fofr/consistent-character – Run with an API on Replicate

fofr / consistent-character

Create images of a given character in different poses

Warm

Public
878.9K runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

A closeup headshot photo of a young woman in a grey sweaterA closeup headshot photo of a young woman in a grey sweater

Describe the subject. Include clothes and hairstyle for more consistency.

Default: "A headshot photo"

negative_prompt

string

Shift + Return to add a new line

Things you do not want to see in your image

Default: ""

subject

file

An image of a person. Best images are square close ups of a face, but they do not have to be.

number_of_outputs

integer

(minimum: 1, maximum: 20)

The number of images to generate.

Default: 3

number_of_images_per_pose

integer

(minimum: 1, maximum: 4)

The number of images to generate for each pose.

Default: 1

randomise_poses

boolean

Randomise the poses used.

Default: true

output_format

string

Format of the output images

Default: "webp"

output_quality

integer

(minimum: 0, maximum: 100)

Quality of the output images, from 0 to 100. 100 is best quality, 0 is lowest quality.

Default: 80

seed

integer

Set a seed for reproducibility. Random by default.

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/consistent-character

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

const output = await replicate.run(
  "fofr/consistent-character:9c77a3c2f884193fcee4d89645f02a0b9def9434f9e03cb98460456b831c8772",
  {
    input: {
      prompt: "A closeup headshot photo of a young woman in a grey sweater",
      subject: "https://replicate.delivery/pbxt/L0gy7uyLE5UP0uz12cndDdSOIgw5R3rV5N6G2pbt7kEK9dCr/0_3.webp",
      output_format: "webp",
      output_quality: 80,
      negative_prompt: "",
      randomise_poses: true,
      number_of_outputs: 5,
      number_of_images_per_pose: 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/consistent-character using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/consistent-character:9c77a3c2f884193fcee4d89645f02a0b9def9434f9e03cb98460456b831c8772",
    input={
        "prompt": "A closeup headshot photo of a young woman in a grey sweater",
        "subject": "https://replicate.delivery/pbxt/L0gy7uyLE5UP0uz12cndDdSOIgw5R3rV5N6G2pbt7kEK9dCr/0_3.webp",
        "output_format": "webp",
        "output_quality": 80,
        "negative_prompt": "",
        "randomise_poses": True,
        "number_of_outputs": 5,
        "number_of_images_per_pose": 1
    }
)

# The fofr/consistent-character model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/fofr/consistent-character/api#output-schema
    print(item)

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/consistent-character 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": "9c77a3c2f884193fcee4d89645f02a0b9def9434f9e03cb98460456b831c8772",
    "input": {
      "prompt": "A closeup headshot photo of a young woman in a grey sweater",
      "subject": "https://replicate.delivery/pbxt/L0gy7uyLE5UP0uz12cndDdSOIgw5R3rV5N6G2pbt7kEK9dCr/0_3.webp",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "",
      "randomise_poses": true,
      "number_of_outputs": 5,
      "number_of_images_per_pose": 1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Install Cog

brew install cog

If you don’t have Homebrew, there are other installation options available.

Pull and run fofr/consistent-character using Cog (this will download the full model and run it in your local environment):

cog predict r8.im/fofr/consistent-character@sha256:9c77a3c2f884193fcee4d89645f02a0b9def9434f9e03cb98460456b831c8772 \
  -i 'prompt="A closeup headshot photo of a young woman in a grey sweater"' \
  -i 'subject="https://replicate.delivery/pbxt/L0gy7uyLE5UP0uz12cndDdSOIgw5R3rV5N6G2pbt7kEK9dCr/0_3.webp"' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'negative_prompt=""' \
  -i 'randomise_poses=true' \
  -i 'number_of_outputs=5' \
  -i 'number_of_images_per_pose=1'

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

Pull and run fofr/consistent-character using Docker (this will download the full model and run it in your local environment):

docker run -d -p 5000:5000 --gpus=all r8.im/fofr/consistent-character@sha256:9c77a3c2f884193fcee4d89645f02a0b9def9434f9e03cb98460456b831c8772
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "prompt": "A closeup headshot photo of a young woman in a grey sweater",
      "subject": "https://replicate.delivery/pbxt/L0gy7uyLE5UP0uz12cndDdSOIgw5R3rV5N6G2pbt7kEK9dCr/0_3.webp",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "",
      "randomise_poses": true,
      "number_of_outputs": 5,
      "number_of_images_per_pose": 1
    }
  }' \
  http://localhost:5000/predictions

