Readme
Implementation of thibaud/controlnet-openpose-sdxl-1.0
Give me a follow if you like my work! @lucataco93
lucataco
/
sdxl-controlnet-openpose
SDXL ControlNet - OpenPose
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=lucataco/sdxl-controlnet-openpose
or set up a project from scratch
Install Replicate’s Node.js client library:
npm install replicateSet 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-openpose 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-openpose:d63e0b238b2d963d90348e2dad19830fbe372a7a43d90d234b2b63cae76d4397",
{
input: {
seed: 25403,
image: "https://replicate.delivery/pbxt/JMf0SV6w1yp8ZcrtrYungReCNQzUUhXJHciDFi5nylAdqmCo/demo.jpg",
prompt: "a latina ballerina, romantic sunset, 4k photo",
guidance_scale: 7.5,
high_noise_frac: 0.8,
negative_prompt: "low quality, bad quality",
num_inference_steps: 50
}
}
);
// To access the file URL:
console.log(output.url()); //=> "http://example.com"
// To write the file to disk:
fs.writeFile("my-image.png", output);To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:
pip install replicateSet 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 replicateRun lucataco/sdxl-controlnet-openpose using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"lucataco/sdxl-controlnet-openpose:d63e0b238b2d963d90348e2dad19830fbe372a7a43d90d234b2b63cae76d4397",
input={
"seed": 25403,
"image": "https://replicate.delivery/pbxt/JMf0SV6w1yp8ZcrtrYungReCNQzUUhXJHciDFi5nylAdqmCo/demo.jpg",
"prompt": "a latina ballerina, romantic sunset, 4k photo",
"guidance_scale": 7.5,
"high_noise_frac": 0.8,
"negative_prompt": "low quality, bad quality",
"num_inference_steps": 50
}
)
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-openpose 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": "d63e0b238b2d963d90348e2dad19830fbe372a7a43d90d234b2b63cae76d4397",
"input": {
"seed": 25403,
"image": "https://replicate.delivery/pbxt/JMf0SV6w1yp8ZcrtrYungReCNQzUUhXJHciDFi5nylAdqmCo/demo.jpg",
"prompt": "a latina ballerina, romantic sunset, 4k photo",
"guidance_scale": 7.5,
"high_noise_frac": 0.8,
"negative_prompt": "low quality, bad quality",
"num_inference_steps": 50
}
}' \
https://api.replicate.com/v1/predictionsTo 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 cogIf 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-openpose@sha256:d63e0b238b2d963d90348e2dad19830fbe372a7a43d90d234b2b63cae76d4397 \
-i 'seed=25403' \
-i 'image="https://replicate.delivery/pbxt/JMf0SV6w1yp8ZcrtrYungReCNQzUUhXJHciDFi5nylAdqmCo/demo.jpg"' \
-i 'prompt="a latina ballerina, romantic sunset, 4k photo"' \
-i 'guidance_scale=7.5' \
-i 'high_noise_frac=0.8' \
-i 'negative_prompt="low quality, bad quality"' \
-i 'num_inference_steps=50'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-openpose@sha256:d63e0b238b2d963d90348e2dad19830fbe372a7a43d90d234b2b63cae76d4397curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 25403, "image": "https://replicate.delivery/pbxt/JMf0SV6w1yp8ZcrtrYungReCNQzUUhXJHciDFi5nylAdqmCo/demo.jpg", "prompt": "a latina ballerina, romantic sunset, 4k photo", "guidance_scale": 7.5, "high_noise_frac": 0.8, "negative_prompt": "low quality, bad quality", "num_inference_steps": 50 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Add a payment method to run this model.
Each run costs approximately $0.012. Alternatively, try out our featured models for free.
