Prediction

4f4atn3blzh57avgawg3gqt3yu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

12.3s

Created

over 1 year ago

Input

steps: 20
width: 1024
height: 1024
prompt: a bright abstract painting of a cyborg
image_1
image_2
base_model: albedobaseXL_v13.safetensors
batch_size: 1
merge_strength: 0.92
negative_prompt
added_merge_noise: 0

{
  "steps": 20,
  "width": 1024,
  "height": 1024,
  "prompt": "a bright abstract painting of a cyborg",
  "image_1": "https://replicate.delivery/pbxt/KRyveMWjBWpI9NR6GuK1B1GoJMUhlvfUEa0yq6RWBqz3HaP5/ComfyUI_00319_.png",
  "image_2": "https://replicate.delivery/pbxt/KRyveLQ82s8OdaAqUNIV5kbH3dPIdrGTqO9ka1IK5TecpWz0/output-0.png",
  "base_model": "albedobaseXL_v13.safetensors",
  "batch_size": 1,
  "merge_strength": 0.92,
  "negative_prompt": "",
  "added_merge_noise": 0
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
  {
    input: {
      steps: 20,
      width: 1024,
      height: 1024,
      prompt: "a bright abstract painting of a cyborg",
      image_1: "https://replicate.delivery/pbxt/KRyveMWjBWpI9NR6GuK1B1GoJMUhlvfUEa0yq6RWBqz3HaP5/ComfyUI_00319_.png",
      image_2: "https://replicate.delivery/pbxt/KRyveLQ82s8OdaAqUNIV5kbH3dPIdrGTqO9ka1IK5TecpWz0/output-0.png",
      base_model: "albedobaseXL_v13.safetensors",
      batch_size: 1,
      merge_strength: 0.92,
      negative_prompt: "",
      added_merge_noise: 0
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    input={
        "steps": 20,
        "width": 1024,
        "height": 1024,
        "prompt": "a bright abstract painting of a cyborg",
        "image_1": "https://replicate.delivery/pbxt/KRyveMWjBWpI9NR6GuK1B1GoJMUhlvfUEa0yq6RWBqz3HaP5/ComfyUI_00319_.png",
        "image_2": "https://replicate.delivery/pbxt/KRyveLQ82s8OdaAqUNIV5kbH3dPIdrGTqO9ka1IK5TecpWz0/output-0.png",
        "base_model": "albedobaseXL_v13.safetensors",
        "batch_size": 1,
        "merge_strength": 0.92,
        "negative_prompt": "",
        "added_merge_noise": 0
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/image-merge-sdxl 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": "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    "input": {
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "a bright abstract painting of a cyborg",
      "image_1": "https://replicate.delivery/pbxt/KRyveMWjBWpI9NR6GuK1B1GoJMUhlvfUEa0yq6RWBqz3HaP5/ComfyUI_00319_.png",
      "image_2": "https://replicate.delivery/pbxt/KRyveLQ82s8OdaAqUNIV5kbH3dPIdrGTqO9ka1IK5TecpWz0/output-0.png",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 0.92,
      "negative_prompt": "",
      "added_merge_noise": 0
    }
  }' \
  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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75 \
  -i 'steps=20' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="a bright abstract painting of a cyborg"' \
  -i 'image_1="https://replicate.delivery/pbxt/KRyveMWjBWpI9NR6GuK1B1GoJMUhlvfUEa0yq6RWBqz3HaP5/ComfyUI_00319_.png"' \
  -i 'image_2="https://replicate.delivery/pbxt/KRyveLQ82s8OdaAqUNIV5kbH3dPIdrGTqO9ka1IK5TecpWz0/output-0.png"' \
  -i 'base_model="albedobaseXL_v13.safetensors"' \
  -i 'batch_size=1' \
  -i 'merge_strength=0.92' \
  -i 'negative_prompt=""' \
  -i 'added_merge_noise=0'

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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "a bright abstract painting of a cyborg",
      "image_1": "https://replicate.delivery/pbxt/KRyveMWjBWpI9NR6GuK1B1GoJMUhlvfUEa0yq6RWBqz3HaP5/ComfyUI_00319_.png",
      "image_2": "https://replicate.delivery/pbxt/KRyveLQ82s8OdaAqUNIV5kbH3dPIdrGTqO9ka1IK5TecpWz0/output-0.png",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 0.92,
      "negative_prompt": "",
      "added_merge_noise": 0
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-02-22T22:13:04.454822Z",
  "created_at": "2024-02-22T22:12:52.171142Z",
  "data_removed": false,
  "error": null,
  "id": "4f4atn3blzh57avgawg3gqt3yu",
  "input": {
    "steps": 20,
    "width": 1024,
    "height": 1024,
    "prompt": "a bright abstract painting of a cyborg",
    "image_1": "https://replicate.delivery/pbxt/KRyveMWjBWpI9NR6GuK1B1GoJMUhlvfUEa0yq6RWBqz3HaP5/ComfyUI_00319_.png",
    "image_2": "https://replicate.delivery/pbxt/KRyveLQ82s8OdaAqUNIV5kbH3dPIdrGTqO9ka1IK5TecpWz0/output-0.png",
    "base_model": "albedobaseXL_v13.safetensors",
    "batch_size": 1,
    "merge_strength": 0.92,
    "negative_prompt": "",
    "added_merge_noise": 0
  },
  "logs": "Random seed set to: 3573528874\nChecking weights\n✅ albedobaseXL_v13.safetensors\n✅ model.sdxl.safetensors\n✅ ip-adapter_sdxl.safetensors\n====================================\nChecking inputs\n✅ /tmp/inputs/left.png\n✅ /tmp/inputs/right.png\n====================================\nRunning workflow\ngot prompt\nExecuting node 4, title: Efficient Loader, class type: Efficient Loader\nRequested to load SDXLClipModel\nLoading 1 new model\n----------------------------------------\n\u001b[36mEfficient Loader Models Cache:\u001b[0m\nCkpt:\n[1] albedobaseXL_v13\nExecuting node 15, title: Apply IPAdapter, class type: IPAdapterApply\nExecuting node 8, title: KSampler (Efficient), class type: KSampler (Efficient)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:04,  4.40it/s]\n 10%|█         | 2/20 [00:00<00:04,  4.25it/s]\n 15%|█▌        | 3/20 [00:00<00:04,  4.20it/s]\n 20%|██        | 4/20 [00:00<00:03,  4.17it/s]\n 25%|██▌       | 5/20 [00:01<00:03,  4.16it/s]\n 30%|███       | 6/20 [00:01<00:03,  4.13it/s]\n 35%|███▌      | 7/20 [00:01<00:03,  4.10it/s]\n 40%|████      | 8/20 [00:01<00:02,  4.11it/s]\n 45%|████▌     | 9/20 [00:02<00:02,  4.11it/s]\n 50%|█████     | 10/20 [00:02<00:02,  4.02it/s]\n 55%|█████▌    | 11/20 [00:02<00:02,  4.07it/s]\n 60%|██████    | 12/20 [00:02<00:01,  4.09it/s]\n 65%|██████▌   | 13/20 [00:03<00:01,  4.12it/s]\n 70%|███████   | 14/20 [00:03<00:01,  4.15it/s]\n 75%|███████▌  | 15/20 [00:03<00:01,  4.15it/s]\n 80%|████████  | 16/20 [00:03<00:00,  4.17it/s]\n 85%|████████▌ | 17/20 [00:04<00:00,  4.18it/s]\n 90%|█████████ | 18/20 [00:04<00:00,  4.20it/s]\n 95%|█████████▌| 19/20 [00:04<00:00,  4.32it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.44it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.20it/s]\nExecuting node 9, title: Save Image, class type: SaveImage\nPrompt executed in 8.80 seconds\noutputs:  {'8': {'images': []}, '9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 12.203021,
    "total_time": 12.28368
  },
  "output": [
    "https://replicate.delivery/pbxt/NPoOeZCE9WxTIykiejpaQ0eFWKtU3iwrkw1UiXgWqTCcHvykA/ComfyUI_00001_.png"
  ],
  "started_at": "2024-02-22T22:12:52.251801Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/4f4atn3blzh57avgawg3gqt3yu",
    "cancel": "https://api.replicate.com/v1/predictions/4f4atn3blzh57avgawg3gqt3yu/cancel"
  },
  "version": "101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75"
}

