workroomprds/bartbooth1 – Run with an API on Replicate

workroomprds / bartbooth1

Exploring the training and use of DreamBooth, with Bart as a subject

Cold

Public
305 runs
T4

Run with an API

Playground API Examples README Versions

Input

prompt

string

Shift + Return to add a new line

a magnificent, detailed and compelling rembrandt HDR portrait of a btknaack person in space wearing a stetsona magnificent, detailed and compelling rembrandt HDR portrait of a btknaack person in space wearing a stetson

Input prompt

Default: "a photo of a btknaack person"

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=workroomprds/bartbooth1

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 workroomprds/bartbooth1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "workroomprds/bartbooth1:128875f4686be631dd87560aad04ede13582db96732753436d2543a5371e1b56",
  {
    input: {
      width: 512,
      height: 512,
      prompt: "a magnificent, detailed and compelling rembrandt HDR portrait of a btknaack person in space wearing a stetson",
      scheduler: "DDIM",
      num_outputs: 4,
      guidance_scale: 7.5,
      prompt_strength: 0.8,
      num_inference_steps: 50,
      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 workroomprds/bartbooth1 using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "workroomprds/bartbooth1:128875f4686be631dd87560aad04ede13582db96732753436d2543a5371e1b56",
    input={
        "width": 512,
        "height": 512,
        "prompt": "a magnificent, detailed and compelling rembrandt HDR portrait of a btknaack person in space wearing a stetson",
        "scheduler": "DDIM",
        "num_outputs": 4,
        "guidance_scale": 7.5,
        "prompt_strength": 0.8,
        "num_inference_steps": 50,
        "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 workroomprds/bartbooth1 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": "128875f4686be631dd87560aad04ede13582db96732753436d2543a5371e1b56",
    "input": {
      "width": 512,
      "height": 512,
      "prompt": "a magnificent, detailed and compelling rembrandt HDR portrait of a btknaack person in space wearing a stetson",
      "scheduler": "DDIM",
      "num_outputs": 4,
      "guidance_scale": 7.5,
      "prompt_strength": 0.8,
      "num_inference_steps": 50,
      "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": "2023-02-22T23:49:57.394258Z",
  "created_at": "2023-02-22T23:43:53.349958Z",
  "data_removed": false,
  "error": null,
  "id": "xhpv7hxqxbfj3gah6warmssdgm",
  "input": {
    "width": 512,
    "height": 512,
    "prompt": "a magnificent, detailed and compelling rembrandt HDR portrait of a btknaack person in space wearing a stetson",
    "scheduler": "DDIM",
    "num_outputs": "4",
    "guidance_scale": 7.5,
    "prompt_strength": 0.8,
    "num_inference_steps": 50
  },
