mcgregory99/goyofacebooth – Run with an API on Replicate

mcgregory99 / goyofacebooth

Cold

Public
74 runs
T4

Iterate in playground

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

Capture the essence of professionalism with an 8k, meticulously detailed corporate portrait headshot photograph. This stunning image features a distinguished gycn person in a suit, radiating confidence and elegance. This hyperrealistic masterpiece is hailed as the best corporate photo winner, showcasing an unrivaled level of perfection.Capture the essence of professionalism with an 8k, meticulously detailed corporate portrait headshot photograph. This stunning image features a distinguished gycn person in a suit, radiating confidence and elegance. This hyperrealistic masterpiece is hailed as the best corporate photo winner, showcasing an unrivaled level of perfection.

Input prompt

Default: "a photo of cjw"

negative_prompt

string

Shift + Return to add a new line

Specify things to not see in the output

image

file

A starting image from which to generate variations (aka 'img2img'). If this input is set, the `width` and `height` inputs are ignored and the output will have the same dimensions as the input image.

width

integer

Width of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

height

integer

Height of output image. Maximum size is 1024x768 or 768x1024 because of memory limits

Default: 512

prompt_strength

number

Prompt strength when using init image. 1.0 corresponds to full destruction of information in init image

Default: 0.8

num_outputs

integer

(minimum: 1, maximum: 4)

Number of images to output.

Default: 1

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 50

guidance_scale

number

(minimum: 1, maximum: 20)

Scale for classifier-free guidance

Default: 7.5

scheduler

string

Choose a scheduler

Default: "DDIM"

seed

integer

Random seed. Leave blank to randomize the seed

disable_safety_check

boolean

Disable safety check. Use at your own risk!

Default: false

Run this model in Node.js with one line of code:

npx create-replicate --model=mcgregory99/goyofacebooth

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run mcgregory99/goyofacebooth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "mcgregory99/goyofacebooth:6e688d1ea46cb252b0334b3842ccad3ead53ecd2d0ffac2e21ffd2800bb30963",
  {
    input: {
      seed: 1312,
      width: 512,
      height: 512,
      prompt: "Capture the essence of professionalism with an 8k, meticulously detailed corporate portrait headshot photograph. This stunning image features a distinguished gycn person in a suit, radiating confidence and elegance. This hyperrealistic masterpiece is hailed as the best corporate photo winner, showcasing an unrivaled level of perfection.",
      scheduler: "KLMS",
      num_outputs: 3,
      guidance_scale: 7.5,
      prompt_strength: 0.7,
      num_inference_steps: 80,
      disable_safety_check: false
    }
  }
);

// 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=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run mcgregory99/goyofacebooth using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "mcgregory99/goyofacebooth:6e688d1ea46cb252b0334b3842ccad3ead53ecd2d0ffac2e21ffd2800bb30963",
    input={
        "seed": 1312,
        "width": 512,
        "height": 512,
        "prompt": "Capture the essence of professionalism with an 8k, meticulously detailed corporate portrait headshot photograph. This stunning image features a distinguished gycn person in a suit, radiating confidence and elegance. This hyperrealistic masterpiece is hailed as the best corporate photo winner, showcasing an unrivaled level of perfection.",
        "scheduler": "KLMS",
        "num_outputs": 3,
        "guidance_scale": 7.5,
        "prompt_strength": 0.7,
        "num_inference_steps": 80,
        "disable_safety_check": False
    }
)
print(output)

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=<paste-your-token-here>

Find your API token in your account settings.