Generated in

12.2 seconds

fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75

Random seed set to: 3573528874
Checking weights
✅ albedobaseXL_v13.safetensors
✅ model.sdxl.safetensors
✅ ip-adapter_sdxl.safetensors
====================================
Checking inputs
✅ /tmp/inputs/left.png
✅ /tmp/inputs/right.png
====================================
Running workflow
got prompt
Executing node 4, title: Efficient Loader, class type: Efficient Loader
Requested to load SDXLClipModel
Loading 1 new model
----------------------------------------
Efficient Loader Models Cache:
Ckpt:
[1] albedobaseXL_v13
Executing node 15, title: Apply IPAdapter, class type: IPAdapterApply
Executing node 8, title: KSampler (Efficient), class type: KSampler (Efficient)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:04,  4.40it/s]
 10%|█         | 2/20 [00:00<00:04,  4.25it/s]
 15%|█▌        | 3/20 [00:00<00:04,  4.20it/s]
 20%|██        | 4/20 [00:00<00:03,  4.17it/s]
 25%|██▌       | 5/20 [00:01<00:03,  4.16it/s]
 30%|███       | 6/20 [00:01<00:03,  4.13it/s]
 35%|███▌      | 7/20 [00:01<00:03,  4.10it/s]
 40%|████      | 8/20 [00:01<00:02,  4.11it/s]
 45%|████▌     | 9/20 [00:02<00:02,  4.11it/s]
 50%|█████     | 10/20 [00:02<00:02,  4.02it/s]
 55%|█████▌    | 11/20 [00:02<00:02,  4.07it/s]
 60%|██████    | 12/20 [00:02<00:01,  4.09it/s]
 65%|██████▌   | 13/20 [00:03<00:01,  4.12it/s]
 70%|███████   | 14/20 [00:03<00:01,  4.15it/s]
 75%|███████▌  | 15/20 [00:03<00:01,  4.15it/s]
 80%|████████  | 16/20 [00:03<00:00,  4.17it/s]
 85%|████████▌ | 17/20 [00:04<00:00,  4.18it/s]
 90%|█████████ | 18/20 [00:04<00:00,  4.20it/s]
 95%|█████████▌| 19/20 [00:04<00:00,  4.32it/s]
100%|██████████| 20/20 [00:04<00:00,  4.44it/s]
100%|██████████| 20/20 [00:04<00:00,  4.20it/s]
Executing node 9, title: Save Image, class type: SaveImage
Prompt executed in 8.80 seconds
outputs:  {'8': {'images': []}, '9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
Contents of /tmp/outputs:
ComfyUI_00001_.png

Prediction

Model

iesqsutbbhssywhlqfhw466fju

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

15.2s

Created

over 1 year ago

Input

steps: 20
width: 1536
height: 1024
prompt: a romantic couple, renaissance painting, masterpiece, ancient
image_1
image_2
base_model: albedobaseXL_v13.safetensors
batch_size: 1
merge_strength: 1
negative_prompt: ugly, broken
added_merge_noise: 0.5