  "logs": "Using seed: 51805\nusing txt2img\n  0%|          | 0/50 [00:00<?, ?it/s]\n  2%|▏         | 1/50 [00:03<03:04,  3.76s/it]\n  4%|▍         | 2/50 [00:04<01:33,  1.96s/it]\n  6%|▌         | 3/50 [00:05<01:04,  1.37s/it]\n  8%|▊         | 4/50 [00:05<00:50,  1.11s/it]\n 10%|█         | 5/50 [00:06<00:43,  1.04it/s]\n 12%|█▏        | 6/50 [00:07<00:38,  1.15it/s]\n 14%|█▍        | 7/50 [00:07<00:35,  1.23it/s]\n 16%|█▌        | 8/50 [00:08<00:32,  1.28it/s]\n 18%|█▊        | 9/50 [00:09<00:30,  1.32it/s]\n 20%|██        | 10/50 [00:10<00:29,  1.35it/s]\n 22%|██▏       | 11/50 [00:10<00:28,  1.37it/s]\n 24%|██▍       | 12/50 [00:11<00:27,  1.38it/s]\n 26%|██▌       | 13/50 [00:12<00:26,  1.39it/s]\n 28%|██▊       | 14/50 [00:12<00:25,  1.40it/s]\n 30%|███       | 15/50 [00:13<00:25,  1.40it/s]\n 32%|███▏      | 16/50 [00:14<00:24,  1.40it/s]\n 34%|███▍      | 17/50 [00:15<00:23,  1.41it/s]\n 36%|███▌      | 18/50 [00:15<00:22,  1.41it/s]\n 38%|███▊      | 19/50 [00:16<00:21,  1.41it/s]\n 40%|████      | 20/50 [00:17<00:21,  1.41it/s]\n 42%|████▏     | 21/50 [00:17<00:20,  1.41it/s]\n 44%|████▍     | 22/50 [00:18<00:19,  1.41it/s]\n 46%|████▌     | 23/50 [00:19<00:19,  1.41it/s]\n 48%|████▊     | 24/50 [00:19<00:18,  1.41it/s]\n 50%|█████     | 25/50 [00:20<00:17,  1.40it/s]\n 52%|█████▏    | 26/50 [00:21<00:17,  1.40it/s]\n 54%|█████▍    | 27/50 [00:22<00:16,  1.40it/s]\n 56%|█████▌    | 28/50 [00:22<00:15,  1.40it/s]\n 58%|█████▊    | 29/50 [00:23<00:15,  1.39it/s]\n 60%|██████    | 30/50 [00:24<00:14,  1.39it/s]\n 62%|██████▏   | 31/50 [00:25<00:13,  1.38it/s]\n 64%|██████▍   | 32/50 [00:25<00:13,  1.38it/s]\n 66%|██████▌   | 33/50 [00:26<00:12,  1.38it/s]\n 68%|██████▊   | 34/50 [00:27<00:11,  1.37it/s]\n 70%|███████   | 35/50 [00:27<00:10,  1.37it/s]\n 72%|███████▏  | 36/50 [00:28<00:10,  1.37it/s]\n 74%|███████▍  | 37/50 [00:29<00:09,  1.36it/s]\n 76%|███████▌  | 38/50 [00:30<00:08,  1.36it/s]\n 78%|███████▊  | 39/50 [00:30<00:08,  1.36it/s]\n 80%|████████  | 40/50 [00:31<00:07,  1.35it/s]\n 82%|████████▏ | 41/50 [00:32<00:06,  1.34it/s]\n 84%|████████▍ | 42/50 [00:33<00:05,  1.34it/s]\n 86%|████████▌ | 43/50 [00:33<00:05,  1.34it/s]\n 88%|████████▊ | 44/50 [00:34<00:04,  1.34it/s]\n 90%|█████████ | 45/50 [00:35<00:03,  1.34it/s]\n 92%|█████████▏| 46/50 [00:36<00:02,  1.34it/s]\n 94%|█████████▍| 47/50 [00:36<00:02,  1.33it/s]\n 96%|█████████▌| 48/50 [00:37<00:01,  1.33it/s]\n 98%|█████████▊| 49/50 [00:38<00:00,  1.32it/s]\n100%|██████████| 50/50 [00:39<00:00,  1.32it/s]\n100%|██████████| 50/50 [00:39<00:00,  1.28it/s]",
  "metrics": {
    "predict_time": 46.418056,
    "total_time": 364.0443
  },
  "output": [
    "https://replicate.delivery/pbxt/JNsLIXNWfVTEO6w6ztScvYjnqeIcWHvSdWFG4sUmWS6iwFhQA/out-0.png",
    "https://replicate.delivery/pbxt/PEN585QbKUJHBFBkZ04JtYXYzhvesOU4MZzNSLXBtAuR4iQIA/out-1.png",
    "https://replicate.delivery/pbxt/zTTD2eSfRDsHyEe2HDYEwzvvstmmsjogPP3Em7gWe0FQCXECB/out-2.png",
    "https://replicate.delivery/pbxt/qxdcCSxSANpFEBy8HEgNzBGfrKsfxcf678H9Txtu0x5JhLChA/out-3.png"
  ],
  "started_at": "2023-02-22T23:49:10.976202Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/xhpv7hxqxbfj3gah6warmssdgm",
    "cancel": "https://api.replicate.com/v1/predictions/xhpv7hxqxbfj3gah6warmssdgm/cancel"
  },
  "version": "128875f4686be631dd87560aad04ede13582db96732753436d2543a5371e1b56"
}