Output

{
  "completed_at": "2024-11-28T11:06:43.447715Z",
  "created_at": "2024-11-28T11:05:18.680000Z",
  "data_removed": false,
  "error": null,
  "id": "84ny6930b1rm80cke9sbvahyrr",
  "input": {
    "prompt": "A closeup headshot photo of a young woman in a grey sweater",
    "subject": "https://replicate.delivery/pbxt/L0gy7uyLE5UP0uz12cndDdSOIgw5R3rV5N6G2pbt7kEK9dCr/0_3.webp",
    "output_format": "webp",
    "output_quality": 80,
    "negative_prompt": "",
    "randomise_poses": true,
    "number_of_outputs": 5,
    "number_of_images_per_pose": 1
  },
  "logs": "Random seed set to: 3565209131\nRunning workflow\ngot prompt\nExecuting node 7, title: Load Image, class type: LoadImage\nExecuting node 52, title: IPAdapter Advanced, class type: IPAdapterAdvanced\nExecuting node 9, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 94, title: Load Image, class type: LoadImage\nExecuting node 2, title: Apply InstantID, class type: ApplyInstantID\n\u001b[33mWARNING: No face detected in the keypoints image!\u001b[0m\nExecuting node 95, title: Load Image, class type: LoadImage\nExecuting node 74, title: Apply ControlNet, class type: ControlNetApply\nExecuting node 11, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:02,  1.29it/s]\n 50%|█████     | 2/4 [00:01<00:01,  1.28it/s]\n 75%|███████▌  | 3/4 [00:02<00:00,  1.29it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.62it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.48it/s]\nExecuting node 13, title: VAE Decode, class type: VAEDecode\nExecuting node 98, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 2 eyess, 4.1ms\nSpeed: 1.8ms preprocess, 4.1ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((73.86212, 55.299133)) | crop region (221, 165) x 4.635402991449178 -> (1024, 764)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.63it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.55it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.62it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.59it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.17it/s]\nDetailer: segment upscale for ((73.732666, 51.800705)) | crop region (221, 155) x 4.634272994204666 -> (1024, 718)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.63it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.56it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.62it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.60it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.17it/s]\nExecuting node 103, title: Upscale Image By, class type: ImageScaleBy\nExecuting node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 106, title: VAE Encode, class type: VAEEncode\nExecuting node 105, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.01it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.02it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  2.03it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.52it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.31it/s]\nExecuting node 107, title: VAE Decode, class type: VAEDecode\nExecuting node 115, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 2 eyess, 3.7ms\nSpeed: 2.0ms preprocess, 3.7ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((113.00043, 83.53461)) | crop region (339, 250) x 3.0213239563679735 -> (1024, 755)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  5.35it/s]\n 50%|█████     | 2/4 [00:00<00:00,  5.05it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  5.21it/s]\n100%|██████████| 4/4 [00:00<00:00,  6.05it/s]\nDetailer: segment upscale for ((111.63367, 77.24356)) | crop region (334, 231) x 3.0666259557170323 -> (1024, 708)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  5.25it/s]\n 50%|█████     | 2/4 [00:00<00:00,  5.11it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  5.26it/s]\n100%|██████████| 4/4 [00:00<00:00,  6.08it/s]\nExecuting node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 116, title: Save Image, class type: SaveImage\nPrompt executed in 13.72 seconds\noutputs:  {'116': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png\nRunning workflow\ngot prompt\nExecuting node 94, title: Load Image, class type: LoadImage\nExecuting node 2, title: Apply InstantID, class type: ApplyInstantID\n\u001b[33mWARNING: No face detected in the keypoints image!\u001b[0m\nExecuting node 95, title: Load Image, class type: LoadImage\nExecuting node 74, title: Apply ControlNet, class type: ControlNetApply\nExecuting node 11, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:02,  1.29it/s]\n 50%|█████     | 2/4 [00:01<00:01,  1.30it/s]\n 75%|███████▌  | 3/4 [00:02<00:00,  1.31it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.63it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.49it/s]\nExecuting node 13, title: VAE Decode, class type: VAEDecode\nExecuting node 98, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 2 eyess, 3.8ms\nSpeed: 1.8ms preprocess, 3.8ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((73.45352, 53.77359)) | crop region (220, 161) x 4.654638567808891 -> (1024, 749)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.67it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.58it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.62it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.57it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.17it/s]\nDetailer: segment upscale for ((74.03876, 54.732117)) | crop region (222, 164) x 4.614241534884912 -> (1024, 756)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.60it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.50it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.58it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.54it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.12it/s]\nExecuting node 103, title: Upscale Image By, class type: ImageScaleBy\nExecuting node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 106, title: VAE Encode, class type: VAEEncode\nRequested to load SDXL\nLoading 1 new model\nExecuting node 105, title: KSampler, class type: KSampler\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.02it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.02it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  2.03it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.53it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.32it/s]\nExecuting node 107, title: VAE Decode, class type: VAEDecode\nExecuting node 115, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 2 eyess, 3.7ms\nSpeed: 2.0ms preprocess, 3.7ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((112.757385, 81.501495)) | crop region (338, 244) x 3.0305575839970316 -> (1024, 739)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  5.31it/s]\n 50%|█████     | 2/4 [00:00<00:00,  5.14it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  5.28it/s]\n100%|██████████| 4/4 [00:00<00:00,  6.11it/s]\nDetailer: segment upscale for ((108.96271, 81.140656)) | crop region (326, 243) x 3.142738857900158 -> (1024, 763)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  5.26it/s]\n 50%|█████     | 2/4 [00:00<00:00,  5.10it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  5.24it/s]\n100%|██████████| 4/4 [00:00<00:00,  6.06it/s]\nExecuting node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 116, title: Save Image, class type: SaveImage\nPrompt executed in 12.02 seconds\noutputs:  {'116': {'images': [{'filename': 'ComfyUI_00002_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png\nComfyUI_00001_.webp\nComfyUI_00002_.png\nRunning workflow\ngot prompt\nExecuting node 94, title: Load Image, class type: LoadImage\nExecuting node 2, title: Apply InstantID, class type: ApplyInstantID\n\u001b[33mWARNING: No face detected in the keypoints image!\u001b[0m\nExecuting node 95, title: Load Image, class type: LoadImage\nExecuting node 74, title: Apply ControlNet, class type: ControlNetApply\nExecuting node 11, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:02,  1.30it/s]\n 50%|█████     | 2/4 [00:01<00:01,  1.30it/s]\n 75%|███████▌  | 3/4 [00:02<00:00,  1.22it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.55it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.43it/s]\nExecuting node 13, title: VAE Decode, class type: VAEDecode\nExecuting node 98, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 1 eyes, 3.8ms\nSpeed: 1.9ms preprocess, 3.8ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((61.96982, 72.26677)) | crop region (185, 216) x 4.74236357326829 -> (877, 1024)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.91it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.18it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.37it/s]\n100%|██████████| 4/4 [00:01<00:00,  4.34it/s]\n100%|██████████| 4/4 [00:01<00:00,  3.84it/s]\nExecuting node 103, title: Upscale Image By, class type: ImageScaleBy\nExecuting node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 106, title: VAE Encode, class type: VAEEncode\nExecuting node 105, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  1.72it/s]\n 50%|█████     | 2/4 [00:01<00:01,  1.89it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  1.95it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.45it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.20it/s]\nExecuting node 107, title: VAE Decode, class type: VAEDecode\nExecuting node 115, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 1 eyes, 3.8ms\nSpeed: 2.0ms preprocess, 3.8ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((90.188965, 103.0957)) | crop region (270, 309) x 3.3155228542930626 -> (895, 1024)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  4.20it/s]\n 50%|█████     | 2/4 [00:00<00:00,  4.54it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  4.84it/s]\n100%|██████████| 4/4 [00:00<00:00,  5.54it/s]\nExecuting node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 116, title: Save Image, class type: SaveImage\nPrompt executed in 10.39 seconds\noutputs:  {'116': {'images': [{'filename': 'ComfyUI_00003_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png\nComfyUI_00001_.webp\nComfyUI_00002_.png\nComfyUI_00002_.webp\nComfyUI_00003_.png\nRunning workflow\ngot prompt\nExecuting node 94, title: Load Image, class type: LoadImage\nExecuting node 2, title: Apply InstantID, class type: ApplyInstantID\n\u001b[33mWARNING: No face detected in the keypoints image!\u001b[0m\nExecuting node 95, title: Load Image, class type: LoadImage\nExecuting node 74, title: Apply ControlNet, class type: ControlNetApply\nExecuting node 11, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:02,  1.03it/s]\n 50%|█████     | 2/4 [00:01<00:01,  1.17it/s]\n 75%|███████▌  | 3/4 [00:02<00:00,  1.23it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.56it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.39it/s]\nExecuting node 13, title: VAE Decode, class type: VAEDecode\nExecuting node 98, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 2 eyess, 3.7ms\nSpeed: 1.8ms preprocess, 3.7ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((74.9787, 57.678177)) | crop region (224, 173) x 4.572376805496374 -> (1024, 791)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.61it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.42it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.53it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.49it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.07it/s]\nDetailer: segment upscale for ((59.416992, 52.120804)) | crop region (178, 156) x 5.7546297201101035 -> (1024, 897)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.56it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.49it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.56it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.52it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.10it/s]\nExecuting node 103, title: Upscale Image By, class type: ImageScaleBy\nExecuting node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 106, title: VAE Encode, class type: VAEEncode\nExecuting node 105, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.00it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.01it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  