Prediction

Model

emaph/outpaint-controlnet-union:3947eb8c

6fvgec3bx9rge0cgyq2vpehgam

Status

Succeeded

Source

Web

Hardware

Total duration

5m 23s

Created

over 1 year ago

Webhook

–

Input

prompt: grass field, sunset, clouds
negative_prompt: ugly
image: https://i.postimg.cc/PrR5JK6c/Comfy-UI-temp-xdxpz-00001.png
left: 150
right: 150
top: 150
bottom: 150
output_format: webp
output_quality: 80

{
  "bottom": 150,
  "image": "https://i.postimg.cc/PrR5JK6c/Comfy-UI-temp-xdxpz-00001.png",
  "left": 150,
  "negative_prompt": "ugly",
  "output_format": "webp",
  "output_quality": 80,
  "prompt": "grass field, sunset, clouds",
  "right": 150,
  "top": 150
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_Dda**********************************

This is your API token. Keep it to yourself.

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 emaph/outpaint-controlnet-union using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "emaph/outpaint-controlnet-union:3947eb8cde7f5953837f7f25b5b8ae7bb4e0c65ba38d1662d516c537cd6785e0",
  {
    input: {
      bottom: 150,
      image: "https://i.postimg.cc/PrR5JK6c/Comfy-UI-temp-xdxpz-00001.png",
      left: 150,
      negative_prompt: "ugly",
      output_format: "webp",
      output_quality: 80,
      prompt: "grass field, sunset, clouds",
      right: 150,
      top: 150
    }
  }
);

// 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.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_Dda**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run emaph/outpaint-controlnet-union using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "emaph/outpaint-controlnet-union:3947eb8cde7f5953837f7f25b5b8ae7bb4e0c65ba38d1662d516c537cd6785e0",
    input={
        "bottom": 150,
        "image": "https://i.postimg.cc/PrR5JK6c/Comfy-UI-temp-xdxpz-00001.png",
        "left": 150,
        "negative_prompt": "ugly",
        "output_format": "webp",
        "output_quality": 80,
        "prompt": "grass field, sunset, clouds",
        "right": 150,
        "top": 150
    }
)

# 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.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_Dda**********************************

This is your API token. Keep it to yourself.