Run mcgregory99/goyofacebooth 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": "mcgregory99/goyofacebooth:6e688d1ea46cb252b0334b3842ccad3ead53ecd2d0ffac2e21ffd2800bb30963",
    "input": {
      "seed": 1312,
      "width": 512,
      "height": 512,
      "prompt": "Capture the essence of professionalism with an 8k, meticulously detailed corporate portrait headshot photograph. This stunning image features a distinguished gycn person in a suit, radiating confidence and elegance. This hyperrealistic masterpiece is hailed as the best corporate photo winner, showcasing an unrivaled level of perfection.",
      "scheduler": "KLMS",
      "num_outputs": 3,
      "guidance_scale": 7.5,
      "prompt_strength": 0.7,
      "num_inference_steps": 80,
      "disable_safety_check": false
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2024-02-20T08:43:25.614884Z",
  "created_at": "2024-02-20T08:42:33.326915Z",
  "data_removed": false,
  "error": null,
  "id": "tincyhjbwyg7okjhwiefxgr2vi",
  "input": {
    "seed": 1312,
    "width": 512,
    "height": 512,
    "prompt": "Capture the essence of professionalism with an 8k, meticulously detailed corporate portrait headshot photograph. This stunning image features a distinguished gycn person in a suit, radiating confidence and elegance. This hyperrealistic masterpiece is hailed as the best corporate photo winner, showcasing an unrivaled level of perfection.",
    "scheduler": "KLMS",
    "num_outputs": 3,
    "guidance_scale": 7.5,
    "prompt_strength": 0.7,
    "num_inference_steps": 80,
    "disable_safety_check": false
  },
  "logs": "Using seed: 1312\nusing txt2img\n  0%|          | 0/80 [00:00<?, ?it/s]\n  1%|▏         | 1/80 [00:00<00:47,  1.65it/s]\n  2%|▎         | 2/80 [00:01<00:47,  1.66it/s]\n  4%|▍         | 3/80 [00:01<00:45,  1.68it/s]\n  5%|▌         | 4/80 [00:02<00:45,  1.66it/s]\n  6%|▋         | 5/80 [00:02<00:44,  1.67it/s]\n  8%|▊         | 6/80 [00:03<00:44,  1.67it/s]\n  9%|▉         | 7/80 [00:04<00:43,  1.67it/s]\n 10%|█         | 8/80 [00:04<00:43,  1.66it/s]\n 11%|█▏        | 9/80 [00:05<00:42,  1.66it/s]\n 12%|█▎        | 10/80 [00:06<00:42,  1.66it/s]\n 14%|█▍        | 11/80 [00:06<00:41,  1.65it/s]\n 15%|█▌        | 12/80 [00:07<00:41,  1.65it/s]\n 16%|█▋        | 13/80 [00:07<00:40,  1.65it/s]\n 18%|█▊        | 14/80 [00:08<00:40,  1.65it/s]\n 19%|█▉        | 15/80 [00:09<00:39,  1.64it/s]\n 20%|██        | 16/80 [00:09<00:39,  1.63it/s]\n 21%|██▏       | 17/80 [00:10<00:38,  1.63it/s]\n 22%|██▎       | 18/80 [00:10<00:38,  1.63it/s]\n 24%|██▍       | 19/80 [00:11<00:37,  1.62it/s]\n 25%|██▌       | 20/80 [00:12<00:37,  1.62it/s]\n 26%|██▋       | 21/80 [00:12<00:36,  1.62it/s]\n 28%|██▊       | 22/80 [00:13<00:36,  1.60it/s]\n 29%|██▉       | 23/80 [00:14<00:35,  1.60it/s]\n 30%|███       | 24/80 [00:14<00:35,  1.59it/s]\n 31%|███▏      | 25/80 [00:15<00:34,  1.59it/s]\n 32%|███▎      | 26/80 [00:15<00:33,  1.59it/s]\n 34%|███▍      | 27/80 [00:16<00:33,  1.59it/s]\n 35%|███▌      | 28/80 [00:17<00:32,  1.59it/s]\n 36%|███▋      | 29/80 [00:17<00:32,  1.58it/s]\n 38%|███▊      | 30/80 [00:18<00:31,  1.58it/s]\n 39%|███▉      | 31/80 [00:19<00:31,  1.57it/s]\n 40%|████      | 32/80 [00:19<00:30,  1.56it/s]\n 41%|████▏     | 33/80 [00:20<00:30,  1.56it/s]\n 42%|████▎     | 34/80 [00:21<00:29,  1.55it/s]\n 44%|████▍     | 35/80 [00:21<00:28,  1.55it/s]\n 45%|████▌     | 36/80 [00:22<00:28,  1.55it/s]\n 46%|████▋     | 37/80 [00:22<00:27,  1.55it/s]\n 48%|████▊     | 38/80 [00:23<00:27,  1.54it/s]\n 49%|████▉     | 39/80 [00:24<00:26,  1.54it/s]\n 50%|█████     | 40/80 [00:24<00:25,  1.54it/s]\n 51%|█████▏    | 41/80 [00:25<00:25,  1.54it/s]\n 52%|█████▎    | 42/80 [00:26<00:24,  1.54it/s]\n 54%|█████▍    | 43/80 [00:26<00:24,  1.53it/s]\n 55%|█████▌    | 44/80 [00:27<00:23,  1.52it/s]\n 56%|█████▋    | 45/80 [00:28<00:22,  1.52it/s]\n 57%|█████▊    | 46/80 [00:28<00:22,  1.52it/s]\n 59%|█████▉    | 47/80 [00:29<00:21,  1.52it/s]\n 60%|██████    | 48/80 [00:30<00:21,  1.52it/s]\n 61%|██████▏   | 49/80 [00:30<00:20,  1.52it/s]\n 62%|██████▎   | 50/80 [00:31<00:19,  1.53it/s]\n 64%|██████▍   | 51/80 [00:32<00:18,  1.53it/s]\n 65%|██████▌   | 52/80 [00:32<00:18,  1.53it/s]\n 66%|██████▋   | 53/80 [00:33<00:17,  1.53it/s]\n 68%|██████▊   | 54/80 [00:34<00:16,  1.54it/s]\n 69%|██████▉   | 55/80 [00:34<00:16,  1.54it/s]\n 70%|███████   | 56/80 [00:35<00:15,  1.54it/s]\n 71%|███████▏  | 57/80 [00:36<00:14,  1.55it/s]\n 72%|███████▎  | 58/80 [00:36<00:14,  1.55it/s]\n 74%|███████▍  | 59/80 [00:37<00:13,  1.56it/s]\n 75%|███████▌  | 60/80 [00:37<00:12,  1.56it/s]\n 76%|███████▋  | 61/80 [00:38<00:12,  1.56it/s]\n 78%|███████▊  | 62/80 [00:39<00:11,  1.57it/s]\n 79%|███████▉  | 63/80 [00:39<00:10,  1.57it/s]\n 80%|████████  | 64/80 [00:40<00:10,  1.58it/s]\n 81%|████████▏ | 65/80 [00:41<00:09,  1.59it/s]\n 82%|████████▎ | 66/80 [00:41<00:08,  1.58it/s]\n 84%|████████▍ | 67/80 [00:42<00:08,  1.59it/s]\n 85%|████████▌ | 68/80 [00:42<00:07,  1.59it/s]\n 86%|████████▋ | 69/80 [00:43<00:06,  1.60it/s]\n 88%|████████▊ | 70/80 [00:44<00:06,  1.60it/s]\n 89%|████████▉ | 71/80 [00:44<00:05,  1.60it/s]\n 90%|█████████ | 72/80 [00:45<00:04,  1.61it/s]\n 91%|█████████▏| 73/80 [00:46<00:04,  1.61it/s]\n 92%|█████████▎| 74/80 [00:46<00:03,  1.62it/s]\n 94%|█████████▍| 75/80 [00:47<00:03,  1.62it/s]\n 95%|█████████▌| 76/80 [00:47<00:02,  1.62it/s]\n 96%|█████████▋| 77/80 [00:48<00:01,  1.63it/s]\n 98%|█████████▊| 78/80 [00:49<00:01,  1.61it/s]\n 99%|█████████▉| 79/80 [00:49<00:00,  1.62it/s]\n100%|██████████| 80/80 [00:50<00:00,  1.63it/s]\n100%|██████████| 80/80 [00:50<00:00,  1.59it/s]",
  "metrics": {
    "predict_time": 52.274183,
    "total_time": 52.287969
  },
  "output": [
    "https://replicate.delivery/pbxt/xqrWe2FwskwwHqJxABYuqdthVgyFNF3sg3CF1SYNrR0WwQMJA/out-0.png",
    "https://replicate.delivery/pbxt/pufpuEo8TYSAf0AtlDEN3VOpBJENv3AsidcelLQRicNaBDxkA/out-1.png",
    "https://replicate.delivery/pbxt/GI3dZwB7xWJYIJrLnAXhRdTLqaJ7kT5p84KVjqRQN4TLYImE/out-2.png"
  ],
  "started_at": "2024-02-20T08:42:33.340701Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/tincyhjbwyg7okjhwiefxgr2vi",
    "cancel": "https://api.replicate.com/v1/predictions/tincyhjbwyg7okjhwiefxgr2vi/cancel"
  },
  "version": "6e688d1ea46cb252b0334b3842ccad3ead53ecd2d0ffac2e21ffd2800bb30963"
}

