model: dev
prompt: Create a headshot of @brock for use in YouTube thumbnails. The person is seated indoors in a modern, well-lit environment with soft, colorful lighting in the background (gradients of blue and pink). The subject wears a casual hoodie and looks directly at the camera with a confident and calm expression, featuring a slight closed-lip smile. The subject has a curious look on his face as if he is very curious about something. He is grabbing his chin as if he is thinking about something. The overall mood is professional, approachable, and composed. The framing focuses on the face, upper body, and gesture, ensuring the lighting and composition are visually appealing for thumbnails. Make sure the skin on the face does not look too shiny
go_fast
lora_scale: 1
megapixels: 1
num_outputs: 4
aspect_ratio: 16:9
output_format: png
guidance_scale: 3
output_quality: 100
prompt_strength: 0.8
extra_lora_scale: 1
num_inference_steps: 28

{
  "model": "dev",
  "prompt": "Create a headshot of @brock for use in YouTube thumbnails. The person is seated indoors in a modern, well-lit environment with soft, colorful lighting in the background (gradients of blue and pink). The subject wears a casual hoodie and looks directly at the camera with a confident and calm expression, featuring a slight closed-lip smile. The subject has a curious look on his face as if he is very curious about something. He is grabbing his chin as if he is thinking about something. The overall mood is professional, approachable, and composed. The framing focuses on the face, upper body, and gesture, ensuring the lighting and composition are visually appealing for thumbnails. \n\nMake sure the skin on the face does not look too shiny",
  "go_fast": false,
  "lora_scale": 1,
  "megapixels": "1",
  "num_outputs": 4,
  "aspect_ratio": "16:9",
  "output_format": "png",
  "guidance_scale": 3,
  "output_quality": 100,
  "prompt_strength": 0.8,
  "extra_lora_scale": 1,
  "num_inference_steps": 28
}

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 brockmesarich/thumbnailfinal using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "brockmesarich/thumbnailfinal:5c553857be3a87f07df5825bc8eba031187166bb1e3d8841f5d5db3749d7223a",
  {
    input: {
      model: "dev",
      prompt: "Create a headshot of @brock for use in YouTube thumbnails. The person is seated indoors in a modern, well-lit environment with soft, colorful lighting in the background (gradients of blue and pink). The subject wears a casual hoodie and looks directly at the camera with a confident and calm expression, featuring a slight closed-lip smile. The subject has a curious look on his face as if he is very curious about something. He is grabbing his chin as if he is thinking about something. The overall mood is professional, approachable, and composed. The framing focuses on the face, upper body, and gesture, ensuring the lighting and composition are visually appealing for thumbnails. \n\nMake sure the skin on the face does not look too shiny",
      go_fast: false,
      lora_scale: 1,
      megapixels: "1",
      num_outputs: 4,
      aspect_ratio: "16:9",
      output_format: "png",
      guidance_scale: 3,
      output_quality: 100,
      prompt_strength: 0.8,
      extra_lora_scale: 1,
      num_inference_steps: 28
    }
  }
);

// 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 brockmesarich/thumbnailfinal using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "brockmesarich/thumbnailfinal:5c553857be3a87f07df5825bc8eba031187166bb1e3d8841f5d5db3749d7223a",
    input={
        "model": "dev",
        "prompt": "Create a headshot of @brock for use in YouTube thumbnails. The person is seated indoors in a modern, well-lit environment with soft, colorful lighting in the background (gradients of blue and pink). The subject wears a casual hoodie and looks directly at the camera with a confident and calm expression, featuring a slight closed-lip smile. The subject has a curious look on his face as if he is very curious about something. He is grabbing his chin as if he is thinking about something. The overall mood is professional, approachable, and composed. The framing focuses on the face, upper body, and gesture, ensuring the lighting and composition are visually appealing for thumbnails. \n\nMake sure the skin on the face does not look too shiny",
        "go_fast": False,
        "lora_scale": 1,
        "megapixels": "1",
        "num_outputs": 4,
        "aspect_ratio": "16:9",
        "output_format": "png",
        "guidance_scale": 3,
        "output_quality": 100,
        "prompt_strength": 0.8,
        "extra_lora_scale": 1,
        "num_inference_steps": 28
    }
)

