Prediction

Model

jyoung105/stable-diffusion-3.5-large:69b4e203

er195mehvsrj00ck25tvewnz18

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

6m 22s

Created

about 1 year ago

Webhook

–

Input

prompt: A man with hoodie on, illustration
width: 1024
height: 1024
num_images: 1
steps: 28
guidance_scale: 4.5

{
  "guidance_scale": 4.5,
  "height": 1024,
  "num_images": 1,
  "prompt": "A man with hoodie on, illustration",
  "steps": 28,
  "width": 1024
}

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=r8_7Lr**********************************

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 jyoung105/stable-diffusion-3.5-large using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "jyoung105/stable-diffusion-3.5-large:69b4e203be29bb4642a2f48be466ddfe31a83cf2e806ae15e51e39ac5fb16828",
  {
    input: {
      guidance_scale: 4.5,
      height: 1024,
      num_images: 1,
      prompt: "A man with hoodie on, illustration",
      steps: 28,
      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_7Lr**********************************

This is your API token. Keep it to yourself.

Import the client:

import replicate

Run jyoung105/stable-diffusion-3.5-large using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "jyoung105/stable-diffusion-3.5-large:69b4e203be29bb4642a2f48be466ddfe31a83cf2e806ae15e51e39ac5fb16828",
    input={
        "guidance_scale": 4.5,
        "height": 1024,
        "num_images": 1,
        "prompt": "A man with hoodie on, illustration",
        "steps": 28,
        "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_7Lr**********************************

This is your API token. Keep it to yourself.

Run jyoung105/stable-diffusion-3.5-large 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": "jyoung105/stable-diffusion-3.5-large:69b4e203be29bb4642a2f48be466ddfe31a83cf2e806ae15e51e39ac5fb16828",
    "input": {
      "guidance_scale": 4.5,
      "height": 1024,
      "num_images": 1,
      "prompt": "A man with hoodie on, illustration",
      "steps": 28,
      "width": 1024
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "id": "er195mehvsrj00ck25tvewnz18",
  "model": "jyoung105/stable-diffusion-3.5-large",
  "version": "69b4e203be29bb4642a2f48be466ddfe31a83cf2e806ae15e51e39ac5fb16828",
  "input": {
    "guidance_scale": 4.5,
    "height": 1024,
    "num_images": 1,
    "prompt": "A man with hoodie on, illustration",
    "steps": 28,
    "width": 1024
  },
  "logs": "DEVICE: cuda\nDTYPE: torch.bfloat16\nUsing seed: 34122\nFinish setup in 4.696846008300781e-05 secs.\n[Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:06<02:49,  6.26s/it]\n  7%|▋         | 2/28 [00:06<01:12,  2.80s/it]\n 11%|█         | 3/28 [00:07<00:43,  1.75s/it]\n 14%|█▍        | 4/28 [00:07<00:30,  1.25s/it]\n 18%|█▊        | 5/28 [00:08<00:22,  1.02it/s]\n 21%|██▏       | 6/28 [00:08<00:18,  1.22it/s]\n 25%|██▌       | 7/28 [00:09<00:15,  1.39it/s]\n 29%|██▊       | 8/28 [00:09<00:12,  1.54it/s]\n 32%|███▏      | 9/28 [00:10<00:11,  1.66it/s]\n 36%|███▌      | 10/28 [00:10<00:10,  1.74it/s]\n 39%|███▉      | 11/28 [00:11<00:09,  1.81it/s]\n 43%|████▎     | 12/28 [00:11<00:08,  1.86it/s]\n 46%|████▋     | 13/28 [00:12<00:07,  1.90it/s]\n 50%|█████     | 14/28 [00:12<00:07,  1.92it/s]\n 54%|█████▎    | 15/28 [00:13<00:06,  1.94it/s]\n 57%|█████▋    | 16/28 [00:13<00:06,  1.96it/s]\n 61%|██████    | 17/28 [00:14<00:05,  1.97it/s]\n 64%|██████▍   | 18/28 [00:14<00:05,  1.98it/s]\n 68%|██████▊   | 19/28 [00:15<00:04,  1.96it/s]\n 71%|███████▏  | 20/28 [00:15<00:04,  1.97it/s]\n 75%|███████▌  | 21/28 [00:16<00:03,  1.98it/s]\n 79%|███████▊  | 22/28 [00:16<00:03,  1.98it/s]\n 82%|████████▏ | 23/28 [00:17<00:02,  1.99it/s]\n 86%|████████▌ | 24/28 [00:17<00:02,  1.98it/s]\n 89%|████████▉ | 25/28 [00:18<00:01,  1.98it/s]\n 93%|█████████▎| 26/28 [00:18<00:01,  1.99it/s]\n 96%|█████████▋| 27/28 [00:19<00:00,  1.99it/s]\n100%|██████████| 28/28 [00:19<00:00,  1.99it/s]\n100%|██████████| 28/28 [00:19<00:00,  1.42it/s]\nFinish generation in 25.05196213722229 secs.",
  "output": [
    "https://replicate.delivery/yhqm/tNw7D8OEHr7dJZY6vt7U4J0mkUhLWEycELReb2ukTGwnbp3JA/out_0.png"
  ],
  "data_removed": false,
  "error": null,
  "source": "web",
  "status": "succeeded",
  "created_at": "2024-11-09T15:05:54.398Z",
  "started_at": "2024-11-09T15:11:50.558412Z",
  "completed_at": "2024-11-09T15:12:15.995823Z",
  "urls": {
    "cancel": "https://api.replicate.com/v1/predictions/er195mehvsrj00ck25tvewnz18/cancel",
    "get": "https://api.replicate.com/v1/predictions/er195mehvsrj00ck25tvewnz18",
    "stream": "https://stream.replicate.com/v1/files/qoxq-ytqu5rgbwk2pmwyupeqiu7wcam4cev7szxw5q6ttkvkufdcnkd5a",
    "web": "https://replicate.com/p/er195mehvsrj00ck25tvewnz18"
  },
  "metrics": {
    "predict_time": 25.43741148,
    "total_time": 381.597823
  }
}

