laion-ai/ongo:13e4da48 – Run with an API on Replicate

Version

You're looking at a specific version of this model. Jump to the model overview.

laion-ai /ongo:13e4da48

Input

prompt

string

Shift + Return to add a new line

a farmhouse surrounded by flowers paintinga farmhouse surrounded by flowers painting

Your text prompt.

Default: ""

negative

string

Shift + Return to add a new line

(optional) Negate the model's prediction for this text from the model's prediction for the target text.

Default: ""

init_image

file

(optional) Initial image to use for the model's prediction.

guidance_scale

number

(minimum: -20, maximum: 100)

Classifier-free guidance scale. Higher values will result in more guidance toward caption, with diminishing returns. Try values between 1.0 and 40.0. In general, going above 5.0 will introduce some artifacting.

Default: 5

steps

integer

(minimum: 15, maximum: 250)

Number of diffusion steps to run. Due to PLMS sampling, using more than 100 steps is unnecessary and may simply produce the exact same output.

Default: 100

batch_size

integer

(minimum: 1, maximum: 16)

Batch size. (higher = slower)

Default: 1

width

integer

Target width

Default: 256

height

integer

Target height

Default: 256

init_skip_fraction

number

(minimum: 0, maximum: 1)

Fraction of sampling steps to skip when using an init image. Defaults to 0.0 if init_image is not specified and 0.5 if init_image is specified.

Default: 0

aesthetic_rating

integer

Aesthetic rating (1-9) - embed to use.

Default: 9

aesthetic_weight

number

Aesthetic weight (0-1). How much to guide towards the aesthetic embed vs the prompt embed.

Default: 0.5

seed

integer

(minimum: -1, maximum: 4294967295)

Seed for random number generator. If -1, a random seed will be chosen.

Default: -1

intermediate_outputs

boolean

Whether to return intermediate outputs. Enable to visualize the diffusion process and/or debug the model. May slow down inference.

Default: false

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

npx create-replicate --model=laion-ai/ongo

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 laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "laion-ai/ongo:13e4da486d56b62616baf8d6233ffd2c09ad534af3e8d55cba4356be2be6ad84",
  {
    input: {
      seed: -1,
      steps: 100,
      width: 256,
      height: 256,
      prompt: "a farmhouse surrounded by flowers painting",
      negative: "",
      batch_size: 4,
      guidance_scale: 5,
      aesthetic_rating: 8,
      aesthetic_weight: 0.1,
      init_skip_fraction: 0,
      intermediate_outputs: false
    }
  }
);
console.log(output);

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 laion-ai/ongo using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "laion-ai/ongo:13e4da486d56b62616baf8d6233ffd2c09ad534af3e8d55cba4356be2be6ad84",
    input={
        "seed": -1,
        "steps": 100,
        "width": 256,
        "height": 256,
        "prompt": "a farmhouse surrounded by flowers painting",
        "negative": "",
        "batch_size": 4,
        "guidance_scale": 5,
        "aesthetic_rating": 8,
        "aesthetic_weight": 0.1,
        "init_skip_fraction": 0,
        "intermediate_outputs": False
    }
)

# The laion-ai/ongo model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/laion-ai/ongo/api#output-schema
    print(item)

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 laion-ai/ongo 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": "13e4da486d56b62616baf8d6233ffd2c09ad534af3e8d55cba4356be2be6ad84",
    "input": {
      "seed": -1,
      "steps": 100,
      "width": 256,
      "height": 256,
      "prompt": "a farmhouse surrounded by flowers painting",
      "negative": "",
      "batch_size": 4,
      "guidance_scale": 5,
      "aesthetic_rating": 8,
      "aesthetic_weight": 0.1,
      "init_skip_fraction": 0,
      "intermediate_outputs": false
    }
  }' \
  https://api.replicate.com/v1/predictions

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

You can run this model locally using Cog. First, install Cog:

brew install cog

If you don’t have Homebrew, there are other installation options available.

Run this to download the model and run it in your local environment:

cog predict r8.im/laion-ai/ongo@sha256:13e4da486d56b62616baf8d6233ffd2c09ad534af3e8d55cba4356be2be6ad84 \
  -i 'seed=-1' \
  -i 'steps=100' \
  -i 'width=256' \
  -i 'height=256' \
  -i 'prompt="a farmhouse surrounded by flowers painting"' \
  -i 'negative=""' \
  -i 'batch_size=4' \
  -i 'guidance_scale=5' \
  -i 'aesthetic_rating=8' \
  -i 'aesthetic_weight=0.1' \
  -i 'init_skip_fraction=0' \
  -i 'intermediate_outputs=false'

To learn more, take a look at the Cog documentation.

