Prediction

Model

datacte/proteus-v0.3:b28b79d7

pwcksmtb6g6un4xjjn6repaxt4

Status

Succeeded

Source

Web

Hardware

A40 (Large)

Total duration

65.5s

Created

almost 2 years ago

Webhook

–

Input

prompt: Anime mugshot of a tough woman. She is holding a prison sign that reads "Proteus". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)
negative_prompt: nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image
width: 1024
height: 1024
num_outputs: 1
scheduler: DPM++2MSDE
num_inference_steps: 30
guidance_scale: 7.5
prompt_strength: 0.8
apply_watermark: true

{
  "apply_watermark": true,
  "guidance_scale": 7.5,
  "height": 1024,
  "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image",
  "num_inference_steps": 30,
  "num_outputs": 1,
  "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)",
  "prompt_strength": 0.8,
  "scheduler": "DPM++2MSDE",
  "width": 1024
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_BxF**********************************

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 datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48",
  {
    input: {
      apply_watermark: true,
      guidance_scale: 7.5,
      height: 1024,
      negative_prompt: "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image",
      num_inference_steps: 30,
      num_outputs: 1,
      prompt: "Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)",
      prompt_strength: 0.8,
      scheduler: "DPM++2MSDE",
      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_BxF**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run datacte/proteus-v0.3 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48",
    input={
        "apply_watermark": True,
        "guidance_scale": 7.5,
        "height": 1024,
        "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image",
        "num_inference_steps": 30,
        "num_outputs": 1,
        "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)",
        "prompt_strength": 0.8,
        "scheduler": "DPM++2MSDE",
        "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_BxF**********************************

This is your API token. Keep it to yourself.

Run datacte/proteus-v0.3 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": "datacte/proteus-v0.3:b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48",
    "input": {
      "apply_watermark": true,
      "guidance_scale": 7.5,
      "height": 1024,
      "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image",
      "num_inference_steps": 30,
      "num_outputs": 1,
      "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \\"Proteus\\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)",
      "prompt_strength": 0.8,
      "scheduler": "DPM++2MSDE",
      "width": 1024
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "pwcksmtb6g6un4xjjn6repaxt4",
  "model": "datacte/proteus-v0.3",
  "version": "b28b79d725c8548b173b6a19ff9bffd16b9b80df5b18b8dc5cb9e1ee471bfa48",
  "input": {
    "apply_watermark": true,
    "guidance_scale": 7.5,
    "height": 1024,
    "negative_prompt": "nsfw, bad quality, bad anatomy, worst quality, low quality, low resolutions, extra fingers, blur, blurry, ugly, wrongs proportions, watermark, image artifacts, lowres, ugly, jpeg artifacts, deformed, noisy image",
    "num_inference_steps": 30,
    "num_outputs": 1,
    "prompt": "Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)",
    "prompt_strength": 0.8,
    "scheduler": "DPM++2MSDE",
    "width": 1024
  },
  "logs": "Using seed: 1185096284\nPrompt: Anime mugshot of a tough woman. She is holding a prison sign that reads \"Proteus\". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2)\ntxt2img mode\n  0%|          | 0/30 [00:00<?, ?it/s]\n  3%|▎         | 1/30 [00:00<00:15,  1.82it/s]\n  7%|▋         | 2/30 [00:00<00:12,  2.16it/s]\n 10%|█         | 3/30 [00:01<00:11,  2.30it/s]\n 13%|█▎        | 4/30 [00:01<00:10,  2.38it/s]\n 17%|█▋        | 5/30 [00:02<00:10,  2.41it/s]\n 20%|██        | 6/30 [00:02<00:09,  2.44it/s]\n 23%|██▎       | 7/30 [00:02<00:09,  2.45it/s]\n 27%|██▋       | 8/30 [00:03<00:08,  2.46it/s]\n 30%|███       | 9/30 [00:03<00:08,  2.47it/s]\n 33%|███▎      | 10/30 [00:04<00:08,  2.47it/s]\n 37%|███▋      | 11/30 [00:04<00:07,  2.47it/s]\n 40%|████      | 12/30 [00:04<00:07,  2.47it/s]\n 43%|████▎     | 13/30 [00:05<00:06,  2.47it/s]\n 47%|████▋     | 14/30 [00:05<00:06,  2.47it/s]\n 50%|█████     | 15/30 [00:06<00:06,  2.47it/s]\n 53%|█████▎    | 16/30 [00:06<00:05,  2.47it/s]\n 57%|█████▋    | 17/30 [00:06<00:05,  2.47it/s]\n 60%|██████    | 18/30 [00:07<00:04,  2.47it/s]\n 63%|██████▎   | 19/30 [00:07<00:04,  2.47it/s]\n 67%|██████▋   | 20/30 [00:08<00:04,  2.47it/s]\n 70%|███████   | 21/30 [00:08<00:03,  2.47it/s]\n 73%|███████▎  | 22/30 [00:09<00:03,  2.47it/s]\n 77%|███████▋  | 23/30 [00:09<00:02,  2.47it/s]\n 80%|████████  | 24/30 [00:09<00:02,  2.47it/s]\n 83%|████████▎ | 25/30 [00:10<00:02,  2.47it/s]\n 87%|████████▋ | 26/30 [00:10<00:01,  2.47it/s]\n 90%|█████████ | 27/30 [00:11<00:01,  2.47it/s]\n 93%|█████████▎| 28/30 [00:11<00:00,  2.46it/s]\n 97%|█████████▋| 29/30 [00:11<00:00,  2.47it/s]\n100%|██████████| 30/30 [00:12<00:00,  2.91it/s]\n100%|██████████| 30/30 [00:12<00:00,  2.49it/s]",
  "output": [
    "https://replicate.delivery/pbxt/C3LYYa30997dKRdeNDSXNjIK01CH5q8CSto12eWundnPPtWSA/out-0.png"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-02-14T20:24:47.803025Z",
  "started_at": "2024-02-14T20:25:37.73127Z",
  "completed_at": "2024-02-14T20:25:53.26729Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/pwcksmtb6g6un4xjjn6repaxt4/cancel",
    "get": "https://api.replicate.com/v1/predictions/pwcksmtb6g6un4xjjn6repaxt4"
  },
  "metrics": {
    "predict_time": 15.53602,
    "total_time": 65.464265
  }
}

