Readme
Created by Enzo Lanne. Contact: https://twitter.com/Zozonezz
swartype
/
sdxl-pixar
Create Pixar poster easily with SDXL Pixar.
- Public
- 646.4K runs
-
L40S
- SDXL fine-tune
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=swartype/sdxl-pixar
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 swartype/sdxl-pixar using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"swartype/sdxl-pixar:81f8bbd3463056c8521eb528feb10509cc1385e2fabef590747f159848589048",
{
input: {
width: 1024,
height: 1024,
prompt: "breathtaking 3D animated movie poster in the style of Pixar with superman at the center and a destroyed city in the background",
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: "noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo, NSFW",
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.
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 swartype/sdxl-pixar using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"swartype/sdxl-pixar:81f8bbd3463056c8521eb528feb10509cc1385e2fabef590747f159848589048",
input={
"width": 1024,
"height": 1024,
"prompt": "breathtaking 3D animated movie poster in the style of Pixar with superman at the center and a destroyed city in the background",
"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": "noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo, NSFW",
"prompt_strength": 0.8,
"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 swartype/sdxl-pixar 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": "81f8bbd3463056c8521eb528feb10509cc1385e2fabef590747f159848589048",
"input": {
"width": 1024,
"height": 1024,
"prompt": "breathtaking 3D animated movie poster in the style of Pixar with superman at the center and a destroyed city in the background",
"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": "noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo, NSFW",
"prompt_strength": 0.8,
"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/swartype/sdxl-pixar@sha256:81f8bbd3463056c8521eb528feb10509cc1385e2fabef590747f159848589048 \
-i 'width=1024' \
-i 'height=1024' \
-i 'prompt="breathtaking 3D animated movie poster in the style of Pixar with superman at the center and a destroyed city in the background"' \
-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="noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo, NSFW"' \
-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/swartype/sdxl-pixar@sha256:81f8bbd3463056c8521eb528feb10509cc1385e2fabef590747f159848589048curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "width": 1024, "height": 1024, "prompt": "breathtaking 3D animated movie poster in the style of Pixar with superman at the center and a destroyed city in the background", "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": "noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo, NSFW", "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 $0.0048. 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": "2023-10-22T10:33:18.715005Z",
"created_at": "2023-10-22T10:32:47.919870Z",
"data_removed": false,
"error": null,
"id": "ekgonptbzk3zkoe5z2la54qmga",
"input": {
"width": 1024,
"height": 1024,
"prompt": "breathtaking 3D animated movie poster in the style of Pixar with superman at the center and a destroyed city in the background",
"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": "noisy, sloppy, messy, grainy, highly detailed, ultra textured, photo, NSFW",