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2023-08-17T06:24:28.501864Z",
"created_at": "2023-08-17T06:21:10.994936Z",
"data_removed": false,
"error": null,
"id": "v2doo4dbv2foj6ngr26wnjy7cm",
"input": {
"seed": 25403,
"image": "https://replicate.delivery/pbxt/JMf0SV6w1yp8ZcrtrYungReCNQzUUhXJHciDFi5nylAdqmCo/demo.jpg",
"prompt": "a latina ballerina, romantic sunset, 4k photo",
"guidance_scale": 7.5,
"high_noise_frac": 0.8,
"negative_prompt": "low quality, bad quality",
"num_inference_steps": 50
},
"logs": "Using seed: 25403\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:36, 1.35it/s]\n 4%|▍ | 2/50 [00:01<00:22, 2.09it/s]\n 6%|▌ | 3/50 [00:01<00:18, 2.54it/s]\n 8%|▊ | 4/50 [00:01<00:16, 2.82it/s]\n 10%|█ | 5/50 [00:01<00:14, 3.00it/s]\n 12%|█▏ | 6/50 [00:02<00:14, 3.13it/s]\n 14%|█▍ | 7/50 [00:02<00:13, 3.21it/s]\n 16%|█▌ | 8/50 [00:02<00:12, 3.26it/s]\n 18%|█▊ | 9/50 [00:03<00:12, 3.30it/s]\n 20%|██ | 10/50 [00:03<00:12, 3.33it/s]\n 22%|██▏ | 11/50 [00:03<00:11, 3.35it/s]\n 24%|██▍ | 12/50 [00:03<00:11, 3.36it/s]\n 26%|██▌ | 13/50 [00:04<00:10, 3.36it/s]\n 28%|██▊ | 14/50 [00:04<00:10, 3.37it/s]\n 30%|███ | 15/50 [00:04<00:10, 3.37it/s]\n 32%|███▏ | 16/50 [00:05<00:10, 3.37it/s]\n 34%|███▍ | 17/50 [00:05<00:09, 3.37it/s]\n 36%|███▌ | 18/50 [00:05<00:09, 3.37it/s]\n 38%|███▊ | 19/50 [00:06<00:09, 3.37it/s]\n 40%|████ | 20/50 [00:06<00:08, 3.37it/s]\n 42%|████▏ | 21/50 [00:06<00:08, 3.37it/s]\n 44%|████▍ | 22/50 [00:06<00:08, 3.38it/s]\n 46%|████▌ | 23/50 [00:07<00:08, 3.37it/s]\n 48%|████▊ | 24/50 [00:07<00:07, 3.38it/s]\n 50%|█████ | 25/50 [00:07<00:07, 3.38it/s]\n 52%|█████▏ | 26/50 [00:08<00:07, 3.38it/s]\n 54%|█████▍ | 27/50 [00:08<00:06, 3.38it/s]\n 56%|█████▌ | 28/50 [00:08<00:06, 3.37it/s]\n 58%|█████▊ | 29/50 [00:09<00:06, 3.37it/s]\n 60%|██████ | 30/50 [00:09<00:05, 3.37it/s]\n 62%|██████▏ | 31/50 [00:09<00:05, 3.37it/s]\n 64%|██████▍ | 32/50 [00:09<00:05, 3.37it/s]\n 66%|██████▌ | 33/50 [00:10<00:05, 3.36it/s]\n 68%|██████▊ | 34/50 [00:10<00:04, 3.36it/s]\n 70%|███████ | 35/50 [00:10<00:04, 3.36it/s]\n 72%|███████▏ | 36/50 [00:11<00:04, 3.36it/s]\n 74%|███████▍ | 37/50 [00:11<00:03, 3.36it/s]\n 76%|███████▌ | 38/50 [00:11<00:03, 3.37it/s]\n 78%|███████▊ | 39/50 [00:11<00:03, 3.38it/s]\n 80%|████████ | 40/50 [00:12<00:02, 3.38it/s]\n 82%|████████▏ | 41/50 [00:12<00:02, 3.38it/s]\n 84%|████████▍ | 42/50 [00:12<00:02, 3.39it/s]\n 86%|████████▌ | 43/50 [00:13<00:02, 3.39it/s]\n 88%|████████▊ | 44/50 [00:13<00:01, 3.39it/s]\n 90%|█████████ | 45/50 [00:13<00:01, 3.39it/s]\n 92%|█████████▏| 46/50 [00:14<00:01, 3.39it/s]\n 94%|█████████▍| 47/50 [00:14<00:00, 3.39it/s]\n 96%|█████████▌| 48/50 [00:14<00:00, 3.39it/s]\n 98%|█████████▊| 49/50 [00:14<00:00, 3.39it/s]\n100%|██████████| 50/50 [00:15<00:00, 3.39it/s]\n100%|██████████| 50/50 [00:15<00:00, 3.28it/s]\n 0%| | 0/10 [00:00<?, ?it/s]\n 10%|█ | 1/10 [00:00<00:02, 4.22it/s]\n 20%|██ | 2/10 [00:00<00:01, 4.29it/s]\n 30%|███ | 3/10 [00:00<00:01, 4.32it/s]\n 40%|████ | 4/10 [00:00<00:01, 4.31it/s]\n 50%|█████ | 5/10 [00:01<00:01, 4.32it/s]\n 60%|██████ | 6/10 [00:01<00:00, 4.33it/s]\n 70%|███████ | 7/10 [00:01<00:00, 4.33it/s]\n 80%|████████ | 8/10 [00:01<00:00, 4.33it/s]\n 90%|█████████ | 9/10 [00:02<00:00, 4.33it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.33it/s]\n100%|██████████| 10/10 [00:02<00:00, 4.32it/s]",
