Prediction

fofr/pulid-lightning:a0321a0c

Model

fofr/pulid-lightning:a0321a0c

ID

89ga3jk5jxrgg0cfbkfvj6hjb0

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

8.6s

Created

11 months ago

Input

width: 1024
height: 1024
prompt: A photo of a person
face_image
face_style: high-fidelity
output_format: webp
output_quality: 80
negative_prompt
checkpoint_model: realistic
number_of_images: 1

{
  "width": 1024,
  "height": 1024,
  "prompt": "A photo of a person",
  "face_image": "https://replicate.delivery/pbxt/Kt8cUyAZgWIqv4GEW38rhHgqhVQp5vKkkvs1xgsaijicnz4b/guy.webp",
  "face_style": "high-fidelity",
  "output_format": "webp",
  "output_quality": 80,
  "negative_prompt": "",
  "checkpoint_model": "realistic",
  "number_of_images": 1
}

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

const output = await replicate.run(
  "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
  {
    input: {
      width: 1024,
      height: 1024,
      prompt: "A photo of a person",
      face_image: "https://replicate.delivery/pbxt/Kt8cUyAZgWIqv4GEW38rhHgqhVQp5vKkkvs1xgsaijicnz4b/guy.webp",
      face_style: "high-fidelity",
      output_format: "webp",
      output_quality: 80,
      negative_prompt: "",
      checkpoint_model: "realistic",
      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/pulid-lightning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    input={
        "width": 1024,
        "height": 1024,
        "prompt": "A photo of a person",
        "face_image": "https://replicate.delivery/pbxt/Kt8cUyAZgWIqv4GEW38rhHgqhVQp5vKkkvs1xgsaijicnz4b/guy.webp",
        "face_style": "high-fidelity",
        "output_format": "webp",
        "output_quality": 80,
        "negative_prompt": "",
        "checkpoint_model": "realistic",
        "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/pulid-lightning 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": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A photo of a person",
      "face_image": "https://replicate.delivery/pbxt/Kt8cUyAZgWIqv4GEW38rhHgqhVQp5vKkkvs1xgsaijicnz4b/guy.webp",
      "face_style": "high-fidelity",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "",
      "checkpoint_model": "realistic",
      "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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382 \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="A photo of a person"' \
  -i 'face_image="https://replicate.delivery/pbxt/Kt8cUyAZgWIqv4GEW38rhHgqhVQp5vKkkvs1xgsaijicnz4b/guy.webp"' \
  -i 'face_style="high-fidelity"' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'negative_prompt=""' \
  -i 'checkpoint_model="realistic"' \
  -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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1024,
      "height": 1024,
      "prompt": "A photo of a person",
      "face_image": "https://replicate.delivery/pbxt/Kt8cUyAZgWIqv4GEW38rhHgqhVQp5vKkkvs1xgsaijicnz4b/guy.webp",
      "face_style": "high-fidelity",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "",
      "checkpoint_model": "realistic",
      "number_of_images": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-09T10:21:44.078988Z",
  "created_at": "2024-05-09T10:21:35.511000Z",
  "data_removed": false,
  "error": null,
  "id": "89ga3jk5jxrgg0cfbkfvj6hjb0",
  "input": {
    "width": 1024,
    "height": 1024,
    "prompt": "A photo of a person",
    "face_image": "https://replicate.delivery/pbxt/Kt8cUyAZgWIqv4GEW38rhHgqhVQp5vKkkvs1xgsaijicnz4b/guy.webp",
    "face_style": "high-fidelity",
    "output_format": "webp",
    "output_quality": 80,
    "negative_prompt": "",
    "checkpoint_model": "realistic",
    "number_of_images": 1
  },
  "logs": "Random seed set to: 3375421544\nChecking inputs\n✅ /tmp/inputs/image.png\n====================================\nChecking weights\n✅ ip-adapter_pulid_sdxl_fp16.safetensors\n✅ dreamshaperXL_lightningDPMSDE.safetensors\n✅ models/antelopev2\n✅ Juggernaut_RunDiffusionPhoto2_Lightning_4Steps.safetensors\n====================================\nRunning workflow\ngot prompt\nExecuting node 4, title: Load Checkpoint, class type: CheckpointLoaderSimple\nmodel_type EPS\nUsing pytorch attention in VAE\nUsing pytorch attention in VAE\nclip missing: ['clip_l.logit_scale', 'clip_l.transformer.text_projection.weight', 'clip_g.logit_scale']\nloaded straight to GPU\nRequested to load SDXL\nLoading 1 new model\nExecuting node 33, title: Apply Pulid, class type: ApplyPulid\nExecuting node 22, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nRequested to load SDXLClipModel\nLoading 1 new model\nExecuting node 23, title: CLIP Text Encode (Prompt), class type: CLIPTextEncode\nExecuting node 3, 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,  1.93it/s]\n 50%|█████     | 2/4 [00:01<00:01,  1.84it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  1.90it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.41it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.19it/s]\nRequested to load AutoencoderKL\nLoading 1 new model\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 47, title: Save Image, class type: SaveImage\nPrompt executed in 6.29 seconds\noutputs:  {'47': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 8.531323,
    "total_time": 8.567988
  },
  "output": [
    "https://replicate.delivery/pbxt/g2Kybo6t34pCJ5zSewsh6ZiFKHeA23MlbYqmBVpMARy3WlySA/ComfyUI_00001_.webp"
  ],
  "started_at": "2024-05-09T10:21:35.547665Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/89ga3jk5jxrgg0cfbkfvj6hjb0",
    "cancel": "https://api.replicate.com/v1/predictions/89ga3jk5jxrgg0cfbkfvj6hjb0/cancel"
  },
  "version": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382"
}