2.02it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.52it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.31it/s]\nExecuting node 107, title: VAE Decode, class type: VAEDecode\nExecuting node 115, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 2 eyess, 3.7ms\nSpeed: 2.0ms preprocess, 3.7ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((112.56372, 85.240845)) | crop region (337, 255) x 3.038866800927065 -> (1024, 774)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  5.25it/s]\n 50%|█████     | 2/4 [00:00<00:00,  5.05it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  5.19it/s]\n100%|██████████| 4/4 [00:00<00:00,  6.02it/s]\nDetailer: segment upscale for ((87.10809, 73.62387)) | crop region (261, 220) x 3.924229594016791 -> (1024, 863)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  5.20it/s]\n 50%|█████     | 2/4 [00:00<00:00,  5.00it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  5.16it/s]\n100%|██████████| 4/4 [00:00<00:00,  5.98it/s]\nExecuting node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 116, title: Save Image, class type: SaveImage\nPrompt executed in 12.44 seconds\noutputs:  {'116': {'images': [{'filename': 'ComfyUI_00004_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png\nComfyUI_00001_.webp\nComfyUI_00002_.png\nComfyUI_00002_.webp\nComfyUI_00003_.png\nComfyUI_00003_.webp\nComfyUI_00004_.png\nRunning workflow\ngot prompt\nExecuting node 94, title: Load Image, class type: LoadImage\nExecuting node 2, title: Apply InstantID, class type: ApplyInstantID\n\u001b[33mWARNING: No face detected in the keypoints image!\u001b[0m\nExecuting node 95, title: Load Image, class type: LoadImage\nExecuting node 74, title: Apply ControlNet, class type: ControlNetApply\nExecuting node 11, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:02,  1.31it/s]\n 50%|█████     | 2/4 [00:01<00:01,  1.30it/s]\n 75%|███████▌  | 3/4 [00:02<00:00,  1.31it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.64it/s]\n100%|██████████| 4/4 [00:02<00:00,  1.50it/s]\nExecuting node 13, title: VAE Decode, class type: VAEDecode\nExecuting node 98, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 2 eyess, 3.7ms\nSpeed: 1.8ms preprocess, 3.7ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((75.32852, 57.404694)) | crop region (225, 172) x 4.551423817459337 -> (1024, 782)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.63it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.55it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.61it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.59it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.16it/s]\nDetailer: segment upscale for ((59.7713, 49.38565)) | crop region (179, 148) x 5.7240480563388365 -> (1024, 847)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  3.55it/s]\n 50%|█████     | 2/4 [00:00<00:00,  3.48it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  3.56it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.54it/s]\n100%|██████████| 4/4 [00:00<00:00,  4.11it/s]\nExecuting node 103, title: Upscale Image By, class type: ImageScaleBy\nExecuting node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 106, title: VAE Encode, class type: VAEEncode\nExecuting node 105, title: KSampler, class type: KSampler\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.01it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.01it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  2.02it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.52it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.31it/s]\nExecuting node 107, title: VAE Decode, class type: VAEDecode\nExecuting node 115, title: FaceDetailer, class type: FaceDetailer\n0: 640x640 2 eyess, 3.8ms\nSpeed: 2.0ms preprocess, 3.8ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640)\nDetailer: segment upscale for ((109.00989, 86.495056)) | crop region (327, 259) x 3.133087209323432 -> (1024, 811)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  5.19it/s]\n 50%|█████     | 2/4 [00:00<00:00,  5.01it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  5.18it/s]\n100%|██████████| 4/4 [00:00<00:00,  6.01it/s]\nDetailer: segment upscale for ((88.2699, 71.82953)) | crop region (264, 215) x 3.879726843832091 -> (1024, 834)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:00,  5.26it/s]\n 50%|█████     | 2/4 [00:00<00:00,  5.03it/s]\n 75%|███████▌  | 3/4 [00:00<00:00,  5.17it/s]\n100%|██████████| 4/4 [00:00<00:00,  6.00it/s]\nExecuting node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments\nExecuting node 116, title: Save Image, class type: SaveImage\nPrompt executed in 12.44 seconds\noutputs:  {'116': {'images': [{'filename': 'ComfyUI_00005_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png\nComfyUI_00001_.webp\nComfyUI_00002_.png\nComfyUI_00002_.webp\nComfyUI_00003_.png\nComfyUI_00003_.webp\nComfyUI_00004_.png\nComfyUI_00004_.webp\nComfyUI_00005_.png",
  "metrics": {
    "predict_time": 63.163449378,
    "total_time": 84.767715
  },
  "output": [
    "https://replicate.delivery/xezq/Y1WvbO3AmbIUChf8egw5rTdTUCYTe3qFMZ03PIKNIYmlEArnA/ComfyUI_00001_.webp",
    "https://replicate.delivery/xezq/CU906Jf1EgzYOaaHzrpzkbF4GNjfDcQxeUCheTScphofTAseE/ComfyUI_00002_.webp",
    "https://replicate.delivery/xezq/e7VU96fF5whOa0Md4xpSQXDwDam2M5asDR68q6fvcAgTFArnA/ComfyUI_00003_.webp",
    "https://replicate.delivery/xezq/ICHi7tvdo0KCDpYQSAdt2gbgW13OH7FIyfpEPCZ40JNbBw6JA/ComfyUI_00004_.webp",
    "https://replicate.delivery/xezq/TOVBIdLIP6rPLdn4HUtnZHyvHwBAaXzCNUWenllOPD8hBw6JA/ComfyUI_00005_.webp"
  ],
  "started_at": "2024-11-28T11:05:40.284265Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-2lj43macmr2awvtwmwuu3qkwgbakf3zku5znyfq5rfz5cvfw2hna",
    "get": "https://api.replicate.com/v1/predictions/84ny6930b1rm80cke9sbvahyrr",
    "cancel": "https://api.replicate.com/v1/predictions/84ny6930b1rm80cke9sbvahyrr/cancel"
  },
  "version": "9c77a3c2f884193fcee4d89645f02a0b9def9434f9e03cb98460456b831c8772"
}