{
  "steps": 20,
  "width": 1536,
  "height": 1024,
  "prompt": "a romantic couple, renaissance painting, masterpiece, ancient",
  "image_1": "https://replicate.delivery/pbxt/KS0DG4acIC7MRzAT9257GkB9LaC8eGMPTAAosmWdQTwztcqc/2023-11-22--15-10-07-u-q1-fofr_a_romantic_scene_1e14107d-d841-4385-a455-ca5d0ab230c3.png",
  "image_2": "https://replicate.delivery/pbxt/KS0DG75waIWc93KWOTvM53XbQCO8jOWeHxTLax6MyZ1qQWv7/2023-11-22--15-09-55-u-q4-fofr_a_scifi_scene_8b3b892c-e95a-45d6-8df9-adba2e7141dc.png",
  "base_model": "albedobaseXL_v13.safetensors",
  "batch_size": 1,
  "merge_strength": 1,
  "negative_prompt": "ugly, broken",
  "added_merge_noise": 0.5
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
  {
    input: {
      steps: 20,
      width: 1536,
      height: 1024,
      prompt: "a romantic couple, renaissance painting, masterpiece, ancient",
      image_1: "https://replicate.delivery/pbxt/KS0DG4acIC7MRzAT9257GkB9LaC8eGMPTAAosmWdQTwztcqc/2023-11-22--15-10-07-u-q1-fofr_a_romantic_scene_1e14107d-d841-4385-a455-ca5d0ab230c3.png",
      image_2: "https://replicate.delivery/pbxt/KS0DG75waIWc93KWOTvM53XbQCO8jOWeHxTLax6MyZ1qQWv7/2023-11-22--15-09-55-u-q4-fofr_a_scifi_scene_8b3b892c-e95a-45d6-8df9-adba2e7141dc.png",
      base_model: "albedobaseXL_v13.safetensors",
      batch_size: 1,
      merge_strength: 1,
      negative_prompt: "ugly, broken",
      added_merge_noise: 0.5
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    input={
        "steps": 20,
        "width": 1536,
        "height": 1024,
        "prompt": "a romantic couple, renaissance painting, masterpiece, ancient",
        "image_1": "https://replicate.delivery/pbxt/KS0DG4acIC7MRzAT9257GkB9LaC8eGMPTAAosmWdQTwztcqc/2023-11-22--15-10-07-u-q1-fofr_a_romantic_scene_1e14107d-d841-4385-a455-ca5d0ab230c3.png",
        "image_2": "https://replicate.delivery/pbxt/KS0DG75waIWc93KWOTvM53XbQCO8jOWeHxTLax6MyZ1qQWv7/2023-11-22--15-09-55-u-q4-fofr_a_scifi_scene_8b3b892c-e95a-45d6-8df9-adba2e7141dc.png",
        "base_model": "albedobaseXL_v13.safetensors",
        "batch_size": 1,
        "merge_strength": 1,
        "negative_prompt": "ugly, broken",
        "added_merge_noise": 0.5
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/image-merge-sdxl 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": "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    "input": {
      "steps": 20,
      "width": 1536,
      "height": 1024,
      "prompt": "a romantic couple, renaissance painting, masterpiece, ancient",
      "image_1": "https://replicate.delivery/pbxt/KS0DG4acIC7MRzAT9257GkB9LaC8eGMPTAAosmWdQTwztcqc/2023-11-22--15-10-07-u-q1-fofr_a_romantic_scene_1e14107d-d841-4385-a455-ca5d0ab230c3.png",
      "image_2": "https://replicate.delivery/pbxt/KS0DG75waIWc93KWOTvM53XbQCO8jOWeHxTLax6MyZ1qQWv7/2023-11-22--15-09-55-u-q4-fofr_a_scifi_scene_8b3b892c-e95a-45d6-8df9-adba2e7141dc.png",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 1,
      "negative_prompt": "ugly, broken",
      "added_merge_noise": 0.5
    }
  }' \
  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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75 \
  -i 'steps=20' \
  -i 'width=1536' \
  -i 'height=1024' \
  -i 'prompt="a romantic couple, renaissance painting, masterpiece, ancient"' \
  -i 'image_1="https://replicate.delivery/pbxt/KS0DG4acIC7MRzAT9257GkB9LaC8eGMPTAAosmWdQTwztcqc/2023-11-22--15-10-07-u-q1-fofr_a_romantic_scene_1e14107d-d841-4385-a455-ca5d0ab230c3.png"' \
  -i 'image_2="https://replicate.delivery/pbxt/KS0DG75waIWc93KWOTvM53XbQCO8jOWeHxTLax6MyZ1qQWv7/2023-11-22--15-09-55-u-q4-fofr_a_scifi_scene_8b3b892c-e95a-45d6-8df9-adba2e7141dc.png"' \
  -i 'base_model="albedobaseXL_v13.safetensors"' \
  -i 'batch_size=1' \
  -i 'merge_strength=1' \
  -i 'negative_prompt="ugly, broken"' \
  -i 'added_merge_noise=0.5'

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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "steps": 20,
      "width": 1536,
      "height": 1024,
      "prompt": "a romantic couple, renaissance painting, masterpiece, ancient",
      "image_1": "https://replicate.delivery/pbxt/KS0DG4acIC7MRzAT9257GkB9LaC8eGMPTAAosmWdQTwztcqc/2023-11-22--15-10-07-u-q1-fofr_a_romantic_scene_1e14107d-d841-4385-a455-ca5d0ab230c3.png",
      "image_2": "https://replicate.delivery/pbxt/KS0DG75waIWc93KWOTvM53XbQCO8jOWeHxTLax6MyZ1qQWv7/2023-11-22--15-09-55-u-q4-fofr_a_scifi_scene_8b3b892c-e95a-45d6-8df9-adba2e7141dc.png",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 1,
      "negative_prompt": "ugly, broken",
      "added_merge_noise": 0.5
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-02-22T23:37:07.622172Z",
  "created_at": "2024-02-22T23:36:52.465821Z",
  "data_removed": false,
  "error": null,
  "id": "iesqsutbbhssywhlqfhw466fju",
  "input": {
    "steps": 20,
    "width": 1536,
    "height": 1024,
    "prompt": "a romantic couple, renaissance painting, masterpiece, ancient",
    "image_1": "https://replicate.delivery/pbxt/KS0DG4acIC7MRzAT9257GkB9LaC8eGMPTAAosmWdQTwztcqc/2023-11-22--15-10-07-u-q1-fofr_a_romantic_scene_1e14107d-d841-4385-a455-ca5d0ab230c3.png",
    "image_2": "https://replicate.delivery/pbxt/KS0DG75waIWc93KWOTvM53XbQCO8jOWeHxTLax6MyZ1qQWv7/2023-11-22--15-09-55-u-q4-fofr_a_scifi_scene_8b3b892c-e95a-45d6-8df9-adba2e7141dc.png",
    "base_model": "albedobaseXL_v13.safetensors",
    "batch_size": 1,
    "merge_strength": 1,
    "negative_prompt": "ugly, broken",
    "added_merge_noise": 0.5
  },
  "logs": "Random seed set to: 2027930354\nChecking weights\n✅ albedobaseXL_v13.safetensors\n✅ model.sdxl.safetensors\n✅ ip-adapter_sdxl.safetensors\n====================================\nChecking inputs\n✅ /tmp/inputs/left.png\n✅ /tmp/inputs/right.png\n====================================\nRunning workflow\ngot prompt\nExecuting node 4, title: Efficient Loader, class type: Efficient Loader\nRequested to load SDXLClipModel\nLoading 1 new model\n----------------------------------------\n\u001b[36mEfficient Loader Models Cache:\u001b[0m\nCkpt:\n[1] albedobaseXL_v13\n\u001b[33mINFO: the IPAdapter reference image is not a square, CLIPImageProcessor will resize and crop it at the center. If the main focus of the picture is not in the middle the result might not be what you are expecting.\u001b[0m\nExecuting node 15, title: Apply IPAdapter, class type: IPAdapterApply\nExecuting node 8, title: KSampler (Efficient), class type: KSampler (Efficient)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:06,  2.98it/s]\n 10%|█         | 2/20 [00:00<00:06,  2.88it/s]\n 15%|█▌        | 3/20 [00:01<00:05,  2.85it/s]\n 20%|██        | 4/20 [00:01<00:05,  2.83it/s]\n 25%|██▌       | 5/20 [00:01<00:05,  2.84it/s]\n 30%|███       | 6/20 [00:02<00:05,  2.76it/s]\n 35%|███▌      | 7/20 [00:02<00:04,  2.77it/s]\n 40%|████      | 8/20 [00:02<00:04,  2.78it/s]\n 45%|████▌     | 9/20 [00:03<00:03,  2.78it/s]\n 50%|█████     | 10/20 [00:03<00:03,  2.79it/s]\n 55%|█████▌    | 11/20 [00:03<00:03,  2.81it/s]\n 60%|██████    | 12/20 [00:04<00:02,  2.76it/s]\n 65%|██████▌   | 13/20 [00:04<00:02,  2.77it/s]\n 70%|███████   | 14/20 [00:05<00:02,  2.79it/s]\n 75%|███████▌  | 15/20 [00:05<00:01,  2.80it/s]\n 80%|████████  | 16/20 [00:05<00:01,  2.81it/s]\n 85%|████████▌ | 17/20 [00:06<00:01,  2.82it/s]\n 90%|█████████ | 18/20 [00:06<00:00,  2.83it/s]\n 95%|█████████▌| 19/20 [00:06<00:00,  2.92it/s]\n100%|██████████| 20/20 [00:07<00:00,  3.00it/s]\n100%|██████████| 20/20 [00:07<00:00,  2.84it/s]\nExecuting node 9, title: Save Image, class type: SaveImage\nPrompt executed in 11.46 seconds\noutputs:  {'8': {'images': []}, '9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 15.11421,
    "total_time": 15.156351
  },
  "output": [
    "https://replicate.delivery/pbxt/wuZk9RFahAJfekLQSc9VlFgMUJfoAVeVf1fAmQ6YJPhtoMWmE/ComfyUI_00001_.png"
  ],
  "started_at": "2024-02-22T23:36:52.507962Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/iesqsutbbhssywhlqfhw466fju",
    "cancel": "https://api.replicate.com/v1/predictions/iesqsutbbhssywhlqfhw466fju/cancel"
  },
  "version": "101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75"
}

