Prediction

Model

dmitru/sdxl-tests:b1c47432

fotdarlbw33lobn34atozy5t3a

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

18.3s

Created

about 2 years ago

Webhook

–

Input

prompt: a paper collage in the style of TOK, showing a girl swimming in a magic underwater world with weird fishes with human eyes
negative_prompt: Empty string
width: 1024
height: 1024
num_outputs: 1
scheduler: K_EULER
num_inference_steps: 50
guidance_scale: 7.5
prompt_strength: 0.8
refine: expert_ensemble_refiner
high_noise_frac: 0.89
apply_watermark: true
lora_scale: 0.92

{
  "apply_watermark": true,
  "guidance_scale": 7.5,
  "height": 1024,
  "high_noise_frac": 0.89,
  "lora_scale": 0.92,
  "negative_prompt": "",
  "num_inference_steps": 50,
  "num_outputs": 1,
  "prompt": "a paper collage in the style of TOK, showing a girl swimming in a magic underwater world with weird fishes with human eyes",
  "prompt_strength": 0.8,
  "refine": "expert_ensemble_refiner",
  "scheduler": "K_EULER",
  "width": 1024
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_cjw**********************************

This is your API token. Keep it to yourself.

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 dmitru/sdxl-tests using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "dmitru/sdxl-tests:b1c4743256c7db1538a013d04f7d87c788cecdb2e13a7fb2696d73a9547ad4ee",
  {
    input: {
      apply_watermark: true,
      guidance_scale: 7.5,
      height: 1024,
      high_noise_frac: 0.89,
      lora_scale: 0.92,
      negative_prompt: "",
      num_inference_steps: 50,
      num_outputs: 1,
      prompt: "a paper collage in the style of TOK, showing a girl swimming in a magic underwater world with weird fishes with human eyes",
      prompt_strength: 0.8,
      refine: "expert_ensemble_refiner",
      scheduler: "K_EULER",
      width: 1024
    }
  }
);

// 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 replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_cjw**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run dmitru/sdxl-tests using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "dmitru/sdxl-tests:b1c4743256c7db1538a013d04f7d87c788cecdb2e13a7fb2696d73a9547ad4ee",
    input={
        "apply_watermark": True,
        "guidance_scale": 7.5,
        "height": 1024,
        "high_noise_frac": 0.89,
        "lora_scale": 0.92,
        "negative_prompt": "",
        "num_inference_steps": 50,
        "num_outputs": 1,
        "prompt": "a paper collage in the style of TOK, showing a girl swimming in a magic underwater world with weird fishes with human eyes",
        "prompt_strength": 0.8,
        "refine": "expert_ensemble_refiner",
        "scheduler": "K_EULER",
        "width": 1024
    }
)

# 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=r8_cjw**********************************

This is your API token. Keep it to yourself.