"prompt_strength": 0.8,
"num_inference_steps": 50
},
"logs": "Using seed: 15124\nEnsuring enough disk space...\nFree disk space: 1763095707648\nDownloading weights: https://pbxt.replicate.delivery/J1q6LulfioyaM6jmrFPoDH8UtucBitfbZk2cqpp6rD6PFWwRA/trained_model.tar\nb'Downloaded 186 MB bytes in 11.867s (16 MB/s)\\nExtracted 186 MB in 0.079s (2.3 GB/s)\\n'\nDownloaded weights in 12.45238733291626 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: breathtaking 3D animated movie poster in the style of Pixar with superman at the center and a destroyed city in the background\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:13, 3.68it/s]\n 4%|▍ | 2/50 [00:00<00:13, 3.67it/s]\n 6%|▌ | 3/50 [00:00<00:12, 3.66it/s]\n 8%|▊ | 4/50 [00:01<00:12, 3.65it/s]\n 10%|█ | 5/50 [00:01<00:12, 3.65it/s]\n 12%|█▏ | 6/50 [00:01<00:12, 3.65it/s]\n 14%|█▍ | 7/50 [00:01<00:11, 3.65it/s]\n 16%|█▌ | 8/50 [00:02<00:11, 3.64it/s]\n 18%|█▊ | 9/50 [00:02<00:11, 3.64it/s]\n 20%|██ | 10/50 [00:02<00:10, 3.64it/s]\n 22%|██▏ | 11/50 [00:03<00:10, 3.64it/s]\n 24%|██▍ | 12/50 [00:03<00:10, 3.64it/s]\n 26%|██▌ | 13/50 [00:03<00:10, 3.64it/s]\n 28%|██▊ | 14/50 [00:03<00:09, 3.64it/s]\n 30%|███ | 15/50 [00:04<00:09, 3.64it/s]\n 32%|███▏ | 16/50 [00:04<00:09, 3.64it/s]\n 34%|███▍ | 17/50 [00:04<00:09, 3.64it/s]\n 36%|███▌ | 18/50 [00:04<00:08, 3.64it/s]\n 38%|███▊ | 19/50 [00:05<00:08, 3.64it/s]\n 40%|████ | 20/50 [00:05<00:08, 3.63it/s]\n 42%|████▏ | 21/50 [00:05<00:07, 3.64it/s]\n 44%|████▍ | 22/50 [00:06<00:07, 3.64it/s]\n 46%|████▌ | 23/50 [00:06<00:07, 3.64it/s]\n 48%|████▊ | 24/50 [00:06<00:07, 3.64it/s]\n 50%|█████ | 25/50 [00:06<00:06, 3.63it/s]\n 52%|█████▏ | 26/50 [00:07<00:06, 3.63it/s]\n 54%|█████▍ | 27/50 [00:07<00:06, 3.63it/s]\n 56%|█████▌ | 28/50 [00:07<00:06, 3.64it/s]\n 58%|█████▊ | 29/50 [00:07<00:05, 3.63it/s]\n 60%|██████ | 30/50 [00:08<00:05, 3.63it/s]\n 62%|██████▏ | 31/50 [00:08<00:05, 3.63it/s]\n 64%|██████▍ | 32/50 [00:08<00:04, 3.63it/s]\n 66%|██████▌ | 33/50 [00:09<00:04, 3.63it/s]\n 68%|██████▊ | 34/50 [00:09<00:04, 3.63it/s]\n 70%|███████ | 35/50 [00:09<00:04, 3.63it/s]\n 72%|███████▏ | 36/50 [00:09<00:03, 3.63it/s]\n 74%|███████▍ | 37/50 [00:10<00:03, 3.63it/s]\n 76%|███████▌ | 38/50 [00:10<00:03, 3.63it/s]\n 78%|███████▊ | 39/50 [00:10<00:03, 3.63it/s]\n 80%|████████ | 40/50 [00:10<00:02, 3.63it/s]\n 82%|████████▏ | 41/50 [00:11<00:02, 3.63it/s]\n 84%|████████▍ | 42/50 [00:11<00:02, 3.63it/s]\n 86%|████████▌ | 43/50 [00:11<00:01, 3.63it/s]\n 88%|████████▊ | 44/50 [00:12<00:01, 3.63it/s]\n 90%|█████████ | 45/50 [00:12<00:01, 3.63it/s]\n 92%|█████████▏| 46/50 [00:12<00:01, 3.63it/s]\n 94%|█████████▍| 47/50 [00:12<00:00, 3.63it/s]\n 96%|█████████▌| 48/50 [00:13<00:00, 3.63it/s]\n 98%|█████████▊| 49/50 [00:13<00:00, 3.63it/s]\n100%|██████████| 50/50 [00:13<00:00, 3.63it/s]\n100%|██████████| 50/50 [00:13<00:00, 3.64it/s]",
"metrics": {
"predict_time": 29.29581,
"total_time": 30.795135
},
"output": [
"https://replicate.delivery/pbxt/p2zBSSZ7IT4AHR381vy23z6IRAOfr43sf2j6bXIsYuZuxqwRA/out-0.png"
],
"started_at": "2023-10-22T10:32:49.419195Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/ekgonptbzk3zkoe5z2la54qmga",
"cancel": "https://api.replicate.com/v1/predictions/ekgonptbzk3zkoe5z2la54qmga/cancel"
},
"version": "81f8bbd3463056c8521eb528feb10509cc1385e2fabef590747f159848589048"
}Generated in
Using seed: 15124
Ensuring enough disk space...