Generated in

15.1 seconds

fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75

Random seed set to: 2027930354
Checking weights
✅ albedobaseXL_v13.safetensors
✅ model.sdxl.safetensors
✅ ip-adapter_sdxl.safetensors
====================================
Checking inputs
✅ /tmp/inputs/left.png
✅ /tmp/inputs/right.png
====================================
Running workflow
got prompt
Executing node 4, title: Efficient Loader, class type: Efficient Loader
Requested to load SDXLClipModel
Loading 1 new model
----------------------------------------
Efficient Loader Models Cache:
Ckpt:
[1] albedobaseXL_v13
INFO: the IPAdapter reference image is not a square, CLIPImageProcessor will resize and crop it at the center. If the main focus of the picture is not in the middle the result might not be what you are expecting.
Executing node 15, title: Apply IPAdapter, class type: IPAdapterApply
Executing node 8, title: KSampler (Efficient), class type: KSampler (Efficient)
Requested to load SDXL
Loading 1 new model
  0%|          | 0/20 [00:00<?, ?it/s]
  5%|▌         | 1/20 [00:00<00:06,  2.98it/s]
 10%|█         | 2/20 [00:00<00:06,  2.88it/s]
 15%|█▌        | 3/20 [00:01<00:05,  2.85it/s]
 20%|██        | 4/20 [00:01<00:05,  2.83it/s]
 25%|██▌       | 5/20 [00:01<00:05,  2.84it/s]
 30%|███       | 6/20 [00:02<00:05,  2.76it/s]
 35%|███▌      | 7/20 [00:02<00:04,  2.77it/s]
 40%|████      | 8/20 [00:02<00:04,  2.78it/s]
 45%|████▌     | 9/20 [00:03<00:03,  2.78it/s]
 50%|█████     | 10/20 [00:03<00:03,  2.79it/s]
 55%|█████▌    | 11/20 [00:03<00:03,  2.81it/s]
 60%|██████    | 12/20 [00:04<00:02,  2.76it/s]
 65%|██████▌   | 13/20 [00:04<00:02,  2.77it/s]
 70%|███████   | 14/20 [00:05<00:02,  2.79it/s]
 75%|███████▌  | 15/20 [00:05<00:01,  2.80it/s]
 80%|████████  | 16/20 [00:05<00:01,  2.81it/s]
 85%|████████▌ | 17/20 [00:06<00:01,  2.82it/s]
 90%|█████████ | 18/20 [00:06<00:00,  2.83it/s]
 95%|█████████▌| 19/20 [00:06<00:00,  2.92it/s]
100%|██████████| 20/20 [00:07<00:00,  3.00it/s]
100%|██████████| 20/20 [00:07<00:00,  2.84it/s]
Executing node 9, title: Save Image, class type: SaveImage
Prompt executed in 11.46 seconds
outputs:  {'8': {'images': []}, '9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}
====================================
Contents of /tmp/outputs:
ComfyUI_00001_.png

Prediction

Model

trm4wldb7y6clourcq7dqmfeuu

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

8.2s

Created

over 1 year ago

Input

steps: 20
width: 1024
height: 1024
prompt: an abstract painting of a cat
image_1
image_2
base_model: albedobaseXL_v13.safetensors
batch_size: 1
merge_strength: 1
negative_prompt: black and white
added_merge_noise: 0.8

