Readme
This model doesn't have a readme.
A fine-tuned SDXL LoRA trained on steet art murals
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run hunterkamerman/sdxl-murals using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"hunterkamerman/sdxl-murals:6e5a86aa3fd077660633fa2b81ded62ac15784ea05266300f1e7540414c834c7",
{
input: {
width: 1024,
height: 1024,
prompt: "tok a street art mural of kim kardashian vibrant colors",
refine: "no_refiner",
scheduler: "K_EULER",
lora_scale: 0.6,
num_outputs: 1,
guidance_scale: 7.5,
apply_watermark: true,
high_noise_frac: 0.8,
negative_prompt: "",
prompt_strength: 0.8,
num_inference_steps: 50
}
}
);
// 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
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import replicate
Run hunterkamerman/sdxl-murals using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"hunterkamerman/sdxl-murals:6e5a86aa3fd077660633fa2b81ded62ac15784ea05266300f1e7540414c834c7",
input={
"width": 1024,
"height": 1024,
"prompt": "tok a street art mural of kim kardashian vibrant colors",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": True,
"high_noise_frac": 0.8,
"negative_prompt": "",
"prompt_strength": 0.8,
"num_inference_steps": 50
}
)
print(output)
To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run hunterkamerman/sdxl-murals 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": "hunterkamerman/sdxl-murals:6e5a86aa3fd077660633fa2b81ded62ac15784ea05266300f1e7540414c834c7",
"input": {
"width": 1024,
"height": 1024,
"prompt": "tok a street art mural of kim kardashian vibrant colors",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"high_noise_frac": 0.8,
"negative_prompt": "",
"prompt_strength": 0.8,
"num_inference_steps": 50
}
}' \
https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
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/hunterkamerman/sdxl-murals@sha256:6e5a86aa3fd077660633fa2b81ded62ac15784ea05266300f1e7540414c834c7 \
-i 'width=1024' \
-i 'height=1024' \
-i 'prompt="tok a street art mural of kim kardashian vibrant colors"' \
-i 'refine="no_refiner"' \
-i 'scheduler="K_EULER"' \
-i 'lora_scale=0.6' \
-i 'num_outputs=1' \
-i 'guidance_scale=7.5' \
-i 'apply_watermark=true' \
-i 'high_noise_frac=0.8' \
-i 'negative_prompt=""' \
-i 'prompt_strength=0.8' \
-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/hunterkamerman/sdxl-murals@sha256:6e5a86aa3fd077660633fa2b81ded62ac15784ea05266300f1e7540414c834c7
curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "tok a street art mural of kim kardashian vibrant colors", "refine": "no_refiner", "scheduler": "K_EULER", "lora_scale": 0.6, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.8, "negative_prompt": "", "prompt_strength": 0.8, "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 $0.027. Alternatively, try out our featured models for free.
By signing in, you agree to our
terms of service and privacy policy
{
"completed_at": "2023-12-04T15:36:42.467159Z",
"created_at": "2023-12-04T15:36:08.751832Z",
"data_removed": false,
"error": null,
"id": "cpiecbtb2tpj4aqq4m6h5kjs7e",
"input": {
"width": 1024,
"height": 1024,
"prompt": "tok a street art mural of kim kardashian vibrant colors",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.6,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"high_noise_frac": 0.8,