Generated in

63.2 seconds

Tweak it ShareReport

Random seed set to: 3565209131
Running workflow
got prompt
Executing node 7, title: Load Image, class type: LoadImage
Executing node 52, title: IPAdapter Advanced, class type: IPAdapterAdvanced
Executing node 9, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode
Executing node 94, title: Load Image, class type: LoadImage
Executing node 2, title: Apply InstantID, class type: ApplyInstantID
WARNING: No face detected in the keypoints image!
Executing node 95, title: Load Image, class type: LoadImage
Executing node 74, title: Apply ControlNet, class type: ControlNetApply
Executing node 11, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:02,  1.29it/s]
 50%|█████     | 2/4 [00:01<00:01,  1.28it/s]
 75%|███████▌  | 3/4 [00:02<00:00,  1.29it/s]
100%|██████████| 4/4 [00:02<00:00,  1.62it/s]
100%|██████████| 4/4 [00:02<00:00,  1.48it/s]
Executing node 13, title: VAE Decode, class type: VAEDecode
Executing node 98, title: FaceDetailer, class type: FaceDetailer
0: 640x640 2 eyess, 4.1ms
Speed: 1.8ms preprocess, 4.1ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((73.86212, 55.299133)) | crop region (221, 165) x 4.635402991449178 -> (1024, 764)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.63it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.55it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.62it/s]
100%|██████████| 4/4 [00:00<00:00,  4.59it/s]
100%|██████████| 4/4 [00:00<00:00,  4.17it/s]
Detailer: segment upscale for ((73.732666, 51.800705)) | crop region (221, 155) x 4.634272994204666 -> (1024, 718)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.63it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.56it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.62it/s]
100%|██████████| 4/4 [00:00<00:00,  4.60it/s]
100%|██████████| 4/4 [00:00<00:00,  4.17it/s]
Executing node 103, title: Upscale Image By, class type: ImageScaleBy
Executing node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 106, title: VAE Encode, class type: VAEEncode
Executing node 105, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:01,  2.01it/s]
 50%|█████     | 2/4 [00:00<00:00,  2.02it/s]
 75%|███████▌  | 3/4 [00:01<00:00,  2.03it/s]
100%|██████████| 4/4 [00:01<00:00,  2.52it/s]
100%|██████████| 4/4 [00:01<00:00,  2.31it/s]
Executing node 107, title: VAE Decode, class type: VAEDecode
Executing node 115, title: FaceDetailer, class type: FaceDetailer
0: 640x640 2 eyess, 3.7ms
Speed: 2.0ms preprocess, 3.7ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((113.00043, 83.53461)) | crop region (339, 250) x 3.0213239563679735 -> (1024, 755)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  5.35it/s]
 50%|█████     | 2/4 [00:00<00:00,  5.05it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  5.21it/s]
100%|██████████| 4/4 [00:00<00:00,  6.05it/s]
Detailer: segment upscale for ((111.63367, 77.24356)) | crop region (334, 231) x 3.0666259557170323 -> (1024, 708)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  5.25it/s]
 50%|█████     | 2/4 [00:00<00:00,  5.11it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  5.26it/s]
100%|██████████| 4/4 [00:00<00:00,  6.08it/s]
Executing node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 116, title: Save Image, class type: SaveImage
Prompt executed in 13.72 seconds
outputs:  {'116': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png
Running workflow
got prompt
Executing node 94, title: Load Image, class type: LoadImage
Executing node 2, title: Apply InstantID, class type: ApplyInstantID
WARNING: No face detected in the keypoints image!
Executing node 95, title: Load Image, class type: LoadImage
Executing node 74, title: Apply ControlNet, class type: ControlNetApply
Executing node 11, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:02,  1.29it/s]
 50%|█████     | 2/4 [00:01<00:01,  1.30it/s]
 75%|███████▌  | 3/4 [00:02<00:00,  1.31it/s]
100%|██████████| 4/4 [00:02<00:00,  1.63it/s]
100%|██████████| 4/4 [00:02<00:00,  1.49it/s]
Executing node 13, title: VAE Decode, class type: VAEDecode
