbWFnZXMvd2Vic2l0ZS8yMDIyLTA1L2pvYjU4NS12MjE2LXRhbmctYXVtLTAxMC1leWUtYXJ0cHJpbnRzLmpwZw.webp",
      "negative_prompt": "",
      "prompt_strength": 2,
      "number_of_images": 1,
      "denoising_strength": 1,
      "instant_id_strength": 1,
      "image_to_become_noise": 0.3,
      "control_depth_strength": 0.8,
      "image_to_become_strength": 0.75
    }
  }' \
  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/become-image@sha256:8d0b076a2aff3904dfcec3253c778e0310a68f78483c4699c7fd800f3051d2b3 \
  -i 'image="https://replicate.delivery/pbxt/KYEdDz93eyPMIR0zltb9SzZ4lLTQkH0CfMcmnaGD5wHbA7Dt/MTk4MTczMTkzNzI1Mjg5NjYy.webp"' \
  -i 'prompt="a person"' \
  -i 'image_to_become="https://replicate.delivery/pbxt/KYEdDanJM7WAO228dBjJllUErGYq0ysQXgencMcVMDtNW9sf/cHJpdmF0ZS9sci9pbWFnZXMvd2Vic2l0ZS8yMDIyLTA1L2pvYjU4NS12MjE2LXRhbmctYXVtLTAxMC1leWUtYXJ0cHJpbnRzLmpwZw.webp"' \
  -i 'negative_prompt=""' \
  -i 'prompt_strength=2' \
  -i 'number_of_images=1' \
  -i 'denoising_strength=1' \
  -i 'instant_id_strength=1' \
  -i 'image_to_become_noise=0.3' \
  -i 'control_depth_strength=0.8' \
  -i 'image_to_become_strength=0.75'

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/become-image@sha256:8d0b076a2aff3904dfcec3253c778e0310a68f78483c4699c7fd800f3051d2b3
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/KYEdDz93eyPMIR0zltb9SzZ4lLTQkH0CfMcmnaGD5wHbA7Dt/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
      "prompt": "a person",
      "image_to_become": "https://replicate.delivery/pbxt/KYEdDanJM7WAO228dBjJllUErGYq0ysQXgencMcVMDtNW9sf/cHJpdmF0ZS9sci9pbWFnZXMvd2Vic2l0ZS8yMDIyLTA1L2pvYjU4NS12MjE2LXRhbmctYXVtLTAxMC1leWUtYXJ0cHJpbnRzLmpwZw.webp",
      "negative_prompt": "",
      "prompt_strength": 2,
      "number_of_images": 1,
      "denoising_strength": 1,
      "instant_id_strength": 1,
      "image_to_become_noise": 0.3,
      "control_depth_strength": 0.8,
      "image_to_become_strength": 0.75
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-11-28T11:21:13.805480Z",
  "created_at": "2024-11-28T11:21:12.115000Z",
  "data_removed": false,
  "error": null,
  "id": "e8w348fcpdrme0ckea093c5eyg",
  "input": {
    "image": "https://replicate.delivery/pbxt/KYEdDz93eyPMIR0zltb9SzZ4lLTQkH0CfMcmnaGD5wHbA7Dt/MTk4MTczMTkzNzI1Mjg5NjYy.webp",
    "prompt": "a person",
    "image_to_become": "https://replicate.delivery/pbxt/KYEdDanJM7WAO228dBjJllUErGYq0ysQXgencMcVMDtNW9sf/cHJpdmF0ZS9sci9pbWFnZXMvd2Vic2l0ZS8yMDIyLTA1L2pvYjU4NS12MjE2LXRhbmctYXVtLTAxMC1leWUtYXJ0cHJpbnRzLmpwZw.webp",
    "negative_prompt": "",
    "prompt_strength": 2,
    "number_of_images": 1,
    "denoising_strength": 1,
    "instant_id_strength": 1,
    "image_to_become_noise": 0.3,
    "control_depth_strength": 0.8,
    "image_to_become_strength": 0.75
  },
  "logs": "Random seed set to: 1458577306\nChecking inputs\n✅ /tmp/inputs/image_of_face.webp\n✅ /tmp/inputs/image_to_become.webp\n====================================\nRunning workflow\ngot prompt\nExecuting node 75, title: KSampler, class type: KSampler\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.99it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.98it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  3.00it/s]\n100%|██████████| 4/4 [00:01<00:00,  3.74it/s]\n100%|██████████| 4/4 [00:01<00:00,  3.42it/s]\nExecuting node 76, title: VAE Decode, class type: VAEDecode\nExecuting node 5, title: Save Image, class type: SaveImage\nPrompt executed in 1.40 seconds\noutputs:  {'5': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 1.682142265,
    "total_time": 1.69048
  },
  "output": [
    "https://replicate.delivery/xezq/u7JuFFgLS6phIlB8GKvpHQkCqrELTvLqfoTeIbCB7seShArnA/ComfyUI_00001_.png"
  ],
  "started_at": "2024-11-28T11:21:12.123337Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-daeec4kc3iw6oenbfenitdub3of3drsnuxfecvje7nli4d3cbsua",
    "get": "https://api.replicate.com/v1/predictions/e8w348fcpdrme0ckea093c5eyg",
    "cancel": "https://api.replicate.com/v1/predictions/e8w348fcpdrme0ckea093c5eyg/cancel"
  },
  "version": "8d0b076a2aff3904dfcec3253c778e0310a68f78483c4699c7fd800f3051d2b3"
}

Generated in

1.7 seconds

Tweak it ShareReport

Examples

View more examples

Run time and cost

This model costs approximately $0.0095 to run on Replicate, or 105 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 10 seconds.

Readme

Adapt any picture of a face into another image

Follow me on X @fofrAI

ComfyUI

You can also run this as a ComfyUI workflow, details here:

https://github.com/fofr/cog-become-image