Generated in

8.5 seconds

Tweak it ShareReport

Prediction

fofr/pulid-lightning:a0321a0c

Model

fofr/pulid-lightning:a0321a0c

ID

fdjhdp59rsrgj0cfbkgb70mt94

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

4.3s

Created

11 months ago

Input

width: 1152
height: 768
prompt: A screenshot of a person in a video game, unreal engine, ps5
face_image
face_style: high-fidelity
output_format: webp
output_quality: 80
negative_prompt: photo, photography
checkpoint_model: artistic
number_of_images: 1

{
  "width": 1152,
  "height": 768,
  "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
  "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
  "face_style": "high-fidelity",
  "output_format": "webp",
  "output_quality": 80,
  "negative_prompt": "photo, photography",
  "checkpoint_model": "artistic",
  "number_of_images": 1
}

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

const output = await replicate.run(
  "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
  {
    input: {
      width: 1152,
      height: 768,
      prompt: "A screenshot of a person in a video game, unreal engine, ps5",
      face_image: "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
      face_style: "high-fidelity",
      output_format: "webp",
      output_quality: 80,
      negative_prompt: "photo, photography",
      checkpoint_model: "artistic",
      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/pulid-lightning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    input={
        "width": 1152,
        "height": 768,
        "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
        "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
        "face_style": "high-fidelity",
        "output_format": "webp",
        "output_quality": 80,
        "negative_prompt": "photo, photography",
        "checkpoint_model": "artistic",
        "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/pulid-lightning 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": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    "input": {
      "width": 1152,
      "height": 768,
      "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
      "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
      "face_style": "high-fidelity",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "photo, photography",
      "checkpoint_model": "artistic",
      "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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382 \
  -i 'width=1152' \
  -i 'height=768' \
  -i 'prompt="A screenshot of a person in a video game, unreal engine, ps5"' \
  -i 'face_image="https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp"' \
  -i 'face_style="high-fidelity"' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'negative_prompt="photo, photography"' \
  -i 'checkpoint_model="artistic"' \
  -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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1152,
      "height": 768,
      "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
      "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
      "face_style": "high-fidelity",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "photo, photography",
      "checkpoint_model": "artistic",
      "number_of_images": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-09T10:23:02.845388Z",
  "created_at": "2024-05-09T10:22:58.502000Z",
  "data_removed": false,
  "error": null,
  "id": "fdjhdp59rsrgj0cfbkgb70mt94",
  "input": {
    "width": 1152,
    "height": 768,
    "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
    "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
    "face_style": "high-fidelity",
    "output_format": "webp",
    "output_quality": 80,
    "negative_prompt": "photo, photography",
    "checkpoint_model": "artistic",
    "number_of_images": 1
  },
  "logs": "Random seed set to: 559882634\nChecking inputs\n✅ /tmp/inputs/image.png\n====================================\nChecking weights\n✅ Juggernaut_RunDiffusionPhoto2_Lightning_4Steps.safetensors\n✅ models/antelopev2\n✅ ProteusV0.4-Lighting.safetensors\n✅ ip-adapter_pulid_sdxl_fp16.safetensors\n✅ dreamshaperXL_lightningDPMSDE.safetensors\n====================================\nRunning workflow\ngot prompt\nExecuting node 3, title: KSampler, class type: KSampler\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.18it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.09it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  2.14it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.73it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.47it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 47, title: Save Image, class type: SaveImage\nPrompt executed in 1.95 seconds\noutputs:  {'47': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 4.302588,
    "total_time": 4.343388
  },
  "output": [
    "https://replicate.delivery/pbxt/3nXWaSvDV9pFHtyOsWxScx9kfrZegzN4BbQ3z6LOie9MwKllA/ComfyUI_00001_.webp"
  ],
  "started_at": "2024-05-09T10:22:58.542800Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/fdjhdp59rsrgj0cfbkgb70mt94",
    "cancel": "https://api.replicate.com/v1/predictions/fdjhdp59rsrgj0cfbkgb70mt94/cancel"
  },
  "version": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382"
}