Run this to download the model and run it in your local environment:

docker run -d -p 5000:5000 --gpus=all r8.im/laion-ai/ongo@sha256:13e4da486d56b62616baf8d6233ffd2c09ad534af3e8d55cba4356be2be6ad84
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "seed": -1,
      "steps": 100,
      "width": 256,
      "height": 256,
      "prompt": "a farmhouse surrounded by flowers painting",
      "negative": "",
      "batch_size": 4,
      "guidance_scale": 5,
      "aesthetic_rating": 8,
      "aesthetic_weight": 0.1,
      "init_skip_fraction": 0,
      "intermediate_outputs": false
    }
  }' \
  http://localhost:5000/predictions

To learn more, take a look at the Cog documentation.

Output

{
  "completed_at": "2022-06-28T15:15:11.018622Z",
  "created_at": "2022-06-28T15:14:05.514142Z",
  "data_removed": false,
  "error": null,
  "id": "sn5d222eajgo7piqrsp5arjz3y",
  "input": {
    "seed": -1,
    "steps": "100",
    "width": 256,
    "height": 256,
    "prompt": "a farmhouse surrounded by flowers painting",
    "batch_size": "4",
    "guidance_scale": 5,
    "aesthetic_rating": 8,
    "aesthetic_weight": 0.1
  },
  "logs": "Using seed 1629174958\nRunning simulation for a farmhouse surrounded by flowers painting\nEncoding text embeddings with a farmhouse surrounded by flowers painting dimensions\nUsing aesthetic embedding 8 with weight 0.1\nUsing inpaint model but no image is provided. Initializing with zeros.\nRunning diffusion...\n\n  0%|          | 0/100 [00:00<?, ?it/s]\n  1%|          | 1/100 [00:00<01:33,  1.06it/s]\n  2%|▏         | 2/100 [00:01<01:24,  1.17it/s]\n  3%|▎         | 3/100 [00:02<01:20,  1.20it/s]\n  4%|▍         | 4/100 [00:02<00:56,  1.71it/s]\n  5%|▌         | 5/100 [00:02<00:42,  2.24it/s]\n  6%|▌         | 6/100 [00:03<00:34,  2.76it/s]\n  7%|▋         | 7/100 [00:03<00:28,  3.24it/s]\n  8%|▊         | 8/100 [00:03<00:25,  3.64it/s]\n  9%|▉         | 9/100 [00:03<00:22,  3.98it/s]\n 10%|█         | 10/100 [00:03<00:21,  4.24it/s]\n 11%|█         | 11/100 [00:04<00:20,  4.44it/s]\n 12%|█▏        | 12/100 [00:04<00:19,  4.58it/s]\n 13%|█▎        | 13/100 [00:04<00:18,  4.67it/s]\n 14%|█▍        | 14/100 [00:04<00:18,  4.75it/s]\n 15%|█▌        | 15/100 [00:04<00:17,  4.82it/s]\n 16%|█▌        | 16/100 [00:05<00:17,  4.85it/s]\n 17%|█▋        | 17/100 [00:05<00:17,  4.87it/s]\n 18%|█▊        | 18/100 [00:05<00:16,  4.89it/s]\n 19%|█▉        | 19/100 [00:05<00:16,  4.90it/s]\n 20%|██        | 20/100 [00:05<00:16,  4.93it/s]\n 21%|██        | 21/100 [00:06<00:16,  4.92it/s]\n 22%|██▏       | 22/100 [00:06<00:15,  4.92it/s]\n 23%|██▎       | 23/100 [00:06<00:15,  4.93it/s]\n 24%|██▍       | 24/100 [00:06<00:15,  4.93it/s]\n 25%|██▌       | 25/100 [00:06<00:15,  4.93it/s]\n 26%|██▌       | 26/100 [00:07<00:15,  4.93it/s]\n 27%|██▋       | 27/100 [00:07<00:14,  4.92it/s]\n 28%|██▊       | 28/100 [00:07<00:14,  4.93it/s]\n 29%|██▉       | 29/100 [00:07<00:14,  4.93it/s]\n 30%|███       | 30/100 [00:08<00:14,  4.93it/s]\n 31%|███       | 31/100 [00:08<00:13,  4.93it/s]\n 32%|███▏      | 32/100 [00:08<00:13,  4.93it/s]\n 33%|███▎      | 33/100 [00:08<00:13,  4.93it/s]\n 34%|███▍      | 34/100 [00:08<00:13,  4.93it/s]\n 35%|███▌      | 35/100 [00:09<00:13,  4.93it/s]\n 36%|███▌      | 36/100 [00:09<00:12,  4.94it/s]\n 37%|███▋      | 37/100 [00:09<00:12,  4.94it/s]\n 38%|███▊      | 38/100 [00:09<00:12,  4.93it/s]\n 39%|███▉      | 39/100 [00:09<00:12,  4.94it/s]\n 40%|████      | 40/100 [00:10<00:12,  4.94it/s]\n 41%|████      | 41/100 [00:10<00:11,  4.94it/s]\n 42%|████▏     | 42/100 [00:10<00:11,  4.94it/s]\n 43%|████▎     | 43/100 [00:10<00:11,  4.94it/s]\n 44%|████▍     | 44/100 [00:10<00:11,  