Executing node 98, title: FaceDetailer, class type: FaceDetailer
0: 640x640 2 eyess, 3.8ms
Speed: 1.8ms preprocess, 3.8ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((73.45352, 53.77359)) | crop region (220, 161) x 4.654638567808891 -> (1024, 749)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.67it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.58it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.62it/s]
100%|██████████| 4/4 [00:00<00:00,  4.57it/s]
100%|██████████| 4/4 [00:00<00:00,  4.17it/s]
Detailer: segment upscale for ((74.03876, 54.732117)) | crop region (222, 164) x 4.614241534884912 -> (1024, 756)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.60it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.50it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.58it/s]
100%|██████████| 4/4 [00:00<00:00,  4.54it/s]
100%|██████████| 4/4 [00:00<00:00,  4.12it/s]
Executing node 103, title: Upscale Image By, class type: ImageScaleBy
Executing node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 106, title: VAE Encode, class type: VAEEncode
Requested to load SDXL
Loading 1 new model
Executing node 105, title: KSampler, class type: KSampler
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:01,  2.02it/s]
 50%|█████     | 2/4 [00:00<00:00,  2.02it/s]
 75%|███████▌  | 3/4 [00:01<00:00,  2.03it/s]
100%|██████████| 4/4 [00:01<00:00,  2.53it/s]
100%|██████████| 4/4 [00:01<00:00,  2.32it/s]
Executing node 107, title: VAE Decode, class type: VAEDecode
Executing node 115, title: FaceDetailer, class type: FaceDetailer
0: 640x640 2 eyess, 3.7ms
Speed: 2.0ms preprocess, 3.7ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((112.757385, 81.501495)) | crop region (338, 244) x 3.0305575839970316 -> (1024, 739)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  5.31it/s]
 50%|█████     | 2/4 [00:00<00:00,  5.14it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  5.28it/s]
100%|██████████| 4/4 [00:00<00:00,  6.11it/s]
Detailer: segment upscale for ((108.96271, 81.140656)) | crop region (326, 243) x 3.142738857900158 -> (1024, 763)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  5.26it/s]
 50%|█████     | 2/4 [00:00<00:00,  5.10it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  5.24it/s]
100%|██████████| 4/4 [00:00<00:00,  6.06it/s]
Executing node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 116, title: Save Image, class type: SaveImage
Prompt executed in 12.02 seconds
outputs:  {'116': {'images': [{'filename': 'ComfyUI_00002_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png
ComfyUI_00001_.webp
ComfyUI_00002_.png
Running workflow
got prompt
Executing node 94, title: Load Image, class type: LoadImage
Executing node 2, title: Apply InstantID, class type: ApplyInstantID
WARNING: No face detected in the keypoints image!
Executing node 95, title: Load Image, class type: LoadImage
Executing node 74, title: Apply ControlNet, class type: ControlNetApply
Executing node 11, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:02,  1.30it/s]
 50%|█████     | 2/4 [00:01<00:01,  1.30it/s]
 75%|███████▌  | 3/4 [00:02<00:00,  1.22it/s]
100%|██████████| 4/4 [00:02<00:00,  1.55it/s]
100%|██████████| 4/4 [00:02<00:00,  1.43it/s]
Executing node 13, title: VAE Decode, class type: VAEDecode
Executing node 98, title: FaceDetailer, class type: FaceDetailer
0: 640x640 1 eyes, 3.8ms
Speed: 1.9ms preprocess, 3.8ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((61.96982, 72.26677)) | crop region (185, 216) x 4.74236357326829 -> (877, 1024)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:01,  2.91it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.18it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.37it/s]
100%|██████████| 4/4 [00:01<00:00,  4.34it/s]
100%|██████████| 4/4 [00:01<00:00,  3.84it/s]
Executing node 103, title: Upscale Image By, class type: ImageScaleBy
Executing node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 106, title: VAE Encode, class type: VAEEncode
Executing node 105, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:01,  1.72it/s]