Generated in

15.5 seconds

Tweak it Report

Using seed: 1185096284 Prompt: Anime mugshot of a tough woman. She is holding a prison sign that reads "Proteus". Her face is censored. Anime key visual (best quality, HD, ~+~aesthetic~+~:1.2) txt2img mode 0%| | 0/30 [00:00<?, ?it/s] 3%|▎ | 1/30 [00:00<00:15, 1.82it/s] 7%|▋ | 2/30 [00:00<00:12, 2.16it/s] 10%|█ | 3/30 [00:01<00:11, 2.30it/s] 13%|█▎ | 4/30 [00:01<00:10, 2.38it/s] 17%|█▋ | 5/30 [00:02<00:10, 2.41it/s] 20%|██ | 6/30 [00:02<00:09, 2.44it/s] 23%|██▎ | 7/30 [00:02<00:09, 2.45it/s] 27%|██▋ | 8/30 [00:03<00:08, 2.46it/s] 30%|███ | 9/30 [00:03<00:08, 2.47it/s] 33%|███▎ | 10/30 [00:04<00:08, 2.47it/s] 37%|███▋ | 11/30 [00:04<00:07, 2.47it/s] 40%|████ | 12/30 [00:04<00:07, 2.47it/s] 43%|████▎ | 13/30 [00:05<00:06, 2.47it/s] 47%|████▋ | 14/30 [00:05<00:06, 2.47it/s] 50%|█████ | 15/30 [00:06<00:06, 2.47it/s] 53%|█████▎ | 16/30 [00:06<00:05, 2.47it/s] 57%|█████▋ | 17/30 [00:06<00:05, 2.47it/s] 60%|██████ | 18/30 [00:07<00:04, 2.47it/s] 63%|██████▎ | 19/30 [00:07<00:04, 2.47it/s] 67%|██████▋ | 20/30 [00:08<00:04, 2.47it/s] 70%|███████ | 21/30 [00:08<00:03, 2.47it/s] 73%|███████▎ | 22/30 [00:09<00:03, 2.47it/s] 77%|███████▋ | 23/30 [00:09<00:02, 2.47it/s] 80%|████████ | 24/30 [00:09<00:02, 2.47it/s] 83%|████████▎ | 25/30 [00:10<00:02, 2.47it/s] 87%|████████▋ | 26/30 [00:10<00:01, 2.47it/s] 90%|█████████ | 27/30 [00:11<00:01, 2.47it/s] 93%|█████████▎| 28/30 [00:11<00:00, 2.46it/s] 97%|█████████▋| 29/30 [00:11<00:00, 2.47it/s] 100%|██████████| 30/30 [00:12<00:00, 2.91it/s] 100%|██████████| 30/30 [00:12<00:00, 2.49it/s]