Readme
Created by Felix together with the Designing with AI Tools workshop at HSLU in Lucerne 2024.
marcodemutiis/minimal_liminal
minimal_liminal
A model trained on picture of liminal spaces
Input
Run this model in Node.js with one line of code:
npx create-replicate --model=marcodemutiis/minimal_liminal
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";
import fs from "node:fs";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});Run marcodemutiis/minimal_liminal using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"marcodemutiis/minimal_liminal:a48aa7042a28bf43470ff85fe176496f4120f8af24f7e4533823c1a516887b93",
{
input: {
width: 1024,
height: 1024,
prompt: "A photograph of an underground minimal_liminal metro station in New York picturing many animals falling and a floating humpback whale",
refine: "no_refiner",
scheduler: "K_EULER",
lora_scale: 0.72,
num_outputs: 1,
guidance_scale: 7.5,
apply_watermark: true,
high_noise_frac: 0.8,
negative_prompt: "elephant, office, overhead lighting, water, underwater",
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 marcodemutiis/minimal_liminal using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"marcodemutiis/minimal_liminal:a48aa7042a28bf43470ff85fe176496f4120f8af24f7e4533823c1a516887b93",
input={
"width": 1024,
"height": 1024,
"prompt": "A photograph of an underground minimal_liminal metro station in New York picturing many animals falling and a floating humpback whale",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.72,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": True,
"high_noise_frac": 0.8,
"negative_prompt": "elephant, office, overhead lighting, water, underwater",
"prompt_strength": 0.8,
"num_inference_steps": 50
}
)
# 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=<paste-your-token-here>Find your API token in your account settings.
Run marcodemutiis/minimal_liminal 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": "marcodemutiis/minimal_liminal:a48aa7042a28bf43470ff85fe176496f4120f8af24f7e4533823c1a516887b93",
"input": {
"width": 1024,
"height": 1024,
"prompt": "A photograph of an underground minimal_liminal metro station in New York picturing many animals falling and a floating humpback whale",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.72,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"high_noise_frac": 0.8,
"negative_prompt": "elephant, office, overhead lighting, water, underwater",
"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.
Sign in to run this model
Sign in with GitHub
By signing in, you agree to our
terms of service and privacy policy
Output
{
"completed_at": "2024-05-13T14:00:59.598912Z",
"created_at": "2024-05-13T14:00:42.396000Z",
"data_removed": false,
"error": null,
"id": "x1cs0xbgkhrgp0cfe90t5pdw90",
"input": {
"width": 1024,
"height": 1024,
"prompt": "A photograph of an underground minimal_liminal metro station in New York picturing many animals falling and a floating humpback whale",
"refine": "no_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.72,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"high_noise_frac": 0.8,
"negative_prompt": "elephant, office, overhead lighting, water, underwater",
"prompt_strength": 0.8,
"num_inference_steps": 50
},