Generated in

25.4 seconds

Tweak it Report

DEVICE: cuda DTYPE: torch.bfloat16 Using seed: 34122 Finish setup in 4.696846008300781e-05 secs. [Debug] Prompt: A man with hoodie on, illustration, best quality, high detail, sharp focus 0%| | 0/28 [00:00<?, ?it/s] 4%|▎ | 1/28 [00:06<02:49, 6.26s/it] 7%|▋ | 2/28 [00:06<01:12, 2.80s/it] 11%|█ | 3/28 [00:07<00:43, 1.75s/it] 14%|█▍ | 4/28 [00:07<00:30, 1.25s/it] 18%|█▊ | 5/28 [00:08<00:22, 1.02it/s] 21%|██▏ | 6/28 [00:08<00:18, 1.22it/s] 25%|██▌ | 7/28 [00:09<00:15, 1.39it/s] 29%|██▊ | 8/28 [00:09<00:12, 1.54it/s] 32%|███▏ | 9/28 [00:10<00:11, 1.66it/s] 36%|███▌ | 10/28 [00:10<00:10, 1.74it/s] 39%|███▉ | 11/28 [00:11<00:09, 1.81it/s] 43%|████▎ | 12/28 [00:11<00:08, 1.86it/s] 46%|████▋ | 13/28 [00:12<00:07, 1.90it/s] 50%|█████ | 14/28 [00:12<00:07, 1.92it/s] 54%|█████▎ | 15/28 [00:13<00:06, 1.94it/s] 57%|█████▋ | 16/28 [00:13<00:06, 1.96it/s] 61%|██████ | 17/28 [00:14<00:05, 1.97it/s] 64%|██████▍ | 18/28 [00:14<00:05, 1.98it/s] 68%|██████▊ | 19/28 [00:15<00:04, 1.96it/s] 71%|███████▏ | 20/28 [00:15<00:04, 1.97it/s] 75%|███████▌ | 21/28 [00:16<00:03, 1.98it/s] 79%|███████▊ | 22/28 [00:16<00:03, 1.98it/s] 82%|████████▏ | 23/28 [00:17<00:02, 1.99it/s] 86%|████████▌ | 24/28 [00:17<00:02, 1.98it/s] 89%|████████▉ | 25/28 [00:18<00:01, 1.98it/s] 93%|█████████▎| 26/28 [00:18<00:01, 1.99it/s] 96%|█████████▋| 27/28 [00:19<00:00, 1.99it/s] 100%|██████████| 28/28 [00:19<00:00, 1.99it/s] 100%|██████████| 28/28 [00:19<00:00, 1.42it/s] Finish generation in 25.05196213722229 secs.