Generated in

4.3 seconds

Tweak it ShareReport

Prediction

fofr/pulid-lightning:a0321a0c

Model

fofr/pulid-lightning:a0321a0c

ID

zxkc73drpxrgp0cfbkj8k3rgbc

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

4.2s

Created

11 months ago

Input

width: 1152
height: 768
prompt: A closeup screenshot of a person in a fantasy video game, unreal engine, ps5, snowy forest
face_image
face_style: stylized
output_format: webp
output_quality: 80
negative_prompt: photo, photography
checkpoint_model: artistic
number_of_images: 1

{
  "width": 1152,
  "height": 768,
  "prompt": "A closeup screenshot of a person in a fantasy video game, unreal engine, ps5, snowy forest",
  "face_image": "https://replicate.delivery/pbxt/Kt8i1m6BW6qyFwcfpVhSpafDrNt42L0bN0yfnRR89JTweTE1/0_1.webp",
  "face_style": "stylized",
  "output_format": "webp",
  "output_quality": 80,
  "negative_prompt": "photo, photography",
  "checkpoint_model": "artistic",
  "number_of_images": 1
}

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

const output = await replicate.run(
  "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
  {
    input: {
      width: 1152,
      height: 768,
      prompt: "A closeup screenshot of a person in a fantasy video game, unreal engine, ps5, snowy forest",
      face_image: "https://replicate.delivery/pbxt/Kt8i1m6BW6qyFwcfpVhSpafDrNt42L0bN0yfnRR89JTweTE1/0_1.webp",
      face_style: "stylized",
      output_format: "webp",
      output_quality: 80,
      negative_prompt: "photo, photography",
      checkpoint_model: "artistic",
      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/pulid-lightning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    input={
        "width": 1152,
        "height": 768,
        "prompt": "A closeup screenshot of a person in a fantasy video game, unreal engine, ps5, snowy forest",
        "face_image": "https://replicate.delivery/pbxt/Kt8i1m6BW6qyFwcfpVhSpafDrNt42L0bN0yfnRR89JTweTE1/0_1.webp",
        "face_style": "stylized",
        "output_format": "webp",
        "output_quality": 80,
        "negative_prompt": "photo, photography",
        "checkpoint_model": "artistic",
        "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/pulid-lightning 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": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    "input": {
      "width": 1152,
      "height": 768,
      "prompt": "A closeup screenshot of a person in a fantasy video game, unreal engine, ps5, snowy forest",
      "face_image": "https://replicate.delivery/pbxt/Kt8i1m6BW6qyFwcfpVhSpafDrNt42L0bN0yfnRR89JTweTE1/0_1.webp",
      "face_style": "stylized",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "photo, photography",
      "checkpoint_model": "artistic",
      "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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382 \
  -i 'width=1152' \
  -i 'height=768' \