4.93it/s]\n 45%|████▌     | 45/100 [00:11<00:11,  4.93it/s]\n 46%|████▌     | 46/100 [00:11<00:10,  4.92it/s]\n 47%|████▋     | 47/100 [00:11<00:10,  4.91it/s]\n 48%|████▊     | 48/100 [00:11<00:10,  4.92it/s]\n 49%|████▉     | 49/100 [00:11<00:10,  4.93it/s]\n 50%|█████     | 50/100 [00:12<00:10,  4.93it/s]\n 51%|█████     | 51/100 [00:12<00:09,  4.93it/s]\n 52%|█████▏    | 52/100 [00:12<00:09,  4.92it/s]\n 53%|█████▎    | 53/100 [00:12<00:09,  4.92it/s]\n 54%|█████▍    | 54/100 [00:12<00:09,  4.94it/s]\n 55%|█████▌    | 55/100 [00:13<00:09,  4.93it/s]\n 56%|█████▌    | 56/100 [00:13<00:08,  4.93it/s]\n 57%|█████▋    | 57/100 [00:13<00:08,  4.92it/s]\n 58%|█████▊    | 58/100 [00:13<00:08,  4.93it/s]\n 59%|█████▉    | 59/100 [00:13<00:08,  4.93it/s]\n 60%|██████    | 60/100 [00:14<00:08,  4.93it/s]\n 61%|██████    | 61/100 [00:14<00:07,  4.92it/s]\n 62%|██████▏   | 62/100 [00:14<00:07,  4.91it/s]\n 63%|██████▎   | 63/100 [00:14<00:07,  4.91it/s]\n 64%|██████▍   | 64/100 [00:14<00:07,  4.90it/s]\n 65%|██████▌   | 65/100 [00:15<00:07,  4.89it/s]\n 66%|██████▌   | 66/100 [00:15<00:06,  4.88it/s]\n 67%|██████▋   | 67/100 [00:15<00:06,  4.88it/s]\n 68%|██████▊   | 68/100 [00:15<00:06,  4.88it/s]\n 69%|██████▉   | 69/100 [00:15<00:06,  4.88it/s]\n 70%|███████   | 70/100 [00:16<00:06,  4.88it/s]\n 71%|███████   | 71/100 [00:16<00:05,  4.89it/s]\n 72%|███████▏  | 72/100 [00:16<00:05,  4.89it/s]\n 73%|███████▎  | 73/100 [00:16<00:05,  4.90it/s]\n 74%|███████▍  | 74/100 [00:16<00:05,  4.89it/s]\n 75%|███████▌  | 75/100 [00:17<00:05,  4.88it/s]\n 76%|███████▌  | 76/100 [00:17<00:04,  4.87it/s]\n 77%|███████▋  | 77/100 [00:17<00:04,  4.86it/s]\n 78%|███████▊  | 78/100 [00:17<00:04,  4.87it/s]\n 79%|███████▉  | 79/100 [00:17<00:04,  4.87it/s]\n 80%|████████  | 80/100 [00:18<00:04,  4.88it/s]\n 81%|████████  | 81/100 [00:18<00:03,  4.89it/s]\n 82%|████████▏ | 82/100 [00:18<00:03,  4.88it/s]\n 83%|████████▎ | 83/100 [00:18<00:03,  4.88it/s]\n 84%|████████▍ | 84/100 [00:19<00:03,  4.87it/s]\n 85%|████████▌ | 85/100 [00:19<00:03,  4.86it/s]\n 86%|████████▌ | 86/100 [00:19<00:02,  4.86it/s]\n 87%|████████▋ | 87/100 [00:19<00:02,  4.86it/s]\n 88%|████████▊ | 88/100 [00:19<00:02,  4.86it/s]\n 89%|████████▉ | 89/100 [00:20<00:02,  4.87it/s]\n 90%|█████████ | 90/100 [00:20<00:02,  4.88it/s]\n 91%|█████████ | 91/100 [00:20<00:01,  4.86it/s]\n 92%|█████████▏| 92/100 [00:20<00:01,  4.86it/s]\n 93%|█████████▎| 93/100 [00:20<00:01,  4.86it/s]\n 94%|█████████▍| 94/100 [00:21<00:01,  4.85it/s]\n 95%|█████████▌| 95/100 [00:21<00:01,  4.86it/s]\n 96%|█████████▌| 96/100 [00:21<00:00,  4.86it/s]\n 97%|█████████▋| 97/100 [00:21<00:00,  4.86it/s]\n 98%|█████████▊| 98/100 [00:21<00:00,  4.86it/s]\nSaving final sample/s\n 99%|█████████▉| 99/100 [00:22<00:00,  4.85it/s]\n100%|██████████| 100/100 [00:22<00:00,  3.24it/s]\n100%|██████████| 100/100 [00:22<00:00,  4.42it/s]",
  "metrics": {
    "predict_time": 26.032431,
    "total_time": 65.50448
  },
  "output": [
    [
      "https://replicate.delivery/mgxm/730390c5-9761-44d7-b5d8-eaa7eec9619b/current_0.png",
      "https://replicate.delivery/mgxm/5d2239c3-acec-492d-9705-1421358f31f5/current_1.png",
      "https://replicate.delivery/mgxm/d0ab32b5-3e34-48f4-bc02-51c13d554fd2/current_2.png",
      "https://replicate.delivery/mgxm/02390209-5ec2-4e48-bca8-a3e26ae42e25/current_3.png"
    ]
  ],
  "started_at": "2022-06-28T15:14:44.986191Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/sn5d222eajgo7piqrsp5arjz3y",
    "cancel": "https://api.replicate.com/v1/predictions/sn5d222eajgo7piqrsp5arjz3y/cancel"
  },
  "version": "13e4da486d56b62616baf8d6233ffd2c09ad534af3e8d55cba4356be2be6ad84"
}