{
  "steps": 20,
  "width": 1024,
  "height": 1024,
  "prompt": "an abstract painting of a cat",
  "image_1": "https://replicate.delivery/pbxt/KRz8qs41ipSGwqo9gai74Dk3rTB0ihKMBqJUvNnQQYyfFD69/fofr_svg_black_and_white_cat_doodle_style_thick_outlines_8c7e447c-da1e-46b2-a7e1-2025418f2050.webp",
  "image_2": "https://replicate.delivery/pbxt/KRz8r8hSyMNcWLgbcKMCDhvoTQX1KqFKCYvVXeSPfwTf4783/bafkreidar5nwcwmuyusutzy7lxtkwvzq53a7dn2ixsj3mzkbbsz4ci3mda.jpg",
  "base_model": "albedobaseXL_v13.safetensors",
  "batch_size": 1,
  "merge_strength": 1,
  "negative_prompt": "black and white",
  "added_merge_noise": 0.8
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
  {
    input: {
      steps: 20,
      width: 1024,
      height: 1024,
      prompt: "an abstract painting of a cat",
      image_1: "https://replicate.delivery/pbxt/KRz8qs41ipSGwqo9gai74Dk3rTB0ihKMBqJUvNnQQYyfFD69/fofr_svg_black_and_white_cat_doodle_style_thick_outlines_8c7e447c-da1e-46b2-a7e1-2025418f2050.webp",
      image_2: "https://replicate.delivery/pbxt/KRz8r8hSyMNcWLgbcKMCDhvoTQX1KqFKCYvVXeSPfwTf4783/bafkreidar5nwcwmuyusutzy7lxtkwvzq53a7dn2ixsj3mzkbbsz4ci3mda.jpg",
      base_model: "albedobaseXL_v13.safetensors",
      batch_size: 1,
      merge_strength: 1,
      negative_prompt: "black and white",
      added_merge_noise: 0.8
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    input={
        "steps": 20,
        "width": 1024,
        "height": 1024,
        "prompt": "an abstract painting of a cat",
        "image_1": "https://replicate.delivery/pbxt/KRz8qs41ipSGwqo9gai74Dk3rTB0ihKMBqJUvNnQQYyfFD69/fofr_svg_black_and_white_cat_doodle_style_thick_outlines_8c7e447c-da1e-46b2-a7e1-2025418f2050.webp",
        "image_2": "https://replicate.delivery/pbxt/KRz8r8hSyMNcWLgbcKMCDhvoTQX1KqFKCYvVXeSPfwTf4783/bafkreidar5nwcwmuyusutzy7lxtkwvzq53a7dn2ixsj3mzkbbsz4ci3mda.jpg",
        "base_model": "albedobaseXL_v13.safetensors",
        "batch_size": 1,
        "merge_strength": 1,
        "negative_prompt": "black and white",
        "added_merge_noise": 0.8
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/image-merge-sdxl 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": "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    "input": {
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "an abstract painting of a cat",
      "image_1": "https://replicate.delivery/pbxt/KRz8qs41ipSGwqo9gai74Dk3rTB0ihKMBqJUvNnQQYyfFD69/fofr_svg_black_and_white_cat_doodle_style_thick_outlines_8c7e447c-da1e-46b2-a7e1-2025418f2050.webp",
      "image_2": "https://replicate.delivery/pbxt/KRz8r8hSyMNcWLgbcKMCDhvoTQX1KqFKCYvVXeSPfwTf4783/bafkreidar5nwcwmuyusutzy7lxtkwvzq53a7dn2ixsj3mzkbbsz4ci3mda.jpg",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 1,
      "negative_prompt": "black and white",
      "added_merge_noise": 0.8
    }
  }' \
  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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75 \
  -i 'steps=20' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="an abstract painting of a cat"' \
  -i 'image_1="https://replicate.delivery/pbxt/KRz8qs41ipSGwqo9gai74Dk3rTB0ihKMBqJUvNnQQYyfFD69/fofr_svg_black_and_white_cat_doodle_style_thick_outlines_8c7e447c-da1e-46b2-a7e1-2025418f2050.webp"' \
  -i 'image_2="https://replicate.delivery/pbxt/KRz8r8hSyMNcWLgbcKMCDhvoTQX1KqFKCYvVXeSPfwTf4783/bafkreidar5nwcwmuyusutzy7lxtkwvzq53a7dn2ixsj3mzkbbsz4ci3mda.jpg"' \
  -i 'base_model="albedobaseXL_v13.safetensors"' \
  -i 'batch_size=1' \
  -i 'merge_strength=1' \
  -i 'negative_prompt="black and white"' \
  -i 'added_merge_noise=0.8'

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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "an abstract painting of a cat",
      "image_1": "https://replicate.delivery/pbxt/KRz8qs41ipSGwqo9gai74Dk3rTB0ihKMBqJUvNnQQYyfFD69/fofr_svg_black_and_white_cat_doodle_style_thick_outlines_8c7e447c-da1e-46b2-a7e1-2025418f2050.webp",
      "image_2": "https://replicate.delivery/pbxt/KRz8r8hSyMNcWLgbcKMCDhvoTQX1KqFKCYvVXeSPfwTf4783/bafkreidar5nwcwmuyusutzy7lxtkwvzq53a7dn2ixsj3mzkbbsz4ci3mda.jpg",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 1,
      "negative_prompt": "black and white",
      "added_merge_noise": 0.8
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-02-22T22:26:55.682005Z",
  "created_at": "2024-02-22T22:26:47.534495Z",
  "data_removed": false,
  "error": null,
  "id": "trm4wldb7y6clourcq7dqmfeuu",
  "input": {
    "steps": 20,
    "width": 1024,
    "height": 1024,
    "prompt": "an abstract painting of a cat",
    "image_1": "https://replicate.delivery/pbxt/KRz8qs41ipSGwqo9gai74Dk3rTB0ihKMBqJUvNnQQYyfFD69/fofr_svg_black_and_white_cat_doodle_style_thick_outlines_8c7e447c-da1e-46b2-a7e1-2025418f2050.webp",
    "image_2": "https://replicate.delivery/pbxt/KRz8r8hSyMNcWLgbcKMCDhvoTQX1KqFKCYvVXeSPfwTf4783/bafkreidar5nwcwmuyusutzy7lxtkwvzq53a7dn2ixsj3mzkbbsz4ci3mda.jpg",
    "base_model": "albedobaseXL_v13.safetensors",
    "batch_size": 1,
    "merge_strength": 1,
    "negative_prompt": "black and white",
    "added_merge_noise": 0.8
  },
  "logs": "Random seed set to: 3113060388\nChecking weights\n✅ model.sdxl.safetensors\n✅ albedobaseXL_v13.safetensors\n✅ ip-adapter_sdxl.safetensors\n====================================\nChecking inputs\n✅ /tmp/inputs/left.webp\n✅ /tmp/inputs/right.jpg\n====================================\nRunning workflow\ngot prompt\nExecuting node 8, title: KSampler (Efficient), class type: KSampler (Efficient)\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:04,  4.41it/s]\n 10%|█         | 2/20 [00:00<00:04,  4.28it/s]\n 15%|█▌        | 3/20 [00:00<00:04,  4.23it/s]\n 20%|██        | 4/20 [00:00<00:03,  4.20it/s]\n 25%|██▌       | 5/20 [00:01<00:03,  4.20it/s]\n 30%|███       | 6/20 [00:01<00:03,  4.17it/s]\n 35%|███▌      | 7/20 [00:01<00:03,  4.18it/s]\n 40%|████      | 8/20 [00:01<00:02,  4.17it/s]\n 45%|████▌     | 9/20 [00:02<00:02,  4.18it/s]\n 50%|█████     | 10/20 [00:02<00:02,  4.20it/s]\n 55%|█████▌    | 11/20 [00:02<00:02,  4.23it/s]\n 60%|██████    | 12/20 [00:02<00:01,  4.23it/s]\n 65%|██████▌   | 13/20 [00:03<00:01,  4.24it/s]\n 70%|███████   | 14/20 [00:03<00:01,  4.24it/s]\n 75%|███████▌  | 15/20 [00:03<00:01,  4.25it/s]\n 80%|████████  | 16/20 [00:03<00:00,  4.25it/s]\n 85%|████████▌ | 17/20 [00:04<00:00,  4.26it/s]\n 90%|█████████ | 18/20 [00:04<00:00,  4.27it/s]\n 95%|█████████▌| 19/20 [00:04<00:00,  4.39it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.50it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.28it/s]\nExecuting node 9, title: Save Image, class type: SaveImage\nPrompt executed in 5.05 seconds\noutputs:  {'8': {'images': []}, '9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 8.110822,
    "total_time": 8.14751
  },
  "output": [
    "https://replicate.delivery/pbxt/OAudk92mx9rnChY0KpZ6cQ8G7bI7ZaX0GxH9KxzsLRtL8VmE/ComfyUI_00001_.png"
  ],
  "started_at": "2024-02-22T22:26:47.571183Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/trm4wldb7y6clourcq7dqmfeuu",
    "cancel": "https://api.replicate.com/v1/predictions/trm4wldb7y6clourcq7dqmfeuu/cancel"
  },
  "version": "101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75"
}