"metrics": {
"predict_time": 21.248046,
"total_time": 197.506928
},
"output": "https://replicate.delivery/pbxt/6qIkIhoz7EosJVfFfrQUnPYSsXfy2WIcTk9u27TM3LP44t1iA/output.png",
"started_at": "2023-08-17T06:24:07.253818Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/v2doo4dbv2foj6ngr26wnjy7cm",
"cancel": "https://api.replicate.com/v1/predictions/v2doo4dbv2foj6ngr26wnjy7cm/cancel"
},
"version": "d63e0b238b2d963d90348e2dad19830fbe372a7a43d90d234b2b63cae76d4397"
}Generated in
Using seed: 25403
0%| | 0/50 [00:00<?, ?it/s]
2%|▏ | 1/50 [00:00<00:36, 1.35it/s]
4%|▍ | 2/50 [00:01<00:22, 2.09it/s]
6%|▌ | 3/50 [00:01<00:18, 2.54it/s]
8%|▊ | 4/50 [00:01<00:16, 2.82it/s]
10%|█ | 5/50 [00:01<00:14, 3.00it/s]
12%|█▏ | 6/50 [00:02<00:14, 3.13it/s]
14%|█▍ | 7/50 [00:02<00:13, 3.21it/s]
16%|█▌ | 8/50 [00:02<00:12, 3.26it/s]
18%|█▊ | 9/50 [00:03<00:12, 3.30it/s]
20%|██ | 10/50 [00:03<00:12, 3.33it/s]
22%|██▏ | 11/50 [00:03<00:11, 3.35it/s]
24%|██▍ | 12/50 [00:03<00:11, 3.36it/s]
26%|██▌ | 13/50 [00:04<00:10, 3.36it/s]
28%|██▊ | 14/50 [00:04<00:10, 3.37it/s]
30%|███ | 15/50 [00:04<00:10, 3.37it/s]
32%|███▏ | 16/50 [00:05<00:10, 3.37it/s]
34%|███▍ | 17/50 [00:05<00:09, 3.37it/s]
36%|███▌ | 18/50 [00:05<00:09, 3.37it/s]
38%|███▊ | 19/50 [00:06<00:09, 3.37it/s]
40%|████ | 20/50 [00:06<00:08, 3.37it/s]
42%|████▏ | 21/50 [00:06<00:08, 3.37it/s]
44%|████▍ | 22/50 [00:06<00:08, 3.38it/s]
46%|████▌ | 23/50 [00:07<00:08, 3.37it/s]
48%|████▊ | 24/50 [00:07<00:07, 3.38it/s]
50%|█████ | 25/50 [00:07<00:07, 3.38it/s]
52%|█████▏ | 26/50 [00:08<00:07, 3.38it/s]
54%|█████▍ | 27/50 [00:08<00:06, 3.38it/s]
56%|█████▌ | 28/50 [00:08<00:06, 3.37it/s]
58%|█████▊ | 29/50 [00:09<00:06, 3.37it/s]
60%|██████ | 30/50 [00:09<00:05, 3.37it/s]
62%|██████▏ | 31/50 [00:09<00:05, 3.37it/s]
64%|██████▍ | 32/50 [00:09<00:05, 3.37it/s]
66%|██████▌ | 33/50 [00:10<00:05, 3.36it/s]
68%|██████▊ | 34/50 [00:10<00:04, 3.36it/s]
70%|███████ | 35/50 [00:10<00:04, 3.36it/s]
72%|███████▏ | 36/50 [00:11<00:04, 3.36it/s]
74%|███████▍ | 37/50 [00:11<00:03, 3.36it/s]
76%|███████▌ | 38/50 [00:11<00:03, 3.37it/s]
78%|███████▊ | 39/50 [00:11<00:03, 3.38it/s]
80%|████████ | 40/50 [00:12<00:02, 3.38it/s]
82%|████████▏ | 41/50 [00:12<00:02, 3.38it/s]
84%|████████▍ | 42/50 [00:12<00:02, 3.39it/s]
86%|████████▌ | 43/50 [00:13<00:02, 3.39it/s]
88%|████████▊ | 44/50 [00:13<00:01, 3.39it/s]
90%|█████████ | 45/50 [00:13<00:01, 3.39it/s]
92%|█████████▏| 46/50 [00:14<00:01, 3.39it/s]
94%|█████████▍| 47/50 [00:14<00:00, 3.39it/s]
96%|█████████▌| 48/50 [00:14<00:00, 3.39it/s]
98%|█████████▊| 49/50 [00:14<00:00, 3.39it/s]
100%|██████████| 50/50 [00:15<00:00, 3.39it/s]
100%|██████████| 50/50 [00:15<00:00, 3.28it/s]
0%| | 0/10 [00:00<?, ?it/s]
10%|█ | 1/10 [00:00<00:02, 4.22it/s]
20%|██ | 2/10 [00:00<00:01, 4.29it/s]
30%|███ | 3/10 [00:00<00:01, 4.32it/s]
40%|████ | 4/10 [00:00<00:01, 4.31it/s]
50%|█████ | 5/10 [00:01<00:01, 4.32it/s]
60%|██████ | 6/10 [00:01<00:00, 4.33it/s]
70%|███████ | 7/10 [00:01<00:00, 4.33it/s]
80%|████████ | 8/10 [00:01<00:00, 4.33it/s]
90%|█████████ | 9/10 [00:02<00:00, 4.33it/s]
100%|██████████| 10/10 [00:02<00:00, 4.33it/s]
100%|██████████| 10/10 [00:02<00:00, 4.32it/s]Examples
Run time and cost
This model costs approximately $0.012 to run on Replicate, or 83 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 12 seconds.