Run emaph/outpaint-controlnet-union 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": "emaph/outpaint-controlnet-union:3947eb8cde7f5953837f7f25b5b8ae7bb4e0c65ba38d1662d516c537cd6785e0",
    "input": {
      "bottom": 150,
      "image": "https://i.postimg.cc/PrR5JK6c/Comfy-UI-temp-xdxpz-00001.png",
      "left": 150,
      "negative_prompt": "ugly",
      "output_format": "webp",
      "output_quality": 80,
      "prompt": "grass field, sunset, clouds",
      "right": 150,
      "top": 150
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "6fvgec3bx9rge0cgyq2vpehgam",
  "model": "emaph/outpaint-controlnet-union",
  "version": "3947eb8cde7f5953837f7f25b5b8ae7bb4e0c65ba38d1662d516c537cd6785e0",
  "input": {
    "bottom": 150,
    "image": "https://i.postimg.cc/PrR5JK6c/Comfy-UI-temp-xdxpz-00001.png",
    "left": 150,
    "negative_prompt": "ugly",
    "output_format": "webp",
    "output_quality": 80,
    "prompt": "grass field, sunset, clouds",
    "right": 150,
    "top": 150
  },
  "logs": "Random seed set to: 3062084987\nChecking inputs\nDownloading https://i.postimg.cc/PrR5JK6c/Comfy-UI-temp-xdxpz-00001.png to /tmp/inputs/Comfy-UI-temp-xdxpz-00001.png\n✅ /tmp/inputs/Comfy-UI-temp-xdxpz-00001.png\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\nloaded straight to GPU\nRequested to load SDXL\nLoading 1 new model\nExecuting node 6, title: Positive, class type: CLIPTextEncode\nRequested to load SDXLClipModel\nLoading 1 new model\nExecuting node 7, title: Negetive, class type: CLIPTextEncode\nExecuting node 16, title: Load ControlNet Model, class type: ControlNetLoader\nExecuting node 17, title: SetUnionControlNetType, class type: SetUnionControlNetType\nExecuting node 11, title: Load Image, class type: LoadImage\nExecuting node 10, title: Pad Image for Outpainting, class type: ImagePadForOutpaint\nExecuting node 48, title: InvertMask, class type: InvertMask\nExecuting node 47, title: Convert Mask to Image, class type: MaskToImage\nExecuting node 49, title: ImageCompositeMasked, class type: ImageCompositeMasked\nExecuting node 15, title: Apply ControlNet (Advanced), class type: ControlNetApplyAdvanced\nExecuting node 39, title: VAE Encode (for Inpainting), class type: VAEEncodeForInpaint\nRequested to load AutoencoderKL\nLoading 1 new model\nExecuting node 3, title: KSampler, class type: KSampler\nRequested to load ControlNet\nLoading 1 new model\n  0%|          | 0/26 [00:00<?, ?it/s]\n  4%|▍         | 1/26 [00:01<00:37,  1.48s/it]\n  8%|▊         | 2/26 [00:02<00:34,  1.43s/it]\n 12%|█▏        | 3/26 [00:04<00:32,  1.41s/it]\n 15%|█▌        | 4/26 [00:05<00:30,  1.40s/it]\n 19%|█▉        | 5/26 [00:07<00:29,  1.40s/it]\n 23%|██▎       | 6/26 [00:08<00:27,  1.40s/it]\n 27%|██▋       | 7/26 [00:09<00:26,  1.40s/it]\n 31%|███       | 8/26 [00:11<00:25,  1.40s/it]\n 35%|███▍      | 9/26 [00:12<00:23,  1.41s/it]\n 38%|███▊      | 10/26 [00:14<00:22,  1.40s/it]\n 42%|████▏     | 11/26 [00:15<00:21,  1.41s/it]\n 46%|████▌     | 12/26 [00:16<00:19,  1.41s/it]\n 50%|█████     | 13/26 [00:18<00:18,  1.41s/it]\n 54%|█████▍    | 14/26 [00:19<00:16,  1.41s/it]\n 58%|█████▊    | 15/26 [00:21<00:15,  1.42s/it]\n 62%|██████▏   | 16/26 [00:22<00:14,  1.42s/it]\n 65%|██████▌   | 17/26 [00:23<00:12,  1.42s/it]\n 69%|██████▉   | 18/26 [00:25<00:11,  1.43s/it]\n 73%|███████▎  | 19/26 [00:26<00:10,  1.43s/it]\n 77%|███████▋  | 20/26 [00:28<00:08,  1.44s/it]\n 81%|████████  | 21/26 [00:29<00:07,  1.44s/it]\n 85%|████████▍ | 22/26 [00:31<00:05,  1.45s/it]\n 88%|████████▊ | 23/26 [00:32<00:04,  1.45s/it]\n 92%|█████████▏| 24/26 [00:34<00:02,  1.46s/it]\n 96%|█████████▌| 25/26 [00:35<00:01,  1.46s/it]\n100%|██████████| 26/26 [00:37<00:00,  1.47s/it]\n100%|██████████| 26/26 [00:37<00:00,  1.43s/it]\nExecuting node 8, title: VAE Decode, class type: VAEDecode\nExecuting node 58, title: ImageCompositeMasked, class type: ImageCompositeMasked\nExecuting node 65, title: Save Image, class type: SaveImage\nPrompt executed in 53.09 seconds\noutputs:  {'65': {'images': [{'filename': 'outpainted_00001_.png', 'subfolder': '', 'type': 'output'}]}}\n====================================\noutpainted_00001_.png",
  "output": [
    "https://replicate.delivery/czjl/cBsfmDDMoEzOdy4bF517fnm4XxVKns8vNR4dJx3ODv8FSwMTA/outpainted_00001_.webp"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-07-27T19:57:54.538Z",
  "started_at": "2024-07-27T20:02:23.525489Z",
  "completed_at": "2024-07-27T20:03:17.987029Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/6fvgec3bx9rge0cgyq2vpehgam/cancel",
    "get": "https://api.replicate.com/v1/predictions/6fvgec3bx9rge0cgyq2vpehgam",
    "web": "https://replicate.com/p/6fvgec3bx9rge0cgyq2vpehgam"
  },
  "metrics": {
    "predict_time": 54.461539476,
    "total_time": 323.449029
  }
}