Generated in

52.3 seconds

Tweak itReport

Using seed: 1312
using txt2img
  0%|          | 0/80 [00:00<?, ?it/s]
  1%|▏         | 1/80 [00:00<00:47,  1.65it/s]
  2%|▎         | 2/80 [00:01<00:47,  1.66it/s]
  4%|▍         | 3/80 [00:01<00:45,  1.68it/s]
  5%|▌         | 4/80 [00:02<00:45,  1.66it/s]
  6%|▋         | 5/80 [00:02<00:44,  1.67it/s]
  8%|▊         | 6/80 [00:03<00:44,  1.67it/s]
  9%|▉         | 7/80 [00:04<00:43,  1.67it/s]
 10%|█         | 8/80 [00:04<00:43,  1.66it/s]
 11%|█▏        | 9/80 [00:05<00:42,  1.66it/s]
 12%|█▎        | 10/80 [00:06<00:42,  1.66it/s]
 14%|█▍        | 11/80 [00:06<00:41,  1.65it/s]
 15%|█▌        | 12/80 [00:07<00:41,  1.65it/s]
 16%|█▋        | 13/80 [00:07<00:40,  1.65it/s]
 18%|█▊        | 14/80 [00:08<00:40,  1.65it/s]
 19%|█▉        | 15/80 [00:09<00:39,  1.64it/s]
 20%|██        | 16/80 [00:09<00:39,  1.63it/s]
 21%|██▏       | 17/80 [00:10<00:38,  1.63it/s]
 22%|██▎       | 18/80 [00:10<00:38,  1.63it/s]
 24%|██▍       | 19/80 [00:11<00:37,  1.62it/s]
 25%|██▌       | 20/80 [00:12<00:37,  1.62it/s]
 26%|██▋       | 21/80 [00:12<00:36,  1.62it/s]
 28%|██▊       | 22/80 [00:13<00:36,  1.60it/s]
 29%|██▉       | 23/80 [00:14<00:35,  1.60it/s]
 30%|███       | 24/80 [00:14<00:35,  1.59it/s]
 31%|███▏      | 25/80 [00:15<00:34,  1.59it/s]
 32%|███▎      | 26/80 [00:15<00:33,  1.59it/s]
 34%|███▍      | 27/80 [00:16<00:33,  1.59it/s]
 35%|███▌      | 28/80 [00:17<00:32,  1.59it/s]
 36%|███▋      | 29/80 [00:17<00:32,  1.58it/s]
 38%|███▊      | 30/80 [00:18<00:31,  1.58it/s]
 39%|███▉      | 31/80 [00:19<00:31,  1.57it/s]
 40%|████      | 32/80 [00:19<00:30,  1.56it/s]
 41%|████▏     | 33/80 [00:20<00:30,  1.56it/s]
 42%|████▎     | 34/80 [00:21<00:29,  1.55it/s]
 44%|████▍     | 35/80 [00:21<00:28,  1.55it/s]
 45%|████▌     | 36/80 [00:22<00:28,  1.55it/s]
 46%|████▋     | 37/80 [00:22<00:27,  1.55it/s]
 48%|████▊     | 38/80 [00:23<00:27,  1.54it/s]
 49%|████▉     | 39/80 [00:24<00:26,  1.54it/s]
 50%|█████     | 40/80 [00:24<00:25,  1.54it/s]
 51%|█████▏    | 41/80 [00:25<00:25,  1.54it/s]
 52%|█████▎    | 42/80 [00:26<00:24,  1.54it/s]
 54%|█████▍    | 43/80 [00:26<00:24,  1.53it/s]