Generated in

8.1 seconds

fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75

Prediction

Model

3x4o3utbrfplkr34e547uz37yy

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

8.3s

Created

over 1 year ago

Input

steps: 20
width: 1024
height: 1024
prompt: an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes
image_1
image_2
base_model: albedobaseXL_v13.safetensors
batch_size: 1
merge_strength: 1
negative_prompt: photo, render, unreal engine
added_merge_noise: 0.8

{
  "steps": 20,
  "width": 1024,
  "height": 1024,
  "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
  "image_1": "https://replicate.delivery/pbxt/KRzHiQ1JYzogdduCatHddDmXycdc60RPjKJLpbWwb6m1bbbs/_full.png",
  "image_2": "https://replicate.delivery/pbxt/KRzHiiqvMDiQF8Eg34ilSXap4BJQNManWQZpMmTdJBVVvPNr/319055-2.jpg",
  "base_model": "albedobaseXL_v13.safetensors",
  "batch_size": 1,
  "merge_strength": 1,
  "negative_prompt": "photo, render, unreal engine",
  "added_merge_noise": 0.8
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
  {
    input: {
      steps: 20,
      width: 1024,
      height: 1024,
      prompt: "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
      image_1: "https://replicate.delivery/pbxt/KRzHiQ1JYzogdduCatHddDmXycdc60RPjKJLpbWwb6m1bbbs/_full.png",
      image_2: "https://replicate.delivery/pbxt/KRzHiiqvMDiQF8Eg34ilSXap4BJQNManWQZpMmTdJBVVvPNr/319055-2.jpg",
      base_model: "albedobaseXL_v13.safetensors",
      batch_size: 1,
      merge_strength: 1,
      negative_prompt: "photo, render, unreal engine",
      added_merge_noise: 0.8
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    input={
        "steps": 20,
        "width": 1024,
        "height": 1024,
        "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
        "image_1": "https://replicate.delivery/pbxt/KRzHiQ1JYzogdduCatHddDmXycdc60RPjKJLpbWwb6m1bbbs/_full.png",
        "image_2": "https://replicate.delivery/pbxt/KRzHiiqvMDiQF8Eg34ilSXap4BJQNManWQZpMmTdJBVVvPNr/319055-2.jpg",
        "base_model": "albedobaseXL_v13.safetensors",
        "batch_size": 1,
        "merge_strength": 1,
        "negative_prompt": "photo, render, unreal engine",
        "added_merge_noise": 0.8
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/image-merge-sdxl 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": "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    "input": {
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
      "image_1": "https://replicate.delivery/pbxt/KRzHiQ1JYzogdduCatHddDmXycdc60RPjKJLpbWwb6m1bbbs/_full.png",
      "image_2": "https://replicate.delivery/pbxt/KRzHiiqvMDiQF8Eg34ilSXap4BJQNManWQZpMmTdJBVVvPNr/319055-2.jpg",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 1,
      "negative_prompt": "photo, render, unreal engine",
      "added_merge_noise": 0.8
    }
  }' \
  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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75 \
  -i 'steps=20' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes"' \
  -i 'image_1="https://replicate.delivery/pbxt/KRzHiQ1JYzogdduCatHddDmXycdc60RPjKJLpbWwb6m1bbbs/_full.png"' \
  -i 'image_2="https://replicate.delivery/pbxt/KRzHiiqvMDiQF8Eg34ilSXap4BJQNManWQZpMmTdJBVVvPNr/319055-2.jpg"' \
  -i 'base_model="albedobaseXL_v13.safetensors"' \
  -i 'batch_size=1' \
  -i 'merge_strength=1' \
  -i 'negative_prompt="photo, render, unreal engine"' \
  -i 'added_merge_noise=0.8'

