lucataco/sdxl-controlnet-depth – Run with an API on Replicate

lucataco / sdxl-controlnet-depth

SDXL ControlNet - Depth

Cold

Public
30.4K runs
L40S
GitHub
License

Run with an API

Playground API Examples README Versions

Input

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

npx create-replicate --model=lucataco/sdxl-controlnet-depth

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 lucataco/sdxl-controlnet-depth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/sdxl-controlnet-depth:465fb41789dc2203a9d7158be11d1d2570606a039c65e0e236fd329b5eecb10c",
  {
    input: {
      seed: 25087,
      image: "https://replicate.delivery/pbxt/JLl0qK0Hjm0GCGhfrmDPQDZkzKHBD98jQ1EjiRiUpC08MzK1/demo.png",
      prompt: "spiderman lecture, photorealistic",
      condition_scale: 0.5,
      num_inference_steps: 30
    }
  }
);
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 lucataco/sdxl-controlnet-depth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/sdxl-controlnet-depth:465fb41789dc2203a9d7158be11d1d2570606a039c65e0e236fd329b5eecb10c",
    input={
        "seed": 25087,
        "image": "https://replicate.delivery/pbxt/JLl0qK0Hjm0GCGhfrmDPQDZkzKHBD98jQ1EjiRiUpC08MzK1/demo.png",
        "prompt": "spiderman lecture, photorealistic",
        "condition_scale": 0.5,
        "num_inference_steps": 30
    }
)
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 lucataco/sdxl-controlnet-depth 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": "465fb41789dc2203a9d7158be11d1d2570606a039c65e0e236fd329b5eecb10c",
    "input": {
      "seed": 25087,
      "image": "https://replicate.delivery/pbxt/JLl0qK0Hjm0GCGhfrmDPQDZkzKHBD98jQ1EjiRiUpC08MzK1/demo.png",
      "prompt": "spiderman lecture, photorealistic",
      "condition_scale": 0.5,
      "num_inference_steps": 30
    }
  }' \
  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/lucataco/sdxl-controlnet-depth@sha256:465fb41789dc2203a9d7158be11d1d2570606a039c65e0e236fd329b5eecb10c \
  -i 'seed=25087' \
  -i 'image="https://replicate.delivery/pbxt/JLl0qK0Hjm0GCGhfrmDPQDZkzKHBD98jQ1EjiRiUpC08MzK1/demo.png"' \
  -i 'prompt="spiderman lecture, photorealistic"' \
  -i 'condition_scale=0.5' \
  -i 'num_inference_steps=30'

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/lucataco/sdxl-controlnet-depth@sha256:465fb41789dc2203a9d7158be11d1d2570606a039c65e0e236fd329b5eecb10c
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": 25087,
      "image": "https://replicate.delivery/pbxt/JLl0qK0Hjm0GCGhfrmDPQDZkzKHBD98jQ1EjiRiUpC08MzK1/demo.png",
      "prompt": "spiderman lecture, photorealistic",
      "condition_scale": 0.5,
      "num_inference_steps": 30
    }
  }' \
  http://localhost:5000/predictions