"negative_prompt": "",
"prompt_strength": 0.8,
"num_inference_steps": 50
},
"logs": "Using seed: 57523\nEnsuring enough disk space...\nFree disk space: 1549440708608\nDownloading weights: https://replicate.delivery/pbxt/BWxDtfEkhV0KfEGKJIC7mgSdH4WUy3NXoeiXpgcxfURklekPC/trained_model.tar\nb'Downloaded 186 MB bytes in 3.114s (60 MB/s)\\nExtracted 186 MB in 0.066s (2.8 GB/s)\\n'\nDownloaded weights in 3.6236653327941895 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: tok a street art mural of kim kardashian vibrant colors\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:14, 3.49it/s]\n 4%|▍ | 2/50 [00:00<00:13, 3.49it/s]\n 6%|▌ | 3/50 [00:00<00:13, 3.49it/s]\n 8%|▊ | 4/50 [00:01<00:13, 3.49it/s]\n 10%|█ | 5/50 [00:01<00:12, 3.49it/s]\n 12%|█▏ | 6/50 [00:01<00:12, 3.49it/s]\n 14%|█▍ | 7/50 [00:02<00:12, 3.49it/s]\n 16%|█▌ | 8/50 [00:02<00:12, 3.48it/s]\n 18%|█▊ | 9/50 [00:02<00:11, 3.48it/s]\n 20%|██ | 10/50 [00:02<00:11, 3.48it/s]\n 22%|██▏ | 11/50 [00:03<00:11, 3.48it/s]\n 24%|██▍ | 12/50 [00:03<00:10, 3.48it/s]\n 26%|██▌ | 13/50 [00:03<00:10, 3.48it/s]\n 28%|██▊ | 14/50 [00:04<00:10, 3.48it/s]\n 30%|███ | 15/50 [00:04<00:10, 3.48it/s]\n 32%|███▏ | 16/50 [00:04<00:09, 3.48it/s]\n 34%|███▍ | 17/50 [00:04<00:09, 3.48it/s]\n 36%|███▌ | 18/50 [00:05<00:09, 3.48it/s]\n 38%|███▊ | 19/50 [00:05<00:08, 3.47it/s]\n 40%|████ | 20/50 [00:05<00:08, 3.47it/s]\n 42%|████▏ | 21/50 [00:06<00:08, 3.48it/s]\n 44%|████▍ | 22/50 [00:06<00:08, 3.47it/s]\n 46%|████▌ | 23/50 [00:06<00:07, 3.48it/s]\n 48%|████▊ | 24/50 [00:06<00:07, 3.47it/s]\n 50%|█████ | 25/50 [00:07<00:07, 3.47it/s]\n 52%|█████▏ | 26/50 [00:07<00:06, 3.47it/s]\n 54%|█████▍ | 27/50 [00:07<00:06, 3.47it/s]\n 56%|█████▌ | 28/50 [00:08<00:06, 3.47it/s]\n 58%|█████▊ | 29/50 [00:08<00:06, 3.46it/s]\n 60%|██████ | 30/50 [00:08<00:05, 3.47it/s]\n 62%|██████▏ | 31/50 [00:08<00:05, 3.46it/s]\n 64%|██████▍ | 32/50 [00:09<00:05, 3.46it/s]\n 66%|██████▌ | 33/50 [00:09<00:04, 3.46it/s]\n 68%|██████▊ | 34/50 [00:09<00:04, 3.46it/s]\n 70%|███████ | 35/50 [00:10<00:04, 3.46it/s]\n 72%|███████▏ | 36/50 [00:10<00:04, 3.46it/s]\n 74%|███████▍ | 37/50 [00:10<00:03, 3.46it/s]\n 76%|███████▌ | 38/50 [00:10<00:03, 3.46it/s]\n 78%|███████▊ | 39/50 [00:11<00:03, 3.46it/s]\n 80%|████████ | 40/50 [00:11<00:02, 3.46it/s]\n 82%|████████▏ | 41/50 [00:11<00:02, 3.46it/s]\n 84%|████████▍ | 42/50 [00:12<00:02, 3.46it/s]\n 86%|████████▌ | 43/50 [00:12<00:02, 3.46it/s]\n 88%|████████▊ | 44/50 [00:12<00:01, 3.46it/s]\n 90%|█████████ | 45/50 [00:12<00:01, 3.46it/s]\n 92%|█████████▏| 46/50 [00:13<00:01, 3.46it/s]\n 94%|█████████▍| 47/50 [00:13<00:00, 3.46it/s]\n 96%|█████████▌| 48/50 [00:13<00:00, 3.46it/s]\n 98%|█████████▊| 49/50 [00:14<00:00, 3.46it/s]\n100%|██████████| 50/50 [00:14<00:00, 3.46it/s]\n100%|██████████| 50/50 [00:14<00:00, 3.47it/s]",
"metrics": {
"predict_time": 21.023981,
"total_time": 33.715327
},
"output": [
"https://replicate.delivery/pbxt/THc9x4BbMNqtCZgfrzYRpDmKn9aAa06xfPzwNlf3qKcSg09jA/out-0.png"
],
"started_at": "2023-12-04T15:36:21.443178Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/cpiecbtb2tpj4aqq4m6h5kjs7e",
"cancel": "https://api.replicate.com/v1/predictions/cpiecbtb2tpj4aqq4m6h5kjs7e/cancel"
},
"version": "6e5a86aa3fd077660633fa2b81ded62ac15784ea05266300f1e7540414c834c7"
}
Using seed: 57523
Ensuring enough disk space...