# 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.

Run brockmesarich/thumbnailfinal 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": "brockmesarich/thumbnailfinal:5c553857be3a87f07df5825bc8eba031187166bb1e3d8841f5d5db3749d7223a",
    "input": {
      "model": "dev",
      "prompt": "Create a headshot of @brock for use in YouTube thumbnails. The person is seated indoors in a modern, well-lit environment with soft, colorful lighting in the background (gradients of blue and pink). The subject wears a casual hoodie and looks directly at the camera with a confident and calm expression, featuring a slight closed-lip smile. The subject has a curious look on his face as if he is very curious about something. He is grabbing his chin as if he is thinking about something. The overall mood is professional, approachable, and composed. The framing focuses on the face, upper body, and gesture, ensuring the lighting and composition are visually appealing for thumbnails. \\n\\nMake sure the skin on the face does not look too shiny",
      "go_fast": false,
      "lora_scale": 1,
      "megapixels": "1",
      "num_outputs": 4,
      "aspect_ratio": "16:9",
      "output_format": "png",
      "guidance_scale": 3,
      "output_quality": 100,
      "prompt_strength": 0.8,
      "extra_lora_scale": 1,
      "num_inference_steps": 28
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2025-04-19T15:55:46.090030Z",
  "created_at": "2025-04-19T15:55:14.336000Z",
  "data_removed": false,
  "error": null,
  "id": "wvbda3er41rmc0cp9v1bjjhepr",
  "input": {
    "model": "dev",
    "prompt": "Create a headshot of @brock for use in YouTube thumbnails. The person is seated indoors in a modern, well-lit environment with soft, colorful lighting in the background (gradients of blue and pink). The subject wears a casual hoodie and looks directly at the camera with a confident and calm expression, featuring a slight closed-lip smile. The subject has a curious look on his face as if he is very curious about something. He is grabbing his chin as if he is thinking about something. The overall mood is professional, approachable, and composed. The framing focuses on the face, upper body, and gesture, ensuring the lighting and composition are visually appealing for thumbnails. \n\nMake sure the skin on the face does not look too shiny",
    "go_fast": false,
    "lora_scale": 1,
    "megapixels": "1",
    "num_outputs": 4,
    "aspect_ratio": "16:9",
    "output_format": "png",
    "guidance_scale": 3,
    "output_quality": 100,
    "prompt_strength": 0.8,
    "extra_lora_scale": 1,
    "num_inference_steps": 28
  },
  "logs": "free=26195492270080\nDownloading weights\n2025-04-19T15:55:14Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpygn7lpik/weights url=https://replicate.delivery/xezq/c9hVAILYekQoVyFsVBfLGja1BfelELSypyAViyz0Bc47PscQB/trained_model.tar\n2025-04-19T15:55:14Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local\n2025-04-19T15:55:16Z | INFO  | [ Complete ] dest=/tmp/tmpygn7lpik/weights size=\"172 MB\" total_elapsed=2.316s url=https://replicate.delivery/xezq/c9hVAILYekQoVyFsVBfLGja1BfelELSypyAViyz0Bc47PscQB/trained_model.tar\nDownloaded weights in 2.34s\nLoaded LoRAs