  -i 'prompt="A closeup screenshot of a person in a fantasy video game, unreal engine, ps5, snowy forest"' \
  -i 'face_image="https://replicate.delivery/pbxt/Kt8i1m6BW6qyFwcfpVhSpafDrNt42L0bN0yfnRR89JTweTE1/0_1.webp"' \
  -i 'face_style="stylized"' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'negative_prompt="photo, photography"' \
  -i 'checkpoint_model="artistic"' \
  -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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1152,
      "height": 768,
      "prompt": "A closeup screenshot of a person in a fantasy video game, unreal engine, ps5, snowy forest",
      "face_image": "https://replicate.delivery/pbxt/Kt8i1m6BW6qyFwcfpVhSpafDrNt42L0bN0yfnRR89JTweTE1/0_1.webp",
      "face_style": "stylized",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "photo, photography",
      "checkpoint_model": "artistic",
      "number_of_images": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-09T10:27:28.627159Z",
  "created_at": "2024-05-09T10:27:24.471000Z",
  "data_removed": false,
  "error": null,
  "id": "zxkc73drpxrgp0cfbkj8k3rgbc",
  "input": {
    "width": 1152,
    "height": 768,
    "prompt": "A closeup screenshot of a person in a fantasy video game, unreal engine, ps5, snowy forest",
    "face_image": "https://replicate.delivery/pbxt/Kt8i1m6BW6qyFwcfpVhSpafDrNt42L0bN0yfnRR89JTweTE1/0_1.webp",
    "face_style": "stylized",
    "output_format": "webp",
    "output_quality": 80,
    "negative_prompt": "photo, photography",
    "checkpoint_model": "artistic",
    "number_of_images": 1
  },
  "logs": "Random seed set to: 1084633989\nChecking inputs\n✅ /tmp/inputs/image.png\n====================================\nChecking weights\n✅ Juggernaut_RunDiffusionPhoto2_Lightning_4Steps.safetensors\n✅ models/antelopev2\n✅ ProteusV0.4-Lighting.safetensors\n✅ ip-adapter_pulid_sdxl_fp16.safetensors\n✅ dreamshaperXL_lightningDPMSDE.safetensors\n====================================\nRunning workflow\ngot prompt\nExecuting node 3, title: KSampler, class type: KSampler\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.23it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.14it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  2.20it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.79it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.53it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 47, title: Save Image, class type: SaveImage\nPrompt executed in 1.93 seconds\noutputs:  {'47': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 4.0836,
    "total_time": 4.156159
  },
  "output": [
    "https://replicate.delivery/pbxt/ugRc6ByBLLZoKFDynsgfyqvZIvvNXnDgNkBagLalPNpHuSZJA/ComfyUI_00001_.webp"
  ],
  "started_at": "2024-05-09T10:27:24.543559Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zxkc73drpxrgp0cfbkj8k3rgbc",
    "cancel": "https://api.replicate.com/v1/predictions/zxkc73drpxrgp0cfbkj8k3rgbc/cancel"
  },
  "version": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382"
}