Generated in

46.4 seconds

Tweak itReport

Using seed: 51805
using txt2img
  0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:03<03:04,  3.76s/it]
  4%|▍         | 2/50 [00:04<01:33,  1.96s/it]
  6%|▌         | 3/50 [00:05<01:04,  1.37s/it]
  8%|▊         | 4/50 [00:05<00:50,  1.11s/it]
 10%|█         | 5/50 [00:06<00:43,  1.04it/s]
 12%|█▏        | 6/50 [00:07<00:38,  1.15it/s]
 14%|█▍        | 7/50 [00:07<00:35,  1.23it/s]
 16%|█▌        | 8/50 [00:08<00:32,  1.28it/s]
 18%|█▊        | 9/50 [00:09<00:30,  1.32it/s]
 20%|██        | 10/50 [00:10<00:29,  1.35it/s]
 22%|██▏       | 11/50 [00:10<00:28,  1.37it/s]
 24%|██▍       | 12/50 [00:11<00:27,  1.38it/s]
 26%|██▌       | 13/50 [00:12<00:26,  1.39it/s]
 28%|██▊       | 14/50 [00:12<00:25,  1.40it/s]
 30%|███       | 15/50 [00:13<00:25,  1.40it/s]
 32%|███▏      | 16/50 [00:14<00:24,  1.40it/s]
 34%|███▍      | 17/50 [00:15<00:23,  1.41it/s]
 36%|███▌      | 18/50 [00:15<00:22,  1.41it/s]
 38%|███▊      | 19/50 [00:16<00:21,  1.41it/s]
 40%|████      | 20/50 [00:17<00:21,  1.41it/s]
 42%|████▏     | 21/50 [00:17<00:20,  1.41it/s]
 44%|████▍     | 22/50 [00:18<00:19,  1.41it/s]
 46%|████▌     | 23/50 [00:19<00:19,  1.41it/s]
 48%|████▊     | 24/50 [00:19<00:18,  1.41it/s]
 50%|█████     | 25/50 [00:20<00:17,  1.40it/s]
 52%|█████▏    | 26/50 [00:21<00:17,  1.40it/s]
 54%|█████▍    | 27/50 [00:22<00:16,  1.40it/s]
 56%|█████▌    | 28/50 [00:22<00:15,  1.40it/s]
 58%|█████▊    | 29/50 [00:23<00:15,  1.39it/s]
 60%|██████    | 30/50 [00:24<00:14,  1.39it/s]
 62%|██████▏   | 31/50 [00:25<00:13,  1.38it/s]
 64%|██████▍   | 32/50 [00:25<00:13,  1.38it/s]
 66%|██████▌   | 33/50 [00:26<00:12,  1.38it/s]
 68%|██████▊   | 34/50 [00:27<00:11,  1.37it/s]
 70%|███████   | 35/50 [00:27<00:10,  1.37it/s]
 72%|███████▏  | 36/50 [00:28<00:10,  1.37it/s]
 74%|███████▍  | 37/50 [00:29<00:09,  1.36it/s]
 76%|███████▌  | 38/50 [00:30<00:08,  1.36it/s]
 78%|███████▊  | 39/50 [00:30<00:08,  1.36it/s]
 80%|████████  | 40/50 [00:31<00:07,  1.35it/s]
 82%|████████▏ | 41/50 [00:32<00:06,  1.34it/s]
 84%|████████▍ | 42/50 [00:33<00:05,  1.34it/s]
 86%|████████▌ | 43/50 [00:33<00:05,  1.34it/s]
 88%|████████▊ | 44/50 [00:34<00:04,  1.34it/s]
 90%|█████████ | 45/50 [00:35<00:03,  1.34it/s]
 92%|█████████▏| 46/50 [00:36<00:02,  1.34it/s]
 94%|█████████▍| 47/50 [00:36<00:02,  1.33it/s]
 96%|█████████▌| 48/50 [00:37<00:01,  1.33it/s]
 98%|█████████▊| 49/50 [00:38<00:00,  1.32it/s]
100%|██████████| 50/50 [00:39<00:00,  1.32it/s]
100%|██████████| 50/50 [00:39<00:00,  1.28it/s]

Examples

View more examples

Run time and cost

This model costs approximately $0.0085 to run on Replicate, or 117 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 38 seconds. The predict time for this model varies significantly based on the inputs.

Readme

…

Model description

…

Intended use

…

Ethical considerations

…

Caveats and recommendations

…