fofr/image-merge-sdxl – Run with an API on Replicate

fofr / image-merge-sdxl

Merge two images together with a prompt

Cold

Public
6K runs
L40S
GitHub
Paper

Run with an API

Playground API Examples README Versions

Input

base_model

string

Select the base model for the prediction

Default: "albedobaseXL_v13.safetensors"

image_1

*file

Preview

image_2

*file

Preview

merge_strength

number

(minimum: 0, maximum: 1)

Reduce strength to increase prompt weight

Default: 1

added_merge_noise

number

(minimum: 0, maximum: 1)

More noise allows for more prompt control

Default: 0.8

prompt

string

Shift + Return to add a new line

A prompt to guide the image merging

Default: "a photo"

negative_prompt

string

Shift + Return to add a new line

Things you do not want in the merged image

Default: ""

width

integer

Default: 1024

height

integer

Default: 1024

steps

integer

Default: 20

seed

integer

Fix the random seed for reproducibility

batch_size

integer

(minimum: 1, maximum: 8)

The batch size for the model

Default: 1

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

npx create-replicate --model=fofr/image-merge-sdxl

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

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

Run fofr/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
    }
  }
);
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/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
    }
)
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/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": "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.

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

Tweak itReport

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

Examples

View more examples

Run time and cost

This model costs approximately $0.0066 to run on Replicate, or 151 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 7 seconds.

Readme

This model doesn't have a readme.