 50%|█████     | 2/4 [00:01<00:01,  1.89it/s]
 75%|███████▌  | 3/4 [00:01<00:00,  1.95it/s]
100%|██████████| 4/4 [00:01<00:00,  2.45it/s]
100%|██████████| 4/4 [00:01<00:00,  2.20it/s]
Executing node 107, title: VAE Decode, class type: VAEDecode
Executing node 115, title: FaceDetailer, class type: FaceDetailer
0: 640x640 1 eyes, 3.8ms
Speed: 2.0ms preprocess, 3.8ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((90.188965, 103.0957)) | crop region (270, 309) x 3.3155228542930626 -> (895, 1024)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  4.20it/s]
 50%|█████     | 2/4 [00:00<00:00,  4.54it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  4.84it/s]
100%|██████████| 4/4 [00:00<00:00,  5.54it/s]
Executing node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 116, title: Save Image, class type: SaveImage
Prompt executed in 10.39 seconds
outputs:  {'116': {'images': [{'filename': 'ComfyUI_00003_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png
ComfyUI_00001_.webp
ComfyUI_00002_.png
ComfyUI_00002_.webp
ComfyUI_00003_.png
Running workflow
got prompt
Executing node 94, title: Load Image, class type: LoadImage
Executing node 2, title: Apply InstantID, class type: ApplyInstantID
WARNING: No face detected in the keypoints image!
Executing node 95, title: Load Image, class type: LoadImage
Executing node 74, title: Apply ControlNet, class type: ControlNetApply
Executing node 11, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:02,  1.03it/s]
 50%|█████     | 2/4 [00:01<00:01,  1.17it/s]
 75%|███████▌  | 3/4 [00:02<00:00,  1.23it/s]
100%|██████████| 4/4 [00:02<00:00,  1.56it/s]
100%|██████████| 4/4 [00:02<00:00,  1.39it/s]
Executing node 13, title: VAE Decode, class type: VAEDecode
Executing node 98, title: FaceDetailer, class type: FaceDetailer
0: 640x640 2 eyess, 3.7ms
Speed: 1.8ms preprocess, 3.7ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((74.9787, 57.678177)) | crop region (224, 173) x 4.572376805496374 -> (1024, 791)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.61it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.42it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.53it/s]
100%|██████████| 4/4 [00:00<00:00,  4.49it/s]
100%|██████████| 4/4 [00:00<00:00,  4.07it/s]
Detailer: segment upscale for ((59.416992, 52.120804)) | crop region (178, 156) x 5.7546297201101035 -> (1024, 897)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.56it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.49it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.56it/s]
100%|██████████| 4/4 [00:00<00:00,  4.52it/s]
100%|██████████| 4/4 [00:00<00:00,  4.10it/s]
Executing node 103, title: Upscale Image By, class type: ImageScaleBy
Executing node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 106, title: VAE Encode, class type: VAEEncode
Executing node 105, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:01,  2.00it/s]
 50%|█████     | 2/4 [00:00<00:00,  2.01it/s]
 75%|███████▌  | 3/4 [00:01<00:00,  2.02it/s]
100%|██████████| 4/4 [00:01<00:00,  2.52it/s]
100%|██████████| 4/4 [00:01<00:00,  2.31it/s]
Executing node 107, title: VAE Decode, class type: VAEDecode
Executing node 115, title: FaceDetailer, class type: FaceDetailer
0: 640x640 2 eyess, 3.7ms
Speed: 2.0ms preprocess, 3.7ms inference, 1.0ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((112.56372, 85.240845)) | crop region (337, 255) x 3.038866800927065 -> (1024, 774)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  5.25it/s]
 50%|█████     | 2/4 [00:00<00:00,  5.05it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  5.19it/s]
100%|██████████| 4/4 [00:00<00:00,  6.02it/s]
Detailer: segment upscale for ((87.10809, 73.62387)) | crop region (261, 220) x 3.924229594016791 -> (1024, 863)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  5.20it/s]
 50%|█████     | 2/4 [00:00<00:00,  5.00it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  5.16it/s]
100%|██████████| 4/4 [00:00<00:00,  5.98it/s]