Generated in

4.1 seconds

Tweak it ShareReport

Prediction

fofr/pulid-lightning:a0321a0c

Model

fofr/pulid-lightning:a0321a0c

ID

hy1be1dvcdrgj0cfbkjt2cdwmg

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

3.7s

Created

11 months ago

Input

width: 1152
height: 768
prompt: A screenshot of a person in a video game, unreal engine, ps5
face_image
face_style: stylized
output_format: webp
output_quality: 80
negative_prompt: photo, photography
checkpoint_model: artistic
number_of_images: 1

{
  "width": 1152,
  "height": 768,
  "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
  "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
  "face_style": "stylized",
  "output_format": "webp",
  "output_quality": 80,
  "negative_prompt": "photo, photography",
  "checkpoint_model": "artistic",
  "number_of_images": 1
}

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

const output = await replicate.run(
  "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
  {
    input: {
      width: 1152,
      height: 768,
      prompt: "A screenshot of a person in a video game, unreal engine, ps5",
      face_image: "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
      face_style: "stylized",
      output_format: "webp",
      output_quality: 80,
      negative_prompt: "photo, photography",
      checkpoint_model: "artistic",
      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/pulid-lightning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    input={
        "width": 1152,
        "height": 768,
        "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
        "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
        "face_style": "stylized",
        "output_format": "webp",
        "output_quality": 80,
        "negative_prompt": "photo, photography",
        "checkpoint_model": "artistic",
        "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/pulid-lightning 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": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    "input": {
      "width": 1152,
      "height": 768,
      "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
      "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
      "face_style": "stylized",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "photo, photography",
      "checkpoint_model": "artistic",
      "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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382 \
  -i 'width=1152' \
  -i 'height=768' \
  -i 'prompt="A screenshot of a person in a video game, unreal engine, ps5"' \
  -i 'face_image="https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp"' \
  -i 'face_style="stylized"' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'negative_prompt="photo, photography"' \
  -i 'checkpoint_model="artistic"' \
  -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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1152,
      "height": 768,
      "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
      "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
      "face_style": "stylized",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "photo, photography",
      "checkpoint_model": "artistic",
      "number_of_images": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-09T10:28:34.389205Z",
  "created_at": "2024-05-09T10:28:30.691000Z",
  "data_removed": false,
  "error": null,
  "id": "hy1be1dvcdrgj0cfbkjt2cdwmg",
  "input": {
    "width": 1152,
    "height": 768,
    "prompt": "A screenshot of a person in a video game, unreal engine, ps5",
    "face_image": "https://replicate.delivery/pbxt/Kt8dp9R5JbK7ixrWbjM3fTXUiz4t0fi4JOSqyRkReHrMgYjm/guy.webp",
    "face_style": "stylized",
    "output_format": "webp",
    "output_quality": 80,
    "negative_prompt": "photo, photography",
    "checkpoint_model": "artistic",
    "number_of_images": 1
  },
  "logs": "Random seed set to: 763561143\nChecking inputs\n✅ /tmp/inputs/image.png\n====================================\nChecking weights\n✅ Juggernaut_RunDiffusionPhoto2_Lightning_4Steps.safetensors\n✅ models/antelopev2\n✅ ProteusV0.4-Lighting.safetensors\n✅ ip-adapter_pulid_sdxl_fp16.safetensors\n✅ dreamshaperXL_lightningDPMSDE.safetensors\n====================================\nRunning workflow\ngot prompt\nExecuting node 3, title: KSampler, class type: KSampler\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.24it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.16it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  2.22it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.81it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.55it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 47, title: Save Image, class type: SaveImage\nPrompt executed in 1.92 seconds\noutputs:  {'47': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 3.656876,
    "total_time": 3.698205
  },
  "output": [
    "https://replicate.delivery/pbxt/lkVnJA1sQWpdAt5Yphp9W8yVKLeNZkY1A0rHWk2YjFgouSZJA/ComfyUI_00001_.webp"
  ],
  "started_at": "2024-05-09T10:28:30.732329Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/hy1be1dvcdrgj0cfbkjt2cdwmg",
    "cancel": "https://api.replicate.com/v1/predictions/hy1be1dvcdrgj0cfbkjt2cdwmg/cancel"
  },
  "version": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382"
}

Generated in

3.7 seconds

Tweak it ShareReport

Prediction

fofr/pulid-lightning:a0321a0c

Model

fofr/pulid-lightning:a0321a0c

ID

bxp0f23dtsrgj0cfbkrsb4zmqw

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

4.4s

Created

11 months ago by @fofr

Input

width: 1152
height: 768
prompt: A screenshot of a person in an italian renaissance video game, unreal engine, ps5
face_image
face_style: high-fidelity
output_format: webp
output_quality: 80
negative_prompt: photo, photography
checkpoint_model: artistic
number_of_images: 1

{
  "width": 1152,
  "height": 768,
  "prompt": "A screenshot of a person in an italian renaissance video game, unreal engine, ps5",
  "face_image": "https://replicate.delivery/pbxt/Kt8v9siysiEOn2p7zTlH7ZUceiPxUCxtC24wSPoJcP5j7vCl/mona-lisa.png",
  "face_style": "high-fidelity",
  "output_format": "webp",
  "output_quality": 80,
  "negative_prompt": "photo, photography",
  "checkpoint_model": "artistic",
  "number_of_images": 1
}