Free disk space: 1549440708608
Downloading weights: https://replicate.delivery/pbxt/BWxDtfEkhV0KfEGKJIC7mgSdH4WUy3NXoeiXpgcxfURklekPC/trained_model.tar
b'Downloaded 186 MB bytes in 3.114s (60 MB/s)\nExtracted 186 MB in 0.066s (2.8 GB/s)\n'
Downloaded weights in 3.6236653327941895 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: tok a street art mural of kim kardashian vibrant colors
txt2img mode
0%| | 0/50 [00:00<?, ?it/s]
2%|▏ | 1/50 [00:00<00:14, 3.49it/s]
4%|▍ | 2/50 [00:00<00:13, 3.49it/s]
6%|▌ | 3/50 [00:00<00:13, 3.49it/s]
8%|▊ | 4/50 [00:01<00:13, 3.49it/s]
10%|█ | 5/50 [00:01<00:12, 3.49it/s]
12%|█▏ | 6/50 [00:01<00:12, 3.49it/s]
14%|█▍ | 7/50 [00:02<00:12, 3.49it/s]
16%|█▌ | 8/50 [00:02<00:12, 3.48it/s]
18%|█▊ | 9/50 [00:02<00:11, 3.48it/s]
20%|██ | 10/50 [00:02<00:11, 3.48it/s]
22%|██▏ | 11/50 [00:03<00:11, 3.48it/s]
24%|██▍ | 12/50 [00:03<00:10, 3.48it/s]
26%|██▌ | 13/50 [00:03<00:10, 3.48it/s]
28%|██▊ | 14/50 [00:04<00:10, 3.48it/s]
30%|███ | 15/50 [00:04<00:10, 3.48it/s]
32%|███▏ | 16/50 [00:04<00:09, 3.48it/s]
34%|███▍ | 17/50 [00:04<00:09, 3.48it/s]
36%|███▌ | 18/50 [00:05<00:09, 3.48it/s]
38%|███▊ | 19/50 [00:05<00:08, 3.47it/s]
40%|████ | 20/50 [00:05<00:08, 3.47it/s]
42%|████▏ | 21/50 [00:06<00:08, 3.48it/s]
44%|████▍ | 22/50 [00:06<00:08, 3.47it/s]
46%|████▌ | 23/50 [00:06<00:07, 3.48it/s]
48%|████▊ | 24/50 [00:06<00:07, 3.47it/s]
50%|█████ | 25/50 [00:07<00:07, 3.47it/s]
52%|█████▏ | 26/50 [00:07<00:06, 3.47it/s]
54%|█████▍ | 27/50 [00:07<00:06, 3.47it/s]
56%|█████▌ | 28/50 [00:08<00:06, 3.47it/s]
58%|█████▊ | 29/50 [00:08<00:06, 3.46it/s]
60%|██████ | 30/50 [00:08<00:05, 3.47it/s]
62%|██████▏ | 31/50 [00:08<00:05, 3.46it/s]
64%|██████▍ | 32/50 [00:09<00:05, 3.46it/s]
66%|██████▌ | 33/50 [00:09<00:04, 3.46it/s]
68%|██████▊ | 34/50 [00:09<00:04, 3.46it/s]
70%|███████ | 35/50 [00:10<00:04, 3.46it/s]
72%|███████▏ | 36/50 [00:10<00:04, 3.46it/s]
74%|███████▍ | 37/50 [00:10<00:03, 3.46it/s]
76%|███████▌ | 38/50 [00:10<00:03, 3.46it/s]
78%|███████▊ | 39/50 [00:11<00:03, 3.46it/s]
80%|████████ | 40/50 [00:11<00:02, 3.46it/s]
82%|████████▏ | 41/50 [00:11<00:02, 3.46it/s]
84%|████████▍ | 42/50 [00:12<00:02, 3.46it/s]
86%|████████▌ | 43/50 [00:12<00:02, 3.46it/s]
88%|████████▊ | 44/50 [00:12<00:01, 3.46it/s]
90%|█████████ | 45/50 [00:12<00:01, 3.46it/s]
92%|█████████▏| 46/50 [00:13<00:01, 3.46it/s]
94%|█████████▍| 47/50 [00:13<00:00, 3.46it/s]
96%|█████████▌| 48/50 [00:13<00:00, 3.46it/s]
98%|█████████▊| 49/50 [00:14<00:00, 3.46it/s]
100%|██████████| 50/50 [00:14<00:00, 3.46it/s]
100%|██████████| 50/50 [00:14<00:00, 3.47it/s]
This model costs approximately $0.027 to run on Replicate, or 37 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 28 seconds.
This model doesn't have a readme.
This model is warm. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
Choose a file from your machine
Hint: you can also drag files onto the input
Choose a file from your machine
Hint: you can also drag files onto the input
Using seed: 57523
Ensuring enough disk space...
