jyoung105 / stable-diffusion-3.5-medium

Cold

Public
11 runs
A100 (80GB)

Iterate in playground

Run with an API

Playground API Examples README Versions

Prediction

jyoung105/stable-diffusion-3.5-medium:eada3dc37bc57e8639b638eab179b7ed20537a65708123c2f59b58ef621b5ff0

Model

jyoung105/stable-diffusion-3.5-medium:eada3dc3

tbhnqbxtb1rj40ck25tvw9fx48

Status

Succeeded

Source

Web

Hardware

A100 (80GB)

Total duration

3m 14s

Created

8 months ago

Input

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

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

Install Replicate’s Node.js client library:

npm install replicate

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-medium 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-medium:eada3dc37bc57e8639b638eab179b7ed20537a65708123c2f59b58ef621b5ff0",
  {
    input: {
      steps: 28,
      width: 1024,
      height: 1024,
      prompt: "A man with hoodie on, illustration",
      num_images: 1,
      guidance_scale: 4.5
    }
  }
);

// 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

Import the client:

import replicate

Run jyoung105/stable-diffusion-3.5-medium 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-medium:eada3dc37bc57e8639b638eab179b7ed20537a65708123c2f59b58ef621b5ff0",
    input={
        "steps": 28,
        "width": 1024,
        "height": 1024,
        "prompt": "A man with hoodie on, illustration",
        "num_images": 1,
        "guidance_scale": 4.5
    }
)
print(output)

To learn more, take a look at the guide on getting started with Python.

Run jyoung105/stable-diffusion-3.5-medium 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-medium:eada3dc37bc57e8639b638eab179b7ed20537a65708123c2f59b58ef621b5ff0",
    "input": {
      "steps": 28,
      "width": 1024,
      "height": 1024,
      "prompt": "A man with hoodie on, illustration",
      "num_images": 1,
      "guidance_scale": 4.5
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-11-09T15:09:01.933211Z",
  "created_at": "2024-11-09T15:05:48.376000Z",
  "data_removed": false,
  "error": null,
  "id": "tbhnqbxtb1rj40ck25tvw9fx48",
  "input": {
    "steps": 28,
    "width": 1024,
    "height": 1024,
    "prompt": "A man with hoodie on, illustration",
    "num_images": 1,
    "guidance_scale": 4.5
  },
  "logs": "DEVICE: cuda\nDTYPE: torch.bfloat16\nUsing seed: 18899\nFinish setup in 0.000133514404296875 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 [00:05<02:30,  5.59s/it]\n  7%|▋         | 2/28 [00:05<01:02,  2.39s/it]\n 11%|█         | 3/28 [00:05<00:35,  1.40s/it]\n 14%|█▍        | 4/28 [00:06<00:22,  1.07it/s]\n 18%|█▊        | 5/28 [00:06<00:15,  1.47it/s]\n 21%|██▏       | 6/28 [00:06<00:11,  1.91it/s]\n 25%|██▌       | 7/28 [00:06<00:08,  2.35it/s]\n 29%|██▊       | 8/28 [00:07<00:07,  2.78it/s]\n 32%|███▏      | 9/28 [00:07<00:06,  3.16it/s]\n 36%|███▌      | 10/28 [00:07<00:05,  3.48it/s]\n 39%|███▉      | 11/28 [00:07<00:04,  3.74it/s]\n 43%|████▎     | 12/28 [00:07<00:04,  3.95it/s]\n 46%|████▋     | 13/28 [00:08<00:03,  4.11it/s]\n 50%|█████     | 14/28 [00:08<00:03,  4.22it/s]\n 54%|█████▎    | 15/28 [00:08<00:03,  4.31it/s]\n 57%|█████▋    | 16/28 [00:08<00:02,  4.36it/s]\n 61%|██████    | 17/28 [00:09<00:02,  4.42it/s]\n 64%|██████▍   | 18/28 [00:09<00:02,  4.45it/s]\n 68%|██████▊   | 19/28 [00:09<00:02,  4.46it/s]\n 71%|███████▏  | 20/28 [00:09<00:01,  4.48it/s]\n 75%|███████▌  | 21/28 [00:09<00:01,  4.50it/s]\n 79%|███████▊  | 22/28 [00:10<00:01,  4.49it/s]\n 82%|████████▏ | 23/28 [00:10<00:01,  4.50it/s]\n 86%|████████▌ | 24/28 [00:10<00:00,  4.51it/s]\n 89%|████████▉ | 25/28 [00:10<00:00,  4.50it/s]\n 93%|█████████▎| 26/28 [00:11<00:00,  4.51it/s]\n 96%|█████████▋| 27/28 [00:11<00:00,  4.51it/s]\n100%|██████████| 28/28 [00:11<00:00,  4.51it/s]\n100%|██████████| 28/28 [00:11<00:00,  2.43it/s]\nFinish generation in 16.3258216381073 secs.",
  "metrics": {
    "predict_time": 16.69461729,
    "total_time": 193.557211
  },
  "output": [
    "https://replicate.delivery/yhqm/eHPkAk7cCFUFVSmEAFqj8mfev2uCs0eZQDIDwNriwQ53QL9OB/out_0.png"
  ],
  "started_at": "2024-11-09T15:08:45.238593Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/qoxq-52rb2ywa3zvmmchbzrhmckdnqr75xnqdhwfjwrcwgyfowjdclcdq",
    "get": "https://api.replicate.com/v1/predictions/tbhnqbxtb1rj40ck25tvw9fx48",
    "cancel": "https://api.replicate.com/v1/predictions/tbhnqbxtb1rj40ck25tvw9fx48/cancel"
  },
  "version": "eada3dc37bc57e8639b638eab179b7ed20537a65708123c2f59b58ef621b5ff0"
}

