Prediction
organisciak/rad-posters:c765170fID
faaripdbnieij37xelm3mm5ol4
Status
Succeeded
Source
Web
Hardware
A40 (Large)
Total duration
Created
by @organisciak
Input
- seed
- 23014
- width
- 768
- height
- 1024
- prompt
- poster illustration of a skull, limited edition print
- refine
- expert_ensemble_refiner
- scheduler
- K_EULER
- lora_scale
- 0.02
- num_outputs
- 1
- guidance_scale
- 7.5
- apply_watermark
- high_noise_frac
- 0.77
- negative_prompt
- text, heading
- prompt_strength
- 0.62
- num_inference_steps
- 50
{
"seed": 23014,
"width": 768,
"height": 1024,
"prompt": "poster illustration of a skull, limited edition print",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.02,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"high_noise_frac": 0.77,
"negative_prompt": "text, heading",
"prompt_strength": 0.62,
"num_inference_steps": 50
}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 organisciak/rad-posters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"organisciak/rad-posters:c765170f1a906ca7ccd849dcd8c477ea54f72540d37d1f2b109f3dc64132fbb5",
{
input: {
seed: 23014,
width: 768,
height: 1024,
prompt: "poster illustration of a skull, limited edition print",
refine: "expert_ensemble_refiner",
scheduler: "K_EULER",
lora_scale: 0.02,
num_outputs: 1,
guidance_scale: 7.5,
apply_watermark: true,
high_noise_frac: 0.77,
negative_prompt: "text, heading",
prompt_strength: 0.62,
num_inference_steps: 50
}
}
);
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 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 organisciak/rad-posters using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"organisciak/rad-posters:c765170f1a906ca7ccd849dcd8c477ea54f72540d37d1f2b109f3dc64132fbb5",
input={
"seed": 23014,
"width": 768,
"height": 1024,
"prompt": "poster illustration of a skull, limited edition print",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.02,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": True,
"high_noise_frac": 0.77,
"negative_prompt": "text, heading",
"prompt_strength": 0.62,
"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 organisciak/rad-posters 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": "c765170f1a906ca7ccd849dcd8c477ea54f72540d37d1f2b109f3dc64132fbb5",
"input": {
"seed": 23014,
"width": 768,
"height": 1024,
"prompt": "poster illustration of a skull, limited edition print",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.02,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"high_noise_frac": 0.77,
"negative_prompt": "text, heading",
"prompt_strength": 0.62,
"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/organisciak/rad-posters@sha256:c765170f1a906ca7ccd849dcd8c477ea54f72540d37d1f2b109f3dc64132fbb5 \
-i 'seed=23014' \
-i 'width=768' \
-i 'height=1024' \
-i 'prompt="poster illustration of a skull, limited edition print"' \
-i 'refine="expert_ensemble_refiner"' \
-i 'scheduler="K_EULER"' \
-i 'lora_scale=0.02' \
-i 'num_outputs=1' \
-i 'guidance_scale=7.5' \
-i 'apply_watermark=true' \
-i 'high_noise_frac=0.77' \
-i 'negative_prompt="text, heading"' \
-i 'prompt_strength=0.62' \
-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/organisciak/rad-posters@sha256:c765170f1a906ca7ccd849dcd8c477ea54f72540d37d1f2b109f3dc64132fbb5curl -s -X POST \ -H "Content-Type: application/json" \ -d $'{ "input": { "seed": 23014, "width": 768, "height": 1024, "prompt": "poster illustration of a skull, limited edition print", "refine": "expert_ensemble_refiner", "scheduler": "K_EULER", "lora_scale": 0.02, "num_outputs": 1, "guidance_scale": 7.5, "apply_watermark": true, "high_noise_frac": 0.77, "negative_prompt": "text, heading", "prompt_strength": 0.62, "num_inference_steps": 50 } }' \ http://localhost:5000/predictions
To learn more, take a look at the Cog documentation.