Free disk space: 1549440708608
Downloading weights: https://replicate.delivery/pbxt/BWxDtfEkhV0KfEGKJIC7mgSdH4WUy3NXoeiXpgcxfURklekPC/trained_model.tar
b'Downloaded 186 MB bytes in 3.114s (60 MB/s)\nExtracted 186 MB in 0.066s (2.8 GB/s)\n'
Downloaded weights in 3.6236653327941895 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: tok a street art mural of kim kardashian vibrant colors
txt2img mode
0%| | 0/50 [00:00<?, ?it/s]
2%|▏ | 1/50 [00:00<00:14, 3.49it/s]
4%|▍ | 2/50 [00:00<00:13, 3.49it/s]
6%|▌ | 3/50 [00:00<00:13, 3.49it/s]
8%|▊ | 4/50 [00:01<00:13, 3.49it/s]
10%|█ | 5/50 [00:01<00:12, 3.49it/s]
12%|█▏ | 6/50 [00:01<00:12, 3.49it/s]
14%|█▍ | 7/50 [00:02<00:12, 3.49it/s]
16%|█▌ | 8/50 [00:02<00:12, 3.48it/s]
18%|█▊ | 9/50 [00:02<00:11, 3.48it/s]
20%|██ | 10/50 [00:02<00:11, 3.48it/s]
22%|██▏ | 11/50 [00:03<00:11, 3.48it/s]
24%|██▍ | 12/50 [00:03<00:10, 3.48it/s]
26%|██▌ | 13/50 [00:03<00:10, 3.48it/s]
28%|██▊ | 14/50 [00:04<00:10, 3.48it/s]
30%|███ | 15/50 [00:04<00:10, 3.48it/s]
32%|███▏ | 16/50 [00:04<00:09, 3.48it/s]
34%|███▍ | 17/50 [00:04<00:09, 3.48it/s]
36%|███▌ | 18/50 [00:05<00:09, 3.48it/s]
38%|███▊ | 19/50 [00:05<00:08, 3.47it/s]
40%|████ | 20/50 [00:05<00:08, 3.47it/s]
42%|████▏ | 21/50 [00:06<00:08, 3.48it/s]
44%|████▍ | 22/50 [00:06<00:08, 3.47it/s]
46%|████▌ | 23/50 [00:06<00:07, 3.48it/s]
48%|████▊ | 24/50 [00:06<00:07, 3.47it/s]
50%|█████ | 25/50 [00:07<00:07, 3.47it/s]
52%|█████▏ | 26/50 [00:07<00:06, 3.47it/s]
54%|█████▍ | 27/50 [00:07<00:06, 3.47it/s]
56%|█████▌ | 28/50 [00:08<00:06, 3.47it/s]
58%|█████▊ | 29/50 [00:08<00:06, 3.46it/s]
60%|██████ | 30/50 [00:08<00:05, 3.47it/s]
62%|██████▏ | 31/50 [00:08<00:05, 3.46it/s]
64%|██████▍ | 32/50 [00:09<00:05, 3.46it/s]
66%|██████▌ | 33/50 [00:09<00:04, 3.46it/s]
68%|██████▊ | 34/50 [00:09<00:04, 3.46it/s]
70%|███████ | 35/50 [00:10<00:04, 3.46it/s]
72%|███████▏ | 36/50 [00:10<00:04, 3.46it/s]
74%|███████▍ | 37/50 [00:10<00:03, 3.46it/s]
76%|███████▌ | 38/50 [00:10<00:03, 3.46it/s]
78%|███████▊ | 39/50 [00:11<00:03, 3.46it/s]
80%|████████ | 40/50 [00:11<00:02, 3.46it/s]
82%|████████▏ | 41/50 [00:11<00:02, 3.46it/s]
84%|████████▍ | 42/50 [00:12<00:02, 3.46it/s]
86%|████████▌ | 43/50 [00:12<00:02, 3.46it/s]
88%|████████▊ | 44/50 [00:12<00:01, 3.46it/s]
90%|█████████ | 45/50 [00:12<00:01, 3.46it/s]
92%|█████████▏| 46/50 [00:13<00:01, 3.46it/s]
94%|█████████▍| 47/50 [00:13<00:00, 3.46it/s]
96%|█████████▌| 48/50 [00:13<00:00, 3.46it/s]
98%|█████████▊| 49/50 [00:14<00:00, 3.46it/s]
100%|██████████| 50/50 [00:14<00:00, 3.46it/s]
100%|██████████| 50/50 [00:14<00:00, 3.47it/s]