Run dmitru/sdxl-tests 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": "dmitru/sdxl-tests:b1c4743256c7db1538a013d04f7d87c788cecdb2e13a7fb2696d73a9547ad4ee",
    "input": {
      "apply_watermark": true,
      "guidance_scale": 7.5,
      "height": 1024,
      "high_noise_frac": 0.89,
      "lora_scale": 0.92,
      "negative_prompt": "",
      "num_inference_steps": 50,
      "num_outputs": 1,
      "prompt": "a paper collage in the style of TOK, showing a girl swimming in a magic underwater world with weird fishes with human eyes",
      "prompt_strength": 0.8,
      "refine": "expert_ensemble_refiner",
      "scheduler": "K_EULER",
      "width": 1024
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{
  "id": "fotdarlbw33lobn34atozy5t3a",
  "model": "dmitru/sdxl-tests",
  "version": "b1c4743256c7db1538a013d04f7d87c788cecdb2e13a7fb2696d73a9547ad4ee",
  "input": {
    "apply_watermark": true,
    "guidance_scale": 7.5,
    "height": 1024,
    "high_noise_frac": 0.89,
    "lora_scale": 0.92,
    "negative_prompt": "",
    "num_inference_steps": 50,
    "num_outputs": 1,
    "prompt": "a paper collage in the style of TOK, showing a girl swimming in a magic underwater world with weird fishes with human eyes",
    "prompt_strength": 0.8,
    "refine": "expert_ensemble_refiner",
    "scheduler": "K_EULER",
    "width": 1024
  },
  "logs": "Using seed: 1405\nEnsuring enough disk space...\nFree disk space: 1846372753408\nDownloading weights: https://replicate.delivery/pbxt/QEbNqOOYZurOPVCYxB2pQ2jyTw3Uej4HakeVvD4QVydJONejA/trained_model.tar\nb'Downloaded 186 MB bytes in 0.408s (455 MB/s)\\nExtracted 186 MB in 0.100s (1.9 GB/s)\\n'\nDownloaded weights in 1.0749387741088867 seconds\nLoading fine-tuned model\nDoes not have Unet. assume we are using LoRA\nLoading Unet LoRA\nPrompt: a paper collage in the style of <s0><s1>, showing a girl swimming in a magic underwater world with weird fishes with human eyes\ntxt2img mode\n  0%|          | 0/44 [00:00<?, ?it/s]\n  2%|▏         | 1/44 [00:00<00:11,  3.70it/s]\n  5%|▍         | 2/44 [00:00<00:11,  3.68it/s]\n  7%|▋         | 3/44 [00:00<00:11,  3.68it/s]\n  9%|▉         | 4/44 [00:01<00:10,  3.68it/s]\n 11%|█▏        | 5/44 [00:01<00:10,  3.68it/s]\n 14%|█▎        | 6/44 [00:01<00:10,  3.68it/s]\n 16%|█▌        | 7/44 [00:01<00:10,  3.67it/s]\n 18%|█▊        | 8/44 [00:02<00:09,  3.67it/s]\n 20%|██        | 9/44 [00:02<00:09,  3.67it/s]\n 23%|██▎       | 10/44 [00:02<00:09,  3.67it/s]\n 25%|██▌       | 11/44 [00:02<00:08,  3.67it/s]\n 27%|██▋       | 12/44 [00:03<00:08,  3.67it/s]\n 30%|██▉       | 13/44 [00:03<00:08,  3.67it/s]\n 32%|███▏      | 14/44 [00:03<00:08,  3.67it/s]\n 34%|███▍      | 15/44 [00:04<00:07,  3.67it/s]\n 36%|███▋      | 16/44 [00:04<00:07,  3.67it/s]\n 39%|███▊      | 17/44 [00:04<00:07,  3.67it/s]\n 41%|████      | 18/44 [00:04<00:07,  3.67it/s]\n 43%|████▎     | 19/44 [00:05<00:06,  3.67it/s]\n 45%|████▌     | 20/44 [00:05<00:06,  3.67it/s]\n 48%|████▊     | 21/44 [00:05<00:06,  3.67it/s]\n 50%|█████     | 22/44 [00:05<00:06,  3.67it/s]\n 52%|█████▏    | 23/44 [00:06<00:05,  3.66it/s]\n 55%|█████▍    | 24/44 [00:06<00:05,  3.66it/s]\n 57%|█████▋    | 25/44 [00:06<00:05,  3.66it/s]\n 59%|█████▉    | 26/44 [00:07<00:04,  3.66it/s]\n 61%|██████▏   | 27/44 [00:07<00:04,  3.66it/s]\n 64%|██████▎   | 28/44 [00:07<00:04,  3.66it/s]\n 66%|██████▌   | 29/44 [00:07<00:04,  3.66it/s]\n 68%|██████▊   | 30/44 [00:08<00:03,  3.66it/s]\n 70%|███████   | 31/44 [00:08<00:03,  3.66it/s]\n 73%|███████▎  | 32/44 [00:08<00:03,  3.67it/s]\n 75%|███████▌  | 33/44 [00:08<00:02,  3.67it/s]\n 77%|███████▋  | 34/44 [00:09<00:02,  3.68it/s]\n 80%|███████▉  | 35/44 [00:09<00:02,  3.68it/s]\n 82%|████████▏ | 36/44 [00:09<00:02,  3.68it/s]\n 84%|████████▍ | 37/44 [00:10<00:01,  3.68it/s]\n 86%|████████▋ | 38/44 [00:10<00:01,  3.68it/s]\n 89%|████████▊ | 39/44 [00:10<00:01,  3.68it/s]\n 91%|█████████ | 40/44 [00:10<00:01,  3.68it/s]\n 93%|█████████▎| 41/44 [00:11<00:00,  3.68it/s]\n 95%|█████████▌| 42/44 [00:11<00:00,  3.68it/s]\n 98%|█████████▊| 43/44 [00:11<00:00,  3.68it/s]\n100%|██████████| 44/44 [00:11<00:00,  3.68it/s]\n100%|██████████| 44/44 [00:11<00:00,  3.67it/s]\n  0%|          | 0/6 [00:00<?, ?it/s]\n 17%|█▋        | 1/6 [00:00<00:01,  4.33it/s]\n 33%|███▎      | 2/6 [00:00<00:00,  4.31it/s]\n 50%|█████     | 3/6 [00:00<00:00,  4.31it/s]\n 67%|██████▋   | 4/6 [00:00<00:00,  4.30it/s]\n 83%|████████▎ | 5/6 [00:01<00:00,  4.30it/s]\n100%|██████████| 6/6 [00:01<00:00,  4.29it/s]\n100%|██████████| 6/6 [00:01<00:00,  4.30it/s]",
  "output": [
    "https://replicate.delivery/pbxt/PisdflzzIb3FRKXB4mW9vRLttDuzD30jLvyMYSN552SPqGfRA/out-0.png"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2023-12-02T12:29:00.404928Z",
  "started_at": "2023-12-02T12:29:01.946462Z",
  "completed_at": "2023-12-02T12:29:18.718366Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/fotdarlbw33lobn34atozy5t3a/cancel",
    "get": "https://api.replicate.com/v1/predictions/fotdarlbw33lobn34atozy5t3a"
  },
  "metrics": {
    "predict_time": 16.771904,
    "total_time": 18.313438
  }
}