"logs": "Using seed: 31356\nEnsuring enough disk space...\nFree disk space: 3007819141120\nDownloading weights: https://replicate.delivery/pbxt/zyoapeg5soQdX6Dy6e5vZBbYCfNbg1HUcUkzoyS37PTiU5nlA/trained_model.tar\n2024-05-13T14:00:43Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3f3f1214f91af335 url=https://replicate.delivery/pbxt/zyoapeg5soQdX6Dy6e5vZBbYCfNbg1HUcUkzoyS37PTiU5nlA/trained_model.tar\n2024-05-13T14:00:43Z | INFO | [ Complete ] dest=/src/weights-cache/3f3f1214f91af335 size=\"186 MB\" total_elapsed=0.570s url=https://replicate.delivery/pbxt/zyoapeg5soQdX6Dy6e5vZBbYCfNbg1HUcUkzoyS37PTiU5nlA/trained_model.tar\nb''\nDownloaded weights in 0.7151017189025879 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: A photograph of an underground <s0><s1> metro station in New York picturing many animals falling and a floating humpback whale\ntxt2img mode\n 0%| | 0/50 [00:00<?, ?it/s]\n 2%|▏ | 1/50 [00:00<00:13, 3.66it/s]\n 4%|▍ | 2/50 [00:00<00:13, 3.65it/s]\n 6%|▌ | 3/50 [00:00<00:12, 3.64it/s]\n 8%|▊ | 4/50 [00:01<00:12, 3.64it/s]\n 10%|█ | 5/50 [00:01<00:12, 3.64it/s]\n 12%|█▏ | 6/50 [00:01<00:12, 3.64it/s]\n 14%|█▍ | 7/50 [00:01<00:11, 3.65it/s]\n 16%|█▌ | 8/50 [00:02<00:11, 3.65it/s]\n 18%|█▊ | 9/50 [00:02<00:11, 3.65it/s]\n 20%|██ | 10/50 [00:02<00:10, 3.65it/s]\n 22%|██▏ | 11/50 [00:03<00:10, 3.65it/s]\n 24%|██▍ | 12/50 [00:03<00:10, 3.65it/s]\n 26%|██▌ | 13/50 [00:03<00:10, 3.65it/s]\n 28%|██▊ | 14/50 [00:03<00:09, 3.65it/s]\n 30%|███ | 15/50 [00:04<00:09, 3.65it/s]\n 32%|███▏ | 16/50 [00:04<00:09, 3.65it/s]\n 34%|███▍ | 17/50 [00:04<00:09, 3.65it/s]\n 36%|███▌ | 18/50 [00:04<00:08, 3.65it/s]\n 38%|███▊ | 19/50 [00:05<00:08, 3.65it/s]\n 40%|████ | 20/50 [00:05<00:08, 3.65it/s]\n 42%|████▏ | 21/50 [00:05<00:07, 3.65it/s]\n 44%|████▍ | 22/50 [00:06<00:07, 3.65it/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, 3.64it/s]\n 52%|█████▏ | 26/50 [00:07<00:06, 3.64it/s]\n 54%|█████▍ | 27/50 [00:07<00:06, 3.64it/s]\n 56%|█████▌ | 28/50 [00:07<00:06, 3.64it/s]\n 58%|█████▊ | 29/50 [00:07<00:05, 3.64it/s]\n 60%|██████ | 30/50 [00:08<00:05, 3.64it/s]\n 62%|██████▏ | 31/50 [00:08<00:05, 3.64it/s]\n 64%|██████▍ | 32/50 [00:08<00:04, 3.64it/s]\n 66%|██████▌ | 33/50 [00:09<00:04, 3.64it/s]\n 68%|██████▊ | 34/50 [00:09<00:04, 3.64it/s]\n 70%|███████ | 35/50 [00:09<00:04, 3.64it/s]\n 72%|███████▏ | 36/50 [00:09<00:03, 3.64it/s]\n 74%|███████▍ | 37/50 [00:10<00:03, 3.64it/s]\n 76%|███████▌ | 38/50 [00:10<00:03, 3.64it/s]\n 78%|███████▊ | 39/50 [00:10<00:03, 3.64it/s]\n 80%|████████ | 40/50 [00:10<00:02, 3.64it/s]\n 82%|████████▏ | 41/50 [00:11<00:02, 3.63it/s]\n 84%|████████▍ | 42/50 [00:11<00:02, 3.64it/s]\n 86%|████████▌ | 43/50 [00:11<00:01, 3.63it/s]\n 88%|████████▊ | 44/50 [00:12<00:01, 3.64it/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, 3.64it/s]\n100%|██████████| 50/50 [00:13<00:00, 3.64it/s]\n100%|██████████| 50/50 [00:13<00:00, 3.64it/s]",
"metrics": {
"predict_time": 16.44388,
"total_time": 17.202912
},
"output": [
"https://replicate.delivery/pbxt/bmVWj3zhBtIGN1RVGnPU3sHcwIHSTg6d2NopyxedU5zNe8zSA/out-0.png"
],
"started_at": "2024-05-13T14:00:43.155032Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/x1cs0xbgkhrgp0cfe90t5pdw90",
"cancel": "https://api.replicate.com/v1/predictions/x1cs0xbgkhrgp0cfe90t5pdw90/cancel"
},
"version": "a48aa7042a28bf43470ff85fe176496f4120f8af24f7e4533823c1a516887b93"
}Generated in
Using seed: 31356
Ensuring enough disk space...