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

const output = await replicate.run(
  "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
  {
    input: {
      width: 1152,
      height: 768,
      prompt: "A screenshot of a person in an italian renaissance video game, unreal engine, ps5",
      face_image: "https://replicate.delivery/pbxt/Kt8v9siysiEOn2p7zTlH7ZUceiPxUCxtC24wSPoJcP5j7vCl/mona-lisa.png",
      face_style: "high-fidelity",
      output_format: "webp",
      output_quality: 80,
      negative_prompt: "photo, photography",
      checkpoint_model: "artistic",
      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/pulid-lightning using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "fofr/pulid-lightning:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    input={
        "width": 1152,
        "height": 768,
        "prompt": "A screenshot of a person in an italian renaissance video game, unreal engine, ps5",
        "face_image": "https://replicate.delivery/pbxt/Kt8v9siysiEOn2p7zTlH7ZUceiPxUCxtC24wSPoJcP5j7vCl/mona-lisa.png",
        "face_style": "high-fidelity",
        "output_format": "webp",
        "output_quality": 80,
        "negative_prompt": "photo, photography",
        "checkpoint_model": "artistic",
        "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/pulid-lightning 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": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382",
    "input": {
      "width": 1152,
      "height": 768,
      "prompt": "A screenshot of a person in an italian renaissance video game, unreal engine, ps5",
      "face_image": "https://replicate.delivery/pbxt/Kt8v9siysiEOn2p7zTlH7ZUceiPxUCxtC24wSPoJcP5j7vCl/mona-lisa.png",
      "face_style": "high-fidelity",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "photo, photography",
      "checkpoint_model": "artistic",
      "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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382 \
  -i 'width=1152' \
  -i 'height=768' \
  -i 'prompt="A screenshot of a person in an italian renaissance video game, unreal engine, ps5"' \
  -i 'face_image="https://replicate.delivery/pbxt/Kt8v9siysiEOn2p7zTlH7ZUceiPxUCxtC24wSPoJcP5j7vCl/mona-lisa.png"' \
  -i 'face_style="high-fidelity"' \
  -i 'output_format="webp"' \
  -i 'output_quality=80' \
  -i 'negative_prompt="photo, photography"' \
  -i 'checkpoint_model="artistic"' \
  -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/pulid-lightning@sha256:a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "width": 1152,
      "height": 768,
      "prompt": "A screenshot of a person in an italian renaissance video game, unreal engine, ps5",
      "face_image": "https://replicate.delivery/pbxt/Kt8v9siysiEOn2p7zTlH7ZUceiPxUCxtC24wSPoJcP5j7vCl/mona-lisa.png",
      "face_style": "high-fidelity",
      "output_format": "webp",
      "output_quality": 80,
      "negative_prompt": "photo, photography",
      "checkpoint_model": "artistic",
      "number_of_images": 1
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-05-09T10:41:21.645641Z",
  "created_at": "2024-05-09T10:41:17.270000Z",
  "data_removed": false,
  "error": null,
  "id": "bxp0f23dtsrgj0cfbkrsb4zmqw",
  "input": {
    "width": 1152,
    "height": 768,
    "prompt": "A screenshot of a person in an italian renaissance video game, unreal engine, ps5",
    "face_image": "https://replicate.delivery/pbxt/Kt8v9siysiEOn2p7zTlH7ZUceiPxUCxtC24wSPoJcP5j7vCl/mona-lisa.png",
    "face_style": "high-fidelity",
    "output_format": "webp",
    "output_quality": 80,
    "negative_prompt": "photo, photography",
    "checkpoint_model": "artistic",
    "number_of_images": 1
  },
  "logs": "Random seed set to: 3366515947\nChecking inputs\n✅ /tmp/inputs/image.png\n====================================\nChecking weights\n✅ ip-adapter_pulid_sdxl_fp16.safetensors\n✅ dreamshaperXL_lightningDPMSDE.safetensors\n✅ ProteusV0.4-Lighting.safetensors\n✅ models/antelopev2\n====================================\nRunning workflow\ngot prompt\nExecuting node 3, title: KSampler, class type: KSampler\n  0%|          | 0/4 [00:00<?, ?it/s]\n 25%|██▌       | 1/4 [00:00<00:01,  2.19it/s]\n 50%|█████     | 2/4 [00:00<00:00,  2.14it/s]\n 75%|███████▌  | 3/4 [00:01<00:00,  2.18it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.77it/s]\n100%|██████████| 4/4 [00:01<00:00,  2.51it/s]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 47, title: Save Image, class type: SaveImage\nPrompt executed in 1.94 seconds\noutputs:  {'47': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 4.33157,
    "total_time": 4.375641
  },
  "output": [
    "https://replicate.delivery/pbxt/ei78992rJky7SifqGCXyHrt16ejR8RVhpCThAix9h0HhSLllA/ComfyUI_00001_.webp"
  ],
  "started_at": "2024-05-09T10:41:17.314071Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/bxp0f23dtsrgj0cfbkrsb4zmqw",
    "cancel": "https://api.replicate.com/v1/predictions/bxp0f23dtsrgj0cfbkrsb4zmqw/cancel"
  },
  "version": "a0321a0cef20aa9e0828f8a9873dc3fd019266bc929f2fb8d70b76d52e122382"
}

Generated in

4.3 seconds

Tweak it ShareReport

fofr / pulid-lightning

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Prediction

Input

Output

Logs (89ga3jk5jxrgg0cfbkfvj6hjb0)

Logs (fdjhdp59rsrgj0cfbkgb70mt94)

Logs (zxkc73drpxrgp0cfbkj8k3rgbc)

Logs (hy1be1dvcdrgj0cfbkjt2cdwmg)

Logs (bxp0f23dtsrgj0cfbkrsb4zmqw)