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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
      "image_1": "https://replicate.delivery/pbxt/KRzHiQ1JYzogdduCatHddDmXycdc60RPjKJLpbWwb6m1bbbs/_full.png",
      "image_2": "https://replicate.delivery/pbxt/KRzHiiqvMDiQF8Eg34ilSXap4BJQNManWQZpMmTdJBVVvPNr/319055-2.jpg",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 1,
      "negative_prompt": "photo, render, unreal engine",
      "added_merge_noise": 0.8
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-02-22T22:36:16.686549Z",
  "created_at": "2024-02-22T22:36:08.396350Z",
  "data_removed": false,
  "error": null,
  "id": "3x4o3utbrfplkr34e547uz37yy",
  "input": {
    "steps": 20,
    "width": 1024,
    "height": 1024,
    "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
    "image_1": "https://replicate.delivery/pbxt/KRzHiQ1JYzogdduCatHddDmXycdc60RPjKJLpbWwb6m1bbbs/_full.png",
    "image_2": "https://replicate.delivery/pbxt/KRzHiiqvMDiQF8Eg34ilSXap4BJQNManWQZpMmTdJBVVvPNr/319055-2.jpg",
    "base_model": "albedobaseXL_v13.safetensors",
    "batch_size": 1,
    "merge_strength": 1,
    "negative_prompt": "photo, render, unreal engine",
    "added_merge_noise": 0.8
  },
  "logs": "Random seed set to: 2093552613\nChecking weights\n✅ model.sdxl.safetensors\n✅ albedobaseXL_v13.safetensors\n✅ ip-adapter_sdxl.safetensors\n====================================\nChecking inputs\n✅ /tmp/inputs/left.png\n✅ /tmp/inputs/right.jpg\n====================================\nRunning workflow\ngot prompt\nExecuting node 8, title: KSampler (Efficient), class type: KSampler (Efficient)\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:04,  4.42it/s]\n 10%|█         | 2/20 [00:00<00:04,  4.23it/s]\n 15%|█▌        | 3/20 [00:00<00:04,  4.21it/s]\n 20%|██        | 4/20 [00:00<00:03,  4.18it/s]\n 25%|██▌       | 5/20 [00:01<00:03,  4.19it/s]\n 30%|███       | 6/20 [00:01<00:03,  4.13it/s]\n 35%|███▌      | 7/20 [00:01<00:03,  4.15it/s]\n 40%|████      | 8/20 [00:01<00:02,  4.16it/s]\n 45%|████▌     | 9/20 [00:02<00:02,  4.14it/s]\n 50%|█████     | 10/20 [00:02<00:02,  4.16it/s]\n 55%|█████▌    | 11/20 [00:02<00:02,  4.20it/s]\n 60%|██████    | 12/20 [00:02<00:01,  4.21it/s]\n 65%|██████▌   | 13/20 [00:03<00:01,  4.20it/s]\n 70%|███████   | 14/20 [00:03<00:01,  4.21it/s]\n 75%|███████▌  | 15/20 [00:03<00:01,  4.22it/s]\n 80%|████████  | 16/20 [00:03<00:01,  3.94it/s]\n 85%|████████▌ | 17/20 [00:04<00:00,  4.00it/s]\n 90%|█████████ | 18/20 [00:04<00:00,  4.07it/s]\n 95%|█████████▌| 19/20 [00:04<00:00,  4.21it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.36it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.19it/s]\nExecuting node 9, title: Save Image, class type: SaveImage\nPrompt executed in 5.17 seconds\noutputs:  {'8': {'images': []}, '9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 8.253927,
    "total_time": 8.290199
  },
  "output": [
    "https://replicate.delivery/pbxt/I2TffNejR0YvVpUMoe2A5VRrfD5CASoP06c5EeGtPLW3XerMJA/ComfyUI_00001_.png"
  ],
  "started_at": "2024-02-22T22:36:08.432622Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/3x4o3utbrfplkr34e547uz37yy",
    "cancel": "https://api.replicate.com/v1/predictions/3x4o3utbrfplkr34e547uz37yy/cancel"
  },
  "version": "101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75"
}

Generated in

8.3 seconds

fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75

Prediction

Model

e4e3gbdbbeiovdkx4nvtktalia

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

11.7s

Created

over 1 year ago

Input

steps: 20
width: 1024
height: 1024
prompt: an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes
image_1
image_2
base_model: albedobaseXL_v13.safetensors
batch_size: 1
merge_strength: 1
negative_prompt: photo, render, unreal engine
added_merge_noise: 0.8

{
  "steps": 20,
  "width": 1024,
  "height": 1024,
  "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
  "image_1": "https://replicate.delivery/pbxt/KRzPZdgrZtDSMqofrMYmie4KY5i9OXtAfRzdCgPSZh7NgAif/fofr_a_color_svg_vector_image_of_a_video_game_character_circle__9903b67c-220d-4b96-8742-4044e3b7bfc9.webp",
  "image_2": "https://replicate.delivery/pbxt/KRzPZrVrXjwinoz5ogRyqxGMt3SN5MgG37puAUwXCZiIt7QF/ComfyUI_00003_.png",
  "base_model": "albedobaseXL_v13.safetensors",
  "batch_size": 1,
  "merge_strength": 1,
  "negative_prompt": "photo, render, unreal engine",
  "added_merge_noise": 0.8
}

npm install replicate

Import and set up the client:

import Replicate from "replicate";
import fs from "node:fs";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

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

const output = await replicate.run(
  "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
  {
    input: {
      steps: 20,
      width: 1024,
      height: 1024,
      prompt: "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
      image_1: "https://replicate.delivery/pbxt/KRzPZdgrZtDSMqofrMYmie4KY5i9OXtAfRzdCgPSZh7NgAif/fofr_a_color_svg_vector_image_of_a_video_game_character_circle__9903b67c-220d-4b96-8742-4044e3b7bfc9.webp",
      image_2: "https://replicate.delivery/pbxt/KRzPZrVrXjwinoz5ogRyqxGMt3SN5MgG37puAUwXCZiIt7QF/ComfyUI_00003_.png",
      base_model: "albedobaseXL_v13.safetensors",
      batch_size: 1,
      merge_strength: 1,
      negative_prompt: "photo, render, unreal engine",
      added_merge_noise: 0.8
    }
  }
);

// To access the file URL:
console.log(output[0].url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", output[0]);

To learn more, take a look at the guide on getting started with Node.js.

pip install replicate

Import the client:

import replicate

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

output = replicate.run(
    "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    input={
        "steps": 20,
        "width": 1024,
        "height": 1024,
        "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
        "image_1": "https://replicate.delivery/pbxt/KRzPZdgrZtDSMqofrMYmie4KY5i9OXtAfRzdCgPSZh7NgAif/fofr_a_color_svg_vector_image_of_a_video_game_character_circle__9903b67c-220d-4b96-8742-4044e3b7bfc9.webp",
        "image_2": "https://replicate.delivery/pbxt/KRzPZrVrXjwinoz5ogRyqxGMt3SN5MgG37puAUwXCZiIt7QF/ComfyUI_00003_.png",
        "base_model": "albedobaseXL_v13.safetensors",
        "batch_size": 1,
        "merge_strength": 1,
        "negative_prompt": "photo, render, unreal engine",
        "added_merge_noise": 0.8
    }
)

# To access the file URL:
print(output[0].url())
#=> "http://example.com"

# To write the file to disk:
with open("my-image.png", "wb") as file:
    file.write(output[0].read())

To learn more, take a look at the guide on getting started with Python.