Executing node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 116, title: Save Image, class type: SaveImage
Prompt executed in 12.44 seconds
outputs:  {'116': {'images': [{'filename': 'ComfyUI_00004_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png
ComfyUI_00001_.webp
ComfyUI_00002_.png
ComfyUI_00002_.webp
ComfyUI_00003_.png
ComfyUI_00003_.webp
ComfyUI_00004_.png
Running workflow
got prompt
Executing node 94, title: Load Image, class type: LoadImage
Executing node 2, title: Apply InstantID, class type: ApplyInstantID
WARNING: No face detected in the keypoints image!
Executing node 95, title: Load Image, class type: LoadImage
Executing node 74, title: Apply ControlNet, class type: ControlNetApply
Executing node 11, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:02,  1.31it/s]
 50%|█████     | 2/4 [00:01<00:01,  1.30it/s]
 75%|███████▌  | 3/4 [00:02<00:00,  1.31it/s]
100%|██████████| 4/4 [00:02<00:00,  1.64it/s]
100%|██████████| 4/4 [00:02<00:00,  1.50it/s]
Executing node 13, title: VAE Decode, class type: VAEDecode
Executing node 98, title: FaceDetailer, class type: FaceDetailer
0: 640x640 2 eyess, 3.7ms
Speed: 1.8ms preprocess, 3.7ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((75.32852, 57.404694)) | crop region (225, 172) x 4.551423817459337 -> (1024, 782)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.63it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.55it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.61it/s]
100%|██████████| 4/4 [00:00<00:00,  4.59it/s]
100%|██████████| 4/4 [00:00<00:00,  4.16it/s]
Detailer: segment upscale for ((59.7713, 49.38565)) | crop region (179, 148) x 5.7240480563388365 -> (1024, 847)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  3.55it/s]
 50%|█████     | 2/4 [00:00<00:00,  3.48it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  3.56it/s]
100%|██████████| 4/4 [00:00<00:00,  4.54it/s]
100%|██████████| 4/4 [00:00<00:00,  4.11it/s]
Executing node 103, title: Upscale Image By, class type: ImageScaleBy
Executing node 109, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 106, title: VAE Encode, class type: VAEEncode
Executing node 105, title: KSampler, class type: KSampler
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:01,  2.01it/s]
 50%|█████     | 2/4 [00:00<00:00,  2.01it/s]
 75%|███████▌  | 3/4 [00:01<00:00,  2.02it/s]
100%|██████████| 4/4 [00:01<00:00,  2.52it/s]
100%|██████████| 4/4 [00:01<00:00,  2.31it/s]
Executing node 107, title: VAE Decode, class type: VAEDecode
Executing node 115, title: FaceDetailer, class type: FaceDetailer
0: 640x640 2 eyess, 3.8ms
Speed: 2.0ms preprocess, 3.8ms inference, 0.9ms postprocess per image at shape (1, 3, 640, 640)
Detailer: segment upscale for ((109.00989, 86.495056)) | crop region (327, 259) x 3.133087209323432 -> (1024, 811)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  5.19it/s]
 50%|█████     | 2/4 [00:00<00:00,  5.01it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  5.18it/s]
100%|██████████| 4/4 [00:00<00:00,  6.01it/s]
Detailer: segment upscale for ((88.2699, 71.82953)) | crop region (264, 215) x 3.879726843832091 -> (1024, 834)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/4 [00:00<?, ?it/s]
 25%|██▌       | 1/4 [00:00<00:00,  5.26it/s]
 50%|█████     | 2/4 [00:00<00:00,  5.03it/s]
 75%|███████▌  | 3/4 [00:00<00:00,  5.17it/s]
100%|██████████| 4/4 [00:00<00:00,  6.00it/s]
Executing node 111, title: Image Filter Adjustments, class type: Image Filter Adjustments
Executing node 116, title: Save Image, class type: SaveImage
Prompt executed in 12.44 seconds
outputs:  {'116': {'images': [{'filename': 'ComfyUI_00005_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
ComfyUI_00001_.png
ComfyUI_00001_.webp
ComfyUI_00002_.png
ComfyUI_00002_.webp
ComfyUI_00003_.png
ComfyUI_00003_.webp
ComfyUI_00004_.png
ComfyUI_00004_.webp
ComfyUI_00005_.png

Examples

View more examples

Run time and cost

This model costs approximately $0.042 to run on Replicate, or 23 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 43 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Follow @fofrAI on X