 55%|█████▌    | 44/80 [00:27<00:23,  1.52it/s]
 56%|█████▋    | 45/80 [00:28<00:22,  1.52it/s]
 57%|█████▊    | 46/80 [00:28<00:22,  1.52it/s]
 59%|█████▉    | 47/80 [00:29<00:21,  1.52it/s]
 60%|██████    | 48/80 [00:30<00:21,  1.52it/s]
 61%|██████▏   | 49/80 [00:30<00:20,  1.52it/s]
 62%|██████▎   | 50/80 [00:31<00:19,  1.53it/s]
 64%|██████▍   | 51/80 [00:32<00:18,  1.53it/s]
 65%|██████▌   | 52/80 [00:32<00:18,  1.53it/s]
 66%|██████▋   | 53/80 [00:33<00:17,  1.53it/s]
 68%|██████▊   | 54/80 [00:34<00:16,  1.54it/s]
 69%|██████▉   | 55/80 [00:34<00:16,  1.54it/s]
 70%|███████   | 56/80 [00:35<00:15,  1.54it/s]
 71%|███████▏  | 57/80 [00:36<00:14,  1.55it/s]
 72%|███████▎  | 58/80 [00:36<00:14,  1.55it/s]
 74%|███████▍  | 59/80 [00:37<00:13,  1.56it/s]
 75%|███████▌  | 60/80 [00:37<00:12,  1.56it/s]
 76%|███████▋  | 61/80 [00:38<00:12,  1.56it/s]
 78%|███████▊  | 62/80 [00:39<00:11,  1.57it/s]
 79%|███████▉  | 63/80 [00:39<00:10,  1.57it/s]
 80%|████████  | 64/80 [00:40<00:10,  1.58it/s]
 81%|████████▏ | 65/80 [00:41<00:09,  1.59it/s]
 82%|████████▎ | 66/80 [00:41<00:08,  1.58it/s]
 84%|████████▍ | 67/80 [00:42<00:08,  1.59it/s]
 85%|████████▌ | 68/80 [00:42<00:07,  1.59it/s]
 86%|████████▋ | 69/80 [00:43<00:06,  1.60it/s]
 88%|████████▊ | 70/80 [00:44<00:06,  1.60it/s]
 89%|████████▉ | 71/80 [00:44<00:05,  1.60it/s]
 90%|█████████ | 72/80 [00:45<00:04,  1.61it/s]
 91%|█████████▏| 73/80 [00:46<00:04,  1.61it/s]
 92%|█████████▎| 74/80 [00:46<00:03,  1.62it/s]
 94%|█████████▍| 75/80 [00:47<00:03,  1.62it/s]
 95%|█████████▌| 76/80 [00:47<00:02,  1.62it/s]
 96%|█████████▋| 77/80 [00:48<00:01,  1.63it/s]
 98%|█████████▊| 78/80 [00:49<00:01,  1.61it/s]
 99%|█████████▉| 79/80 [00:49<00:00,  1.62it/s]
100%|██████████| 80/80 [00:50<00:00,  1.63it/s]
100%|██████████| 80/80 [00:50<00:00,  1.59it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.012 to run on Replicate, or 83 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia T4 GPU hardware. Predictions typically complete within 53 seconds. The predict time for this model varies significantly based on the inputs.

Readme

Keywork: gycn

Look at the prompts in the examples to see how does it work