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

Output

{
  "completed_at": "2023-09-12T22:47:53.749512Z",
  "created_at": "2023-09-12T22:45:45.734709Z",
  "data_removed": false,
  "error": null,
  "id": "cgekvctbear65ui5vgwiahmn34",
  "input": {
    "seed": 25087,
    "image": "https://replicate.delivery/pbxt/JLl0qK0Hjm0GCGhfrmDPQDZkzKHBD98jQ1EjiRiUpC08MzK1/demo.png",
    "prompt": "spiderman lecture, photorealistic",
    "condition_scale": 0.5,
    "num_inference_steps": 30
  },
  "logs": "Using seed: 25087\nOriginal width:458, height:458\nAspect Ratio: 1.00\nnew_width:1024, new_height:1024\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:09,  3.05it/s]\n  7%|▋         | 2/30 [00:00<00:08,  3.26it/s]\n 10%|█         | 3/30 [00:00<00:08,  3.33it/s]\n 13%|█▎        | 4/30 [00:01<00:07,  3.34it/s]\n 17%|█▋        | 5/30 [00:01<00:07,  3.36it/s]\n 20%|██        | 6/30 [00:01<00:07,  3.38it/s]\n 23%|██▎       | 7/30 [00:02<00:06,  3.38it/s]\n 27%|██▋       | 8/30 [00:02<00:06,  3.38it/s]\n 30%|███       | 9/30 [00:02<00:06,  3.39it/s]\n 33%|███▎      | 10/30 [00:02<00:05,  3.39it/s]\n 37%|███▋      | 11/30 [00:03<00:05,  3.38it/s]\n 40%|████      | 12/30 [00:03<00:05,  3.35it/s]\n 43%|████▎     | 13/30 [00:03<00:05,  3.37it/s]\n 47%|████▋     | 14/30 [00:04<00:04,  3.37it/s]\n 50%|█████     | 15/30 [00:04<00:04,  3.37it/s]\n 53%|█████▎    | 16/30 [00:04<00:04,  3.38it/s]\n 57%|█████▋    | 17/30 [00:05<00:03,  3.38it/s]\n 60%|██████    | 18/30 [00:05<00:03,  3.38it/s]\n 63%|██████▎   | 19/30 [00:05<00:03,  3.38it/s]\n 67%|██████▋   | 20/30 [00:05<00:02,  3.38it/s]\n 70%|███████   | 21/30 [00:06<00:02,  3.38it/s]\n 73%|███████▎  | 22/30 [00:06<00:02,  3.38it/s]\n 77%|███████▋  | 23/30 [00:06<00:02,  3.38it/s]\n 80%|████████  | 24/30 [00:07<00:01,  3.38it/s]\n 83%|████████▎ | 25/30 [00:07<00:01,  3.38it/s]\n 87%|████████▋ | 26/30 [00:07<00:01,  3.38it/s]\n 90%|█████████ | 27/30 [00:08<00:00,  3.38it/s]\n 93%|█████████▎| 28/30 [00:08<00:00,  3.38it/s]\n 97%|█████████▋| 29/30 [00:08<00:00,  3.38it/s]\n100%|██████████| 30/30 [00:08<00:00,  3.38it/s]\n100%|██████████| 30/30 [00:08<00:00,  3.37it/s]",
  "metrics": {
    "predict_time": 12.481869,
    "total_time": 128.014803
  },
  "output": "https://pbxt.replicate.delivery/lvhWUVZ8cqaaDRyNwcoP5SxZnZYO8lG3JXqRmNFAM5Fmc6YE/output.png",
  "started_at": "2023-09-12T22:47:41.267643Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/cgekvctbear65ui5vgwiahmn34",
    "cancel": "https://api.replicate.com/v1/predictions/cgekvctbear65ui5vgwiahmn34/cancel"
  },
  "version": "5e0a5cda895aa23a1aaa1a9a265220097102448e1b4c42b22a3c6d87c12d41a9"
}

Generated in

12.5 seconds

Tweak itReport

Using seed: 25087
Original width:458, height:458
Aspect Ratio: 1.00
new_width:1024, new_height:1024
  0%|          | 0/30 [00:00<?, ?it/s]
  3%|▎         | 1/30 [00:00<00:09,  3.05it/s]
  7%|▋         | 2/30 [00:00<00:08,  3.26it/s]
 10%|█         | 3/30 [00:00<00:08,  3.33it/s]
 13%|█▎        | 4/30 [00:01<00:07,  3.34it/s]
 17%|█▋        | 5/30 [00:01<00:07,  3.36it/s]
 20%|██        | 6/30 [00:01<00:07,  3.38it/s]
 23%|██▎       | 7/30 [00:02<00:06,  3.38it/s]
 27%|██▋       | 8/30 [00:02<00:06,  3.38it/s]
 30%|███       | 9/30 [00:02<00:06,  3.39it/s]
 33%|███▎      | 10/30 [00:02<00:05,  3.39it/s]
 37%|███▋      | 11/30 [00:03<00:05,  3.38it/s]
 40%|████      | 12/30 [00:03<00:05,  3.35it/s]
 43%|████▎     | 13/30 [00:03<00:05,  3.37it/s]
 47%|████▋     | 14/30 [00:04<00:04,  3.37it/s]
 50%|█████     | 15/30 [00:04<00:04,  3.37it/s]
 53%|█████▎    | 16/30 [00:04<00:04,  3.38it/s]
 57%|█████▋    | 17/30 [00:05<00:03,  3.38it/s]
 60%|██████    | 18/30 [00:05<00:03,  3.38it/s]
 63%|██████▎   | 19/30 [00:05<00:03,  3.38it/s]
 67%|██████▋   | 20/30 [00:05<00:02,  3.38it/s]
 70%|███████   | 21/30 [00:06<00:02,  3.38it/s]
 73%|███████▎  | 22/30 [00:06<00:02,  3.38it/s]
 77%|███████▋  | 23/30 [00:06<00:02,  3.38it/s]
 80%|████████  | 24/30 [00:07<00:01,  3.38it/s]
 83%|████████▎ | 25/30 [00:07<00:01,  3.38it/s]
 87%|████████▋ | 26/30 [00:07<00:01,  3.38it/s]
 90%|█████████ | 27/30 [00:08<00:00,  3.38it/s]
 93%|█████████▎| 28/30 [00:08<00:00,  3.38it/s]
 97%|█████████▋| 29/30 [00:08<00:00,  3.38it/s]
100%|██████████| 30/30 [00:08<00:00,  3.38it/s]
100%|██████████| 30/30 [00:08<00:00,  3.37it/s]

This example was created by a different version, lucataco/sdxl-controlnet-depth:5e0a5cda.

Examples

View more examples

Run time and cost

This model costs approximately $0.031 to run on Replicate, or 32 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 32 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Implementation of diffusers/controlnet-depth-sdxl-1.0

Give me a follow if you like my work! @lucataco93