Generated in

16.7 seconds

Tweak it ShareReport

DEVICE: cuda
DTYPE: torch.bfloat16
Using seed: 18899
Finish setup in 0.000133514404296875 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 [00:05<02:30,  5.59s/it]
  7%|▋         | 2/28 [00:05<01:02,  2.39s/it]
 11%|█         | 3/28 [00:05<00:35,  1.40s/it]
 14%|█▍        | 4/28 [00:06<00:22,  1.07it/s]
 18%|█▊        | 5/28 [00:06<00:15,  1.47it/s]
 21%|██▏       | 6/28 [00:06<00:11,  1.91it/s]
 25%|██▌       | 7/28 [00:06<00:08,  2.35it/s]
 29%|██▊       | 8/28 [00:07<00:07,  2.78it/s]
 32%|███▏      | 9/28 [00:07<00:06,  3.16it/s]
 36%|███▌      | 10/28 [00:07<00:05,  3.48it/s]
 39%|███▉      | 11/28 [00:07<00:04,  3.74it/s]
 43%|████▎     | 12/28 [00:07<00:04,  3.95it/s]
 46%|████▋     | 13/28 [00:08<00:03,  4.11it/s]
 50%|█████     | 14/28 [00:08<00:03,  4.22it/s]
 54%|█████▎    | 15/28 [00:08<00:03,  4.31it/s]
 57%|█████▋    | 16/28 [00:08<00:02,  4.36it/s]
 61%|██████    | 17/28 [00:09<00:02,  4.42it/s]
 64%|██████▍   | 18/28 [00:09<00:02,  4.45it/s]
 68%|██████▊   | 19/28 [00:09<00:02,  4.46it/s]
 71%|███████▏  | 20/28 [00:09<00:01,  4.48it/s]
 75%|███████▌  | 21/28 [00:09<00:01,  4.50it/s]
 79%|███████▊  | 22/28 [00:10<00:01,  4.49it/s]
 82%|████████▏ | 23/28 [00:10<00:01,  4.50it/s]
 86%|████████▌ | 24/28 [00:10<00:00,  4.51it/s]
 89%|████████▉ | 25/28 [00:10<00:00,  4.50it/s]
 93%|█████████▎| 26/28 [00:11<00:00,  4.51it/s]
 96%|█████████▋| 27/28 [00:11<00:00,  4.51it/s]
100%|██████████| 28/28 [00:11<00:00,  4.51it/s]
100%|██████████| 28/28 [00:11<00:00,  2.43it/s]
Finish generation in 16.3258216381073 secs.

Want to make some of these yourself?

Run this model