Free disk space: 3007819141120
Downloading weights: https://replicate.delivery/pbxt/zyoapeg5soQdX6Dy6e5vZBbYCfNbg1HUcUkzoyS37PTiU5nlA/trained_model.tar
2024-05-13T14:00:43Z | INFO | [ Initiating ] chunk_size=150M dest=/src/weights-cache/3f3f1214f91af335 url=https://replicate.delivery/pbxt/zyoapeg5soQdX6Dy6e5vZBbYCfNbg1HUcUkzoyS37PTiU5nlA/trained_model.tar
2024-05-13T14:00:43Z | INFO | [ Complete ] dest=/src/weights-cache/3f3f1214f91af335 size="186 MB" total_elapsed=0.570s url=https://replicate.delivery/pbxt/zyoapeg5soQdX6Dy6e5vZBbYCfNbg1HUcUkzoyS37PTiU5nlA/trained_model.tar
b''
Downloaded weights in 0.7151017189025879 seconds
Loading fine-tuned model
Does not have Unet. assume we are using LoRA
Loading Unet LoRA
Prompt: A photograph of an underground <s0><s1> metro station in New York picturing many animals falling and a floating humpback whale
txt2img mode
0%| | 0/50 [00:00<?, ?it/s]
2%|▏ | 1/50 [00:00<00:13, 3.66it/s]
4%|▍ | 2/50 [00:00<00:13, 3.65it/s]
6%|▌ | 3/50 [00:00<00:12, 3.64it/s]
8%|▊ | 4/50 [00:01<00:12, 3.64it/s]
10%|█ | 5/50 [00:01<00:12, 3.64it/s]
12%|█▏ | 6/50 [00:01<00:12, 3.64it/s]
14%|█▍ | 7/50 [00:01<00:11, 3.65it/s]
16%|█▌ | 8/50 [00:02<00:11, 3.65it/s]
18%|█▊ | 9/50 [00:02<00:11, 3.65it/s]
20%|██ | 10/50 [00:02<00:10, 3.65it/s]
22%|██▏ | 11/50 [00:03<00:10, 3.65it/s]
24%|██▍ | 12/50 [00:03<00:10, 3.65it/s]
26%|██▌ | 13/50 [00:03<00:10, 3.65it/s]
28%|██▊ | 14/50 [00:03<00:09, 3.65it/s]
30%|███ | 15/50 [00:04<00:09, 3.65it/s]
32%|███▏ | 16/50 [00:04<00:09, 3.65it/s]
34%|███▍ | 17/50 [00:04<00:09, 3.65it/s]
36%|███▌ | 18/50 [00:04<00:08, 3.65it/s]
38%|███▊ | 19/50 [00:05<00:08, 3.65it/s]
40%|████ | 20/50 [00:05<00:08, 3.65it/s]
42%|████▏ | 21/50 [00:05<00:07, 3.65it/s]
44%|████▍ | 22/50 [00:06<00:07, 3.65it/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, 3.64it/s]
52%|█████▏ | 26/50 [00:07<00:06, 3.64it/s]
54%|█████▍ | 27/50 [00:07<00:06, 3.64it/s]
56%|█████▌ | 28/50 [00:07<00:06, 3.64it/s]
58%|█████▊ | 29/50 [00:07<00:05, 3.64it/s]
60%|██████ | 30/50 [00:08<00:05, 3.64it/s]
62%|██████▏ | 31/50 [00:08<00:05, 3.64it/s]
64%|██████▍ | 32/50 [00:08<00:04, 3.64it/s]
66%|██████▌ | 33/50 [00:09<00:04, 3.64it/s]
68%|██████▊ | 34/50 [00:09<00:04, 3.64it/s]
70%|███████ | 35/50 [00:09<00:04, 3.64it/s]
72%|███████▏ | 36/50 [00:09<00:03, 3.64it/s]
74%|███████▍ | 37/50 [00:10<00:03, 3.64it/s]
76%|███████▌ | 38/50 [00:10<00:03, 3.64it/s]
78%|███████▊ | 39/50 [00:10<00:03, 3.64it/s]
80%|████████ | 40/50 [00:10<00:02, 3.64it/s]
82%|████████▏ | 41/50 [00:11<00:02, 3.63it/s]
84%|████████▍ | 42/50 [00:11<00:02, 3.64it/s]
86%|████████▌ | 43/50 [00:11<00:01, 3.63it/s]
88%|████████▊ | 44/50 [00:12<00:01, 3.64it/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, 3.64it/s]
100%|██████████| 50/50 [00:13<00:00, 3.64it/s]
100%|██████████| 50/50 [00:13<00:00, 3.64it/s]Examples
Run time and cost
This model runs on Nvidia L40S GPU hardware. We don't yet have enough runs of this model to provide performance information.