Generated in

54.5 seconds

Tweak it Report

Random seed set to: 3062084987 Checking inputs Downloading https://i.postimg.cc/PrR5JK6c/Comfy-UI-temp-xdxpz-00001.png to /tmp/inputs/Comfy-UI-temp-xdxpz-00001.png ✅ /tmp/inputs/Comfy-UI-temp-xdxpz-00001.png ==================================== Running workflow got prompt Executing node 4, title: Load Checkpoint, class type: CheckpointLoaderSimple model_type EPS Using pytorch attention in VAE Using pytorch attention in VAE loaded straight to GPU Requested to load SDXL Loading 1 new model Executing node 6, title: Positive, class type: CLIPTextEncode Requested to load SDXLClipModel Loading 1 new model Executing node 7, title: Negetive, class type: CLIPTextEncode Executing node 16, title: Load ControlNet Model, class type: ControlNetLoader Executing node 17, title: SetUnionControlNetType, class type: SetUnionControlNetType Executing node 11, title: Load Image, class type: LoadImage Executing node 10, title: Pad Image for Outpainting, class type: ImagePadForOutpaint Executing node 48, title: InvertMask, class type: InvertMask Executing node 47, title: Convert Mask to Image, class type: MaskToImage Executing node 49, title: ImageCompositeMasked, class type: ImageCompositeMasked Executing node 15, title: Apply ControlNet (Advanced), class type: ControlNetApplyAdvanced Executing node 39, title: VAE Encode (for Inpainting), class type: VAEEncodeForInpaint Requested to load AutoencoderKL Loading 1 new model Executing node 3, title: KSampler, class type: KSampler Requested to load ControlNet Loading 1 new model 0%| | 0/26 [00:00<?, ?it/s] 4%|▍ | 1/26 [00:01<00:37, 1.48s/it] 8%|▊ | 2/26 [00:02<00:34, 1.43s/it] 12%|█▏ | 3/26 [00:04<00:32, 1.41s/it] 15%|█▌ | 4/26 [00:05<00:30, 1.40s/it] 19%|█▉ | 5/26 [00:07<00:29, 1.40s/it] 23%|██▎ | 6/26 [00:08<00:27, 1.40s/it] 27%|██▋ | 7/26 [00:09<00:26, 1.40s/it] 31%|███ | 8/26 [00:11<00:25, 1.40s/it] 35%|███▍ | 9/26 [00:12<00:23, 1.41s/it] 38%|███▊ | 10/26 [00:14<00:22, 1.40s/it] 42%|████▏ | 11/26 [00:15<00:21, 1.41s/it] 46%|████▌ | 12/26 [00:16<00:19, 1.41s/it] 50%|█████ | 13/26 [00:18<00:18, 1.41s/it] 54%|█████▍ | 14/26 [00:19<00:16, 1.41s/it] 58%|█████▊ | 15/26 [00:21<00:15, 1.42s/it] 62%|██████▏ | 16/26 [00:22<00:14, 1.42s/it] 65%|██████▌ | 17/26 [00:23<00:12, 1.42s/it] 69%|██████▉ | 18/26 [00:25<00:11, 1.43s/it] 73%|███████▎ | 19/26 [00:26<00:10, 1.43s/it] 77%|███████▋ | 20/26 [00:28<00:08, 1.44s/it] 81%|████████ | 21/26 [00:29<00:07, 1.44s/it] 85%|████████▍ | 22/26 [00:31<00:05, 1.45s/it] 88%|████████▊ | 23/26 [00:32<00:04, 1.45s/it] 92%|█████████▏| 24/26 [00:34<00:02, 1.46s/it] 96%|█████████▌| 25/26 [00:35<00:01, 1.46s/it] 100%|██████████| 26/26 [00:37<00:00, 1.47s/it] 100%|██████████| 26/26 [00:37<00:00, 1.43s/it] Executing node 8, title: VAE Decode, class type: VAEDecode Executing node 58, title: ImageCompositeMasked, class type: ImageCompositeMasked Executing node 65, title: Save Image, class type: SaveImage Prompt executed in 53.09 seconds outputs: {'65': {'images': [{'filename': 'outpainted_00001_.png', 'subfolder': '', 'type': 'output'}]}} ==================================== outpainted_00001_.png