Output
{
"completed_at": "2023-09-15T22:43:14.722555Z",
"created_at": "2023-09-15T22:43:03.950087Z",
"data_removed": false,
"error": null,
"id": "faaripdbnieij37xelm3mm5ol4",
"input": {
"seed": 23014,
"width": 768,
"height": 1024,
"prompt": "poster illustration of a skull, limited edition print",
"refine": "expert_ensemble_refiner",
"scheduler": "K_EULER",
"lora_scale": 0.02,
"num_outputs": 1,
"guidance_scale": 7.5,
"apply_watermark": true,
"high_noise_frac": 0.77,
"negative_prompt": "text, heading",
"prompt_strength": 0.62,
"num_inference_steps": 50
},
"logs": "Using seed: 23014\nPrompt: poster illustration of a skull, limited edition print\ntxt2img mode\n 0%| | 0/38 [00:00<?, ?it/s]\n 3%|▎ | 1/38 [00:00<00:07, 4.97it/s]\n 5%|▌ | 2/38 [00:00<00:07, 4.96it/s]\n 8%|▊ | 3/38 [00:00<00:07, 4.95it/s]\n 11%|█ | 4/38 [00:00<00:06, 4.95it/s]\n 13%|█▎ | 5/38 [00:01<00:06, 4.94it/s]\n 16%|█▌ | 6/38 [00:01<00:06, 4.94it/s]\n 18%|█▊ | 7/38 [00:01<00:06, 4.93it/s]\n 21%|██ | 8/38 [00:01<00:06, 4.93it/s]\n 24%|██▎ | 9/38 [00:01<00:05, 4.93it/s]\n 26%|██▋ | 10/38 [00:02<00:05, 4.93it/s]\n 29%|██▉ | 11/38 [00:02<00:05, 4.93it/s]\n 32%|███▏ | 12/38 [00:02<00:05, 4.93it/s]\n 34%|███▍ | 13/38 [00:02<00:05, 4.93it/s]\n 37%|███▋ | 14/38 [00:02<00:04, 4.92it/s]\n 39%|███▉ | 15/38 [00:03<00:04, 4.92it/s]\n 42%|████▏ | 16/38 [00:03<00:04, 4.93it/s]\n 45%|████▍ | 17/38 [00:03<00:04, 4.93it/s]\n 47%|████▋ | 18/38 [00:03<00:04, 4.93it/s]\n 50%|█████ | 19/38 [00:03<00:03, 4.92it/s]\n 53%|█████▎ | 20/38 [00:04<00:03, 4.92it/s]\n 55%|█████▌ | 21/38 [00:04<00:03, 4.93it/s]\n 58%|█████▊ | 22/38 [00:04<00:03, 4.92it/s]\n 61%|██████ | 23/38 [00:04<00:03, 4.92it/s]\n 63%|██████▎ | 24/38 [00:04<00:02, 4.92it/s]\n 66%|██████▌ | 25/38 [00:05<00:02, 4.93it/s]\n 68%|██████▊ | 26/38 [00:05<00:02, 4.93it/s]\n 71%|███████ | 27/38 [00:05<00:02, 4.94it/s]\n 74%|███████▎ | 28/38 [00:05<00:02, 4.94it/s]\n 76%|███████▋ | 29/38 [00:05<00:01, 4.94it/s]\n 79%|███████▉ | 30/38 [00:06<00:01, 4.95it/s]\n 82%|████████▏ | 31/38 [00:06<00:01, 4.95it/s]\n 84%|████████▍ | 32/38 [00:06<00:01, 4.95it/s]\n 87%|████████▋ | 33/38 [00:06<00:01, 4.95it/s]\n 89%|████████▉ | 34/38 [00:06<00:00, 4.95it/s]\n 92%|█████████▏| 35/38 [00:07<00:00, 4.95it/s]\n 95%|█████████▍| 36/38 [00:07<00:00, 4.95it/s]\n 97%|█████████▋| 37/38 [00:07<00:00, 4.95it/s]\n100%|██████████| 38/38 [00:07<00:00, 4.95it/s]\n100%|██████████| 38/38 [00:07<00:00, 4.94it/s]\n 0%| | 0/12 [00:00<?, ?it/s]\n 8%|▊ | 1/12 [00:00<00:01, 6.22it/s]\n 17%|█▋ | 2/12 [00:00<00:01, 6.17it/s]\n 25%|██▌ | 3/12 [00:00<00:01, 6.16it/s]\n 33%|███▎ | 4/12 [00:00<00:01, 6.15it/s]\n 42%|████▏ | 5/12 [00:00<00:01, 6.16it/s]\n 50%|█████ | 6/12 [00:00<00:00, 6.15it/s]\n 58%|█████▊ | 7/12 [00:01<00:00, 6.14it/s]\n 67%|██████▋ | 8/12 [00:01<00:00, 6.14it/s]\n 75%|███████▌ | 9/12 [00:01<00:00, 6.14it/s]\n 83%|████████▎ | 10/12 [00:01<00:00, 6.14it/s]\n 92%|█████████▏| 11/12 [00:01<00:00, 6.14it/s]\n100%|██████████| 12/12 [00:01<00:00, 6.15it/s]\n100%|██████████| 12/12 [00:01<00:00, 6.15it/s]",