Free disk space: 1763095707648
Downloading weights: https://pbxt.replicate.delivery/J1q6LulfioyaM6jmrFPoDH8UtucBitfbZk2cqpp6rD6PFWwRA/trained_model.tar
b'Downloaded 186 MB bytes in 11.867s (16 MB/s)\nExtracted 186 MB in 0.079s (2.3 GB/s)\n'
Downloaded weights in 12.45238733291626 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: breathtaking 3D animated movie poster in the style of Pixar with superman at the center and a destroyed city in the background
txt2img mode
0%| | 0/50 [00:00<?, ?it/s]
2%|▏ | 1/50 [00:00<00:13, 3.68it/s]
4%|▍ | 2/50 [00:00<00:13, 3.67it/s]
6%|▌ | 3/50 [00:00<00:12, 3.66it/s]
8%|▊ | 4/50 [00:01<00:12, 3.65it/s]
10%|█ | 5/50 [00:01<00:12, 3.65it/s]
12%|█▏ | 6/50 [00:01<00:12, 3.65it/s]
14%|█▍ | 7/50 [00:01<00:11, 3.65it/s]
16%|█▌ | 8/50 [00:02<00:11, 3.64it/s]
18%|█▊ | 9/50 [00:02<00:11, 3.64it/s]
20%|██ | 10/50 [00:02<00:10, 3.64it/s]
22%|██▏ | 11/50 [00:03<00:10, 3.64it/s]
24%|██▍ | 12/50 [00:03<00:10, 3.64it/s]
26%|██▌ | 13/50 [00:03<00:10, 3.64it/s]
28%|██▊ | 14/50 [00:03<00:09, 3.64it/s]
30%|███ | 15/50 [00:04<00:09, 3.64it/s]
32%|███▏ | 16/50 [00:04<00:09, 3.64it/s]
34%|███▍ | 17/50 [00:04<00:09, 3.64it/s]
36%|███▌ | 18/50 [00:04<00:08, 3.64it/s]
38%|███▊ | 19/50 [00:05<00:08, 3.64it/s]
40%|████ | 20/50 [00:05<00:08, 3.63it/s]
42%|████▏ | 21/50 [00:05<00:07, 3.64it/s]
44%|████▍ | 22/50 [00:06<00:07, 3.64it/s]
46%|████▌ | 23/50 [00:06<00:07, 3.64it/s]
48%|████▊ | 24/50 [00:06<00:07, 3.64it/s]
50%|█████ | 25/50 [00:06<00:06, 3.63it/s]
52%|█████▏ | 26/50 [00:07<00:06, 3.63it/s]
54%|█████▍ | 27/50 [00:07<00:06, 3.63it/s]
56%|█████▌ | 28/50 [00:07<00:06, 3.64it/s]
58%|█████▊ | 29/50 [00:07<00:05, 3.63it/s]
60%|██████ | 30/50 [00:08<00:05, 3.63it/s]
62%|██████▏ | 31/50 [00:08<00:05, 3.63it/s]
64%|██████▍ | 32/50 [00:08<00:04, 3.63it/s]
66%|██████▌ | 33/50 [00:09<00:04, 3.63it/s]
68%|██████▊ | 34/50 [00:09<00:04, 3.63it/s]
70%|███████ | 35/50 [00:09<00:04, 3.63it/s]
72%|███████▏ | 36/50 [00:09<00:03, 3.63it/s]
74%|███████▍ | 37/50 [00:10<00:03, 3.63it/s]
76%|███████▌ | 38/50 [00:10<00:03, 3.63it/s]
78%|███████▊ | 39/50 [00:10<00:03, 3.63it/s]
80%|████████ | 40/50 [00:10<00:02, 3.63it/s]
82%|████████▏ | 41/50 [00:11<00:02, 3.63it/s]
84%|████████▍ | 42/50 [00:11<00:02, 3.63it/s]
86%|████████▌ | 43/50 [00:11<00:01, 3.63it/s]
88%|████████▊ | 44/50 [00:12<00:01, 3.63it/s]
90%|█████████ | 45/50 [00:12<00:01, 3.63it/s]
92%|█████████▏| 46/50 [00:12<00:01, 3.63it/s]
94%|█████████▍| 47/50 [00:12<00:00, 3.63it/s]
96%|█████████▌| 48/50 [00:13<00:00, 3.63it/s]
98%|█████████▊| 49/50 [00:13<00:00, 3.63it/s]
100%|██████████| 50/50 [00:13<00:00, 3.63it/s]
100%|██████████| 50/50 [00:13<00:00, 3.64it/s]Examples
Run time and cost
This model costs approximately $0.0048 to run on Replicate, or 208 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 5 seconds.