Generated in

16.8 seconds

Tweak it Report

Using seed: 1405 Ensuring enough disk space... Free disk space: 1846372753408 Downloading weights: https://replicate.delivery/pbxt/QEbNqOOYZurOPVCYxB2pQ2jyTw3Uej4HakeVvD4QVydJONejA/trained_model.tar b'Downloaded 186 MB bytes in 0.408s (455 MB/s)\nExtracted 186 MB in 0.100s (1.9 GB/s)\n' Downloaded weights in 1.0749387741088867 seconds Loading fine-tuned model Does not have Unet. assume we are using LoRA Loading Unet LoRA Prompt: a paper collage in the style of <s0><s1>, showing a girl swimming in a magic underwater world with weird fishes with human eyes txt2img mode 0%| | 0/44 [00:00<?, ?it/s] 2%|▏ | 1/44 [00:00<00:11, 3.70it/s] 5%|▍ | 2/44 [00:00<00:11, 3.68it/s] 7%|▋ | 3/44 [00:00<00:11, 3.68it/s] 9%|▉ | 4/44 [00:01<00:10, 3.68it/s] 11%|█▏ | 5/44 [00:01<00:10, 3.68it/s] 14%|█▎ | 6/44 [00:01<00:10, 3.68it/s] 16%|█▌ | 7/44 [00:01<00:10, 3.67it/s] 18%|█▊ | 8/44 [00:02<00:09, 3.67it/s] 20%|██ | 9/44 [00:02<00:09, 3.67it/s] 23%|██▎ | 10/44 [00:02<00:09, 3.67it/s] 25%|██▌ | 11/44 [00:02<00:08, 3.67it/s] 27%|██▋ | 12/44 [00:03<00:08, 3.67it/s] 30%|██▉ | 13/44 [00:03<00:08, 3.67it/s] 32%|███▏ | 14/44 [00:03<00:08, 3.67it/s] 34%|███▍ | 15/44 [00:04<00:07, 3.67it/s] 36%|███▋ | 16/44 [00:04<00:07, 3.67it/s] 39%|███▊ | 17/44 [00:04<00:07, 3.67it/s] 41%|████ | 18/44 [00:04<00:07, 3.67it/s] 43%|████▎ | 19/44 [00:05<00:06, 3.67it/s] 45%|████▌ | 20/44 [00:05<00:06, 3.67it/s] 48%|████▊ | 21/44 [00:05<00:06, 3.67it/s] 50%|█████ | 22/44 [00:05<00:06, 3.67it/s] 52%|█████▏ | 23/44 [00:06<00:05, 3.66it/s] 55%|█████▍ | 24/44 [00:06<00:05, 3.66it/s] 57%|█████▋ | 25/44 [00:06<00:05, 3.66it/s] 59%|█████▉ | 26/44 [00:07<00:04, 3.66it/s] 61%|██████▏ | 27/44 [00:07<00:04, 3.66it/s] 64%|██████▎ | 28/44 [00:07<00:04, 3.66it/s] 66%|██████▌ | 29/44 [00:07<00:04, 3.66it/s] 68%|██████▊ | 30/44 [00:08<00:03, 3.66it/s] 70%|███████ | 31/44 [00:08<00:03, 3.66it/s] 73%|███████▎ | 32/44 [00:08<00:03, 3.67it/s] 75%|███████▌ | 33/44 [00:08<00:02, 3.67it/s] 77%|███████▋ | 34/44 [00:09<00:02, 3.68it/s] 80%|███████▉ | 35/44 [00:09<00:02, 3.68it/s] 82%|████████▏ | 36/44 [00:09<00:02, 3.68it/s] 84%|████████▍ | 37/44 [00:10<00:01, 3.68it/s] 86%|████████▋ | 38/44 [00:10<00:01, 3.68it/s] 89%|████████▊ | 39/44 [00:10<00:01, 3.68it/s] 91%|█████████ | 40/44 [00:10<00:01, 3.68it/s] 93%|█████████▎| 41/44 [00:11<00:00, 3.68it/s] 95%|█████████▌| 42/44 [00:11<00:00, 3.68it/s] 98%|█████████▊| 43/44 [00:11<00:00, 3.68it/s] 100%|██████████| 44/44 [00:11<00:00, 3.68it/s] 100%|██████████| 44/44 [00:11<00:00, 3.67it/s] 0%| | 0/6 [00:00<?, ?it/s] 17%|█▋ | 1/6 [00:00<00:01, 4.33it/s] 33%|███▎ | 2/6 [00:00<00:00, 4.31it/s] 50%|█████ | 3/6 [00:00<00:00, 4.31it/s] 67%|██████▋ | 4/6 [00:00<00:00, 4.30it/s] 83%|████████▎ | 5/6 [00:01<00:00, 4.30it/s] 100%|██████████| 6/6 [00:01<00:00, 4.29it/s] 100%|██████████| 6/6 [00:01<00:00, 4.30it/s]