"metrics": {
"predict_time": 10.796288,
"total_time": 10.772468
},
"output": [
"https://replicate.delivery/pbxt/zTCBe4rf6mmIUEBg6q4ReilZzc09aBwedxqQp2xYgmgLAkSGB/out-0.png"
],
"started_at": "2023-09-15T22:43:03.926267Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/faaripdbnieij37xelm3mm5ol4",
"cancel": "https://api.replicate.com/v1/predictions/faaripdbnieij37xelm3mm5ol4/cancel"
},
"version": "c765170f1a906ca7ccd849dcd8c477ea54f72540d37d1f2b109f3dc64132fbb5"
}Generated in
Using seed: 23014
Prompt: poster illustration of a skull, limited edition print
txt2img mode
0%| | 0/38 [00:00<?, ?it/s]
3%|▎ | 1/38 [00:00<00:07, 4.97it/s]
5%|▌ | 2/38 [00:00<00:07, 4.96it/s]
8%|▊ | 3/38 [00:00<00:07, 4.95it/s]
11%|█ | 4/38 [00:00<00:06, 4.95it/s]
13%|█▎ | 5/38 [00:01<00:06, 4.94it/s]
16%|█▌ | 6/38 [00:01<00:06, 4.94it/s]
18%|█▊ | 7/38 [00:01<00:06, 4.93it/s]
21%|██ | 8/38 [00:01<00:06, 4.93it/s]
24%|██▎ | 9/38 [00:01<00:05, 4.93it/s]
26%|██▋ | 10/38 [00:02<00:05, 4.93it/s]
29%|██▉ | 11/38 [00:02<00:05, 4.93it/s]
32%|███▏ | 12/38 [00:02<00:05, 4.93it/s]
34%|███▍ | 13/38 [00:02<00:05, 4.93it/s]
37%|███▋ | 14/38 [00:02<00:04, 4.92it/s]
39%|███▉ | 15/38 [00:03<00:04, 4.92it/s]
42%|████▏ | 16/38 [00:03<00:04, 4.93it/s]
45%|████▍ | 17/38 [00:03<00:04, 4.93it/s]
47%|████▋ | 18/38 [00:03<00:04, 4.93it/s]
50%|█████ | 19/38 [00:03<00:03, 4.92it/s]
53%|█████▎ | 20/38 [00:04<00:03, 4.92it/s]
55%|█████▌ | 21/38 [00:04<00:03, 4.93it/s]
58%|█████▊ | 22/38 [00:04<00:03, 4.92it/s]
61%|██████ | 23/38 [00:04<00:03, 4.92it/s]
63%|██████▎ | 24/38 [00:04<00:02, 4.92it/s]
66%|██████▌ | 25/38 [00:05<00:02, 4.93it/s]
68%|██████▊ | 26/38 [00:05<00:02, 4.93it/s]
71%|███████ | 27/38 [00:05<00:02, 4.94it/s]
74%|███████▎ | 28/38 [00:05<00:02, 4.94it/s]
76%|███████▋ | 29/38 [00:05<00:01, 4.94it/s]
79%|███████▉ | 30/38 [00:06<00:01, 4.95it/s]
82%|████████▏ | 31/38 [00:06<00:01, 4.95it/s]
84%|████████▍ | 32/38 [00:06<00:01, 4.95it/s]
87%|████████▋ | 33/38 [00:06<00:01, 4.95it/s]
89%|████████▉ | 34/38 [00:06<00:00, 4.95it/s]
92%|█████████▏| 35/38 [00:07<00:00, 4.95it/s]
95%|█████████▍| 36/38 [00:07<00:00, 4.95it/s]
97%|█████████▋| 37/38 [00:07<00:00, 4.95it/s]
100%|██████████| 38/38 [00:07<00:00, 4.95it/s]
100%|██████████| 38/38 [00:07<00:00, 4.94it/s]
0%| | 0/12 [00:00<?, ?it/s]
8%|▊ | 1/12 [00:00<00:01, 6.22it/s]
17%|█▋ | 2/12 [00:00<00:01, 6.17it/s]
25%|██▌ | 3/12 [00:00<00:01, 6.16it/s]
33%|███▎ | 4/12 [00:00<00:01, 6.15it/s]
42%|████▏ | 5/12 [00:00<00:01, 6.16it/s]
50%|█████ | 6/12 [00:00<00:00, 6.15it/s]
58%|█████▊ | 7/12 [00:01<00:00, 6.14it/s]
67%|██████▋ | 8/12 [00:01<00:00, 6.14it/s]
75%|███████▌ | 9/12 [00:01<00:00, 6.14it/s]
83%|████████▎ | 10/12 [00:01<00:00, 6.14it/s]
92%|█████████▏| 11/12 [00:01<00:00, 6.14it/s]
100%|██████████| 12/12 [00:01<00:00, 6.15it/s]
100%|██████████| 12/12 [00:01<00:00, 6.15it/s]