Run fofr/image-merge-sdxl 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": "fofr/image-merge-sdxl:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75",
    "input": {
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
      "image_1": "https://replicate.delivery/pbxt/KRzPZdgrZtDSMqofrMYmie4KY5i9OXtAfRzdCgPSZh7NgAif/fofr_a_color_svg_vector_image_of_a_video_game_character_circle__9903b67c-220d-4b96-8742-4044e3b7bfc9.webp",
      "image_2": "https://replicate.delivery/pbxt/KRzPZrVrXjwinoz5ogRyqxGMt3SN5MgG37puAUwXCZiIt7QF/ComfyUI_00003_.png",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 1,
      "negative_prompt": "photo, render, unreal engine",
      "added_merge_noise": 0.8
    }
  }' \
  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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75 \
  -i 'steps=20' \
  -i 'width=1024' \
  -i 'height=1024' \
  -i 'prompt="an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes"' \
  -i 'image_1="https://replicate.delivery/pbxt/KRzPZdgrZtDSMqofrMYmie4KY5i9OXtAfRzdCgPSZh7NgAif/fofr_a_color_svg_vector_image_of_a_video_game_character_circle__9903b67c-220d-4b96-8742-4044e3b7bfc9.webp"' \
  -i 'image_2="https://replicate.delivery/pbxt/KRzPZrVrXjwinoz5ogRyqxGMt3SN5MgG37puAUwXCZiIt7QF/ComfyUI_00003_.png"' \
  -i 'base_model="albedobaseXL_v13.safetensors"' \
  -i 'batch_size=1' \
  -i 'merge_strength=1' \
  -i 'negative_prompt="photo, render, unreal engine"' \
  -i 'added_merge_noise=0.8'

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/image-merge-sdxl@sha256:101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "steps": 20,
      "width": 1024,
      "height": 1024,
      "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
      "image_1": "https://replicate.delivery/pbxt/KRzPZdgrZtDSMqofrMYmie4KY5i9OXtAfRzdCgPSZh7NgAif/fofr_a_color_svg_vector_image_of_a_video_game_character_circle__9903b67c-220d-4b96-8742-4044e3b7bfc9.webp",
      "image_2": "https://replicate.delivery/pbxt/KRzPZrVrXjwinoz5ogRyqxGMt3SN5MgG37puAUwXCZiIt7QF/ComfyUI_00003_.png",
      "base_model": "albedobaseXL_v13.safetensors",
      "batch_size": 1,
      "merge_strength": 1,
      "negative_prompt": "photo, render, unreal engine",
      "added_merge_noise": 0.8
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2024-02-22T22:44:37.983285Z",
  "created_at": "2024-02-22T22:44:26.265730Z",
  "data_removed": false,
  "error": null,
  "id": "e4e3gbdbbeiovdkx4nvtktalia",
  "input": {
    "steps": 20,
    "width": 1024,
    "height": 1024,
    "prompt": "an abstract portrait painting of a person, pastel, impasto, watercolour, thick brushstrokes",
    "image_1": "https://replicate.delivery/pbxt/KRzPZdgrZtDSMqofrMYmie4KY5i9OXtAfRzdCgPSZh7NgAif/fofr_a_color_svg_vector_image_of_a_video_game_character_circle__9903b67c-220d-4b96-8742-4044e3b7bfc9.webp",
    "image_2": "https://replicate.delivery/pbxt/KRzPZrVrXjwinoz5ogRyqxGMt3SN5MgG37puAUwXCZiIt7QF/ComfyUI_00003_.png",
    "base_model": "albedobaseXL_v13.safetensors",
    "batch_size": 1,
    "merge_strength": 1,
    "negative_prompt": "photo, render, unreal engine",
    "added_merge_noise": 0.8
  },
  "logs": "Random seed set to: 1257701481\nChecking weights\n✅ model.sdxl.safetensors\n✅ albedobaseXL_v13.safetensors\n✅ ip-adapter_sdxl.safetensors\n====================================\nChecking inputs\n✅ /tmp/inputs/left.webp\n✅ /tmp/inputs/right.png\n====================================\nRunning workflow\ngot prompt\nExecuting node 16, title: Load Image, class type: LoadImage\nExecuting node 17, title: Batch Images, class type: ImageBatch\nExecuting node 15, title: Apply IPAdapter, class type: IPAdapterApply\nExecuting node 8, title: KSampler (Efficient), class type: KSampler (Efficient)\nRequested to load SDXL\nLoading 1 new model\n  0%|          | 0/20 [00:00<?, ?it/s]\n  5%|▌         | 1/20 [00:00<00:04,  4.40it/s]\n 10%|█         | 2/20 [00:00<00:04,  4.28it/s]\n 15%|█▌        | 3/20 [00:00<00:04,  4.23it/s]\n 20%|██        | 4/20 [00:00<00:03,  4.21it/s]\n 25%|██▌       | 5/20 [00:01<00:03,  4.21it/s]\n 30%|███       | 6/20 [00:01<00:03,  4.17it/s]\n 35%|███▌      | 7/20 [00:01<00:03,  4.17it/s]\n 40%|████      | 8/20 [00:01<00:02,  4.18it/s]\n 45%|████▌     | 9/20 [00:02<00:02,  4.18it/s]\n 50%|█████     | 10/20 [00:02<00:02,  4.18it/s]\n 55%|█████▌    | 11/20 [00:02<00:02,  4.19it/s]\n 60%|██████    | 12/20 [00:02<00:01,  4.18it/s]\n 65%|██████▌   | 13/20 [00:03<00:01,  4.17it/s]\n 70%|███████   | 14/20 [00:03<00:01,  4.20it/s]\n 75%|███████▌  | 15/20 [00:03<00:01,  4.21it/s]\n 80%|████████  | 16/20 [00:03<00:00,  4.22it/s]\n 85%|████████▌ | 17/20 [00:04<00:00,  4.21it/s]\n 90%|█████████ | 18/20 [00:04<00:00,  4.23it/s]\n 95%|█████████▌| 19/20 [00:04<00:00,  4.35it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.47it/s]\n100%|██████████| 20/20 [00:04<00:00,  4.25it/s]\nExecuting node 9, title: Save Image, class type: SaveImage\nPrompt executed in 8.37 seconds\noutputs:  {'8': {'images': []}, '9': {'images': [{'filename': 'ComfyUI_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\nContents of /tmp/outputs:\nComfyUI_00001_.png",
  "metrics": {
    "predict_time": 11.679743,
    "total_time": 11.717555
  },
  "output": [
    "https://replicate.delivery/pbxt/yHAwJXVnEhryFdlDtBIE8XYCLendOCe7QNSzySJAFAWUBYZSA/ComfyUI_00001_.png"
  ],
  "started_at": "2024-02-22T22:44:26.303542Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/e4e3gbdbbeiovdkx4nvtktalia",
    "cancel": "https://api.replicate.com/v1/predictions/e4e3gbdbbeiovdkx4nvtktalia/cancel"
  },
  "version": "101190cbcc57984b9bfba21e1beea3694dc9d121ed1695059b0d4832e468cd75"
}

Generated in

11.7 seconds