in 2.94s\nUsing seed: 4967\nPrompt: Create a headshot of @brock for use in YouTube thumbnails. The person is seated indoors in a modern, well-lit environment with soft, colorful lighting in the background (gradients of blue and pink). The subject wears a casual hoodie and looks directly at the camera with a confident and calm expression, featuring a slight closed-lip smile. The subject has a curious look on his face as if he is very curious about something. He is grabbing his chin as if he is thinking about something. The overall mood is professional, approachable, and composed. The framing focuses on the face, upper body, and gesture, ensuring the lighting and composition are visually appealing for thumbnails.\nMake sure the skin on the face does not look too shiny\n[!] txt2img mode\n  0%|          | 0/28 [00:00<?, ?it/s]\n  4%|▎         | 1/28 [00:00<00:26,  1.04it/s]\n  7%|▋         | 2/28 [00:01<00:22,  1.18it/s]\n 11%|█         | 3/28 [00:02<00:22,  1.11it/s]\n 14%|█▍        | 4/28 [00:03<00:22,  1.08it/s]\n 18%|█▊        | 5/28 [00:04<00:21,  1.06it/s]\n 21%|██▏       | 6/28 [00:05<00:20,  1.05it/s]\n 25%|██▌       | 7/28 [00:06<00:20,  1.05it/s]\n 29%|██▊       | 8/28 [00:07<00:19,  1.04it/s]\n 32%|███▏      | 9/28 [00:08<00:18,  1.04it/s]\n 36%|███▌      | 10/28 [00:09<00:17,  1.04it/s]\n 39%|███▉      | 11/28 [00:10<00:16,  1.04it/s]\n 43%|████▎     | 12/28 [00:11<00:15,  1.04it/s]\n 46%|████▋     | 13/28 [00:12<00:14,  1.04it/s]\n 50%|█████     | 14/28 [00:13<00:13,  1.04it/s]\n 54%|█████▎    | 15/28 [00:14<00:12,  1.04it/s]\n 57%|█████▋    | 16/28 [00:15<00:11,  1.04it/s]\n 61%|██████    | 17/28 [00:16<00:10,  1.04it/s]\n 64%|██████▍   | 18/28 [00:17<00:09,  1.04it/s]\n 68%|██████▊   | 19/28 [00:18<00:08,  1.04it/s]\n 71%|███████▏  | 20/28 [00:19<00:07,  1.04it/s]\n 75%|███████▌  | 21/28 [00:20<00:06,  1.04it/s]\n 79%|███████▊  | 22/28 [00:21<00:05,  1.04it/s]\n 82%|████████▏ | 23/28 [00:22<00:04,  1.04it/s]\n 86%|████████▌ | 24/28 [00:22<00:03,  1.04it/s]\n 89%|████████▉ | 25/28 [00:23<00:02,  1.04it/s]\n 93%|█████████▎| 26/28 [00:24<00:01,  1.04it/s]\n 96%|█████████▋| 27/28 [00:25<00:00,  1.04it/s]\n100%|██████████| 28/28 [00:26<00:00,  1.04it/s]\n100%|██████████| 28/28 [00:26<00:00,  1.04it/s]\nTotal safe images: 4 out of 4",
  "metrics": {
    "predict_time": 31.746896509,
    "total_time": 31.75403
  },
  "output": [
    "https://replicate.delivery/xezq/Fmszf0GlRMyUBC00z1Knohaf6tsVH42OA1rmxNSkSiXCmXkUA/out-0.png",
    "https://replicate.delivery/xezq/ENteVLqk6RxDOaIRIPbzzMjoEQuKj0xbDEsqoZ6ycexCmXkUA/out-1.png",
    "https://replicate.delivery/xezq/xPQpOmS42G7TOdV0RbZyujuOBdvAFOHyECllEn7Ddnhg5FJF/out-2.png",
    "https://replicate.delivery/xezq/4fT6YrFnlK2TXauQAVqA2d2bni0eX4VromjeiIhFMd0FMvIpA/out-3.png"
  ],
  "started_at": "2025-04-19T15:55:14.343134Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://stream.replicate.com/v1/files/bcwr-og22uyqfqtmyhrfzc2vqckvru23f5pqpv4lndyob5ppbxlwbqnla",
    "get": "https://api.replicate.com/v1/predictions/wvbda3er41rmc0cp9v1bjjhepr",
    "cancel": "https://api.replicate.com/v1/predictions/wvbda3er41rmc0cp9v1bjjhepr/cancel"
  },
  "version": "5c553857be3a87f07df5825bc8eba031187166bb1e3d8841f5d5db3749d7223a"
}

Generated in

31.8 seconds

Tweak it Iterate in playground ShareReport

free=26195492270080
Downloading weights
2025-04-19T15:55:14Z | INFO  | [ Initiating ] chunk_size=150M dest=/tmp/tmpygn7lpik/weights url=https://replicate.delivery/xezq/c9hVAILYekQoVyFsVBfLGja1BfelELSypyAViyz0Bc47PscQB/trained_model.tar
2025-04-19T15:55:14Z | INFO  | [ Cache Service ] enabled=true scheme=http target=hermes.services.svc.cluster.local
2025-04-19T15:55:16Z | INFO  | [ Complete ] dest=/tmp/tmpygn7lpik/weights size="172 MB" total_elapsed=2.316s url=https://replicate.delivery/xezq/c9hVAILYekQoVyFsVBfLGja1BfelELSypyAViyz0Bc47PscQB/trained_model.tar
Downloaded weights in 2.34s
Loaded LoRAs in 2.94s
Using seed: 4967
Prompt: Create a headshot of @brock for use in YouTube thumbnails. The person is seated indoors in a modern, well-lit environment with soft, colorful lighting in the background (gradients of blue and pink). The subject wears a casual hoodie and looks directly at the camera with a confident and calm expression, featuring a slight closed-lip smile. The subject has a curious look on his face as if he is very curious about something. He is grabbing his chin as if he is thinking about something. The overall mood is professional, approachable, and composed. The framing focuses on the face, upper body, and gesture, ensuring the lighting and composition are visually appealing for thumbnails.
Make sure the skin on the face does not look too shiny
[!] txt2img mode
  0%|          | 0/28 [00:00<?, ?it/s]
  4%|▎         | 1/28 [00:00<00:26,  1.04it/s]
  7%|▋         | 2/28 [00:01<00:22,  1.18it/s]
 11%|█         | 3/28 [00:02<00:22,  1.11it/s]
 14%|█▍        | 4/28 [00:03<00:22,  1.08it/s]
 18%|█▊        | 5/28 [00:04<00:21,  1.06it/s]
 21%|██▏       | 6/28 [00:05<00:20,  1.05it/s]
 25%|██▌       | 7/28 [00:06<00:20,  1.05it/s]
 29%|██▊       | 8/28 [00:07<00:19,  1.04it/s]
 32%|███▏      | 9/28 [00:08<00:18,  1.04it/s]
 36%|███▌      | 10/28 [00:09<00:17,  1.04it/s]
 39%|███▉      | 11/28 [00:10<00:16,  1.04it/s]
 43%|████▎     | 12/28 [00:11<00:15,  1.04it/s]
 46%|████▋     | 13/28 [00:12<00:14,  1.04it/s]
 50%|█████     | 14/28 [00:13<00:13,  1.04it/s]
 54%|█████▎    | 15/28 [00:14<00:12,  1.04it/s]
 57%|█████▋    | 16/28 [00:15<00:11,  1.04it/s]
 61%|██████    | 17/28 [00:16<00:10,  1.04it/s]
 64%|██████▍   | 18/28 [00:17<00:09,  1.04it/s]
 68%|██████▊   | 19/28 [00:18<00:08,  1.04it/s]
 71%|███████▏  | 20/28 [00:19<00:07,  1.04it/s]
 75%|███████▌  | 21/28 [00:20<00:06,  1.04it/s]
 79%|███████▊  | 22/28 [00:21<00:05,  1.04it/s]
 82%|████████▏ | 23/28 [00:22<00:04,  1.04it/s]
 86%|████████▌ | 24/28 [00:22<00:03,  1.04it/s]
 89%|████████▉ | 25/28 [00:23<00:02,  1.04it/s]
 93%|█████████▎| 26/28 [00:24<00:01,  1.04it/s]
 96%|█████████▋| 27/28 [00:25<00:00,  1.04it/s]
100%|██████████| 28/28 [00:26<00:00,  1.04it/s]
100%|██████████| 28/28 [00:26<00:00,  1.04it/s]
Total safe images: 4 out of 4

Want to make some of these yourself?

Run this model