Generated in

26.0 seconds

Tweak itReport

Using seed 1629174958
Running simulation for a farmhouse surrounded by flowers painting
Encoding text embeddings with a farmhouse surrounded by flowers painting dimensions
Using aesthetic embedding 8 with weight 0.1
Using inpaint model but no image is provided. Initializing with zeros.
Running diffusion...

  0%|          | 0/100 [00:00<?, ?it/s]
  1%|          | 1/100 [00:00<01:33,  1.06it/s]
  2%|▏         | 2/100 [00:01<01:24,  1.17it/s]
  3%|▎         | 3/100 [00:02<01:20,  1.20it/s]
  4%|▍         | 4/100 [00:02<00:56,  1.71it/s]
  5%|▌         | 5/100 [00:02<00:42,  2.24it/s]
  6%|▌         | 6/100 [00:03<00:34,  2.76it/s]
  7%|▋         | 7/100 [00:03<00:28,  3.24it/s]
  8%|▊         | 8/100 [00:03<00:25,  3.64it/s]
  9%|▉         | 9/100 [00:03<00:22,  3.98it/s]
 10%|█         | 10/100 [00:03<00:21,  4.24it/s]
 11%|█         | 11/100 [00:04<00:20,  4.44it/s]
 12%|█▏        | 12/100 [00:04<00:19,  4.58it/s]
 13%|█▎        | 13/100 [00:04<00:18,  4.67it/s]
 14%|█▍        | 14/100 [00:04<00:18,  4.75it/s]
 15%|█▌        | 15/100 [00:04<00:17,  4.82it/s]
 16%|█▌        | 16/100 [00:05<00:17,  4.85it/s]
 17%|█▋        | 17/100 [00:05<00:17,  4.87it/s]
 18%|█▊        | 18/100 [00:05<00:16,  4.89it/s]
 19%|█▉        | 19/100 [00:05<00:16,  4.90it/s]
 20%|██        | 20/100 [00:05<00:16,  4.93it/s]
 21%|██        | 21/100 [00:06<00:16,  4.92it/s]
 22%|██▏       | 22/100 [00:06<00:15,  4.92it/s]
 23%|██▎       | 23/100 [00:06<00:15,  4.93it/s]
 24%|██▍       | 24/100 [00:06<00:15,  4.93it/s]
 25%|██▌       | 25/100 [00:06<00:15,  4.93it/s]
 26%|██▌       | 26/100 [00:07<00:15,  4.93it/s]
 27%|██▋       | 27/100 [00:07<00:14,  4.92it/s]
 28%|██▊       | 28/100 [00:07<00:14,  4.93it/s]
 29%|██▉       | 29/100 [00:07<00:14,  4.93it/s]
 30%|███       | 30/100 [00:08<00:14,  4.93it/s]
 31%|███       | 31/100 [00:08<00:13,  4.93it/s]
 32%|███▏      | 32/100 [00:08<00:13,  4.93it/s]
 33%|███▎      | 33/100 [00:08<00:13,  4.93it/s]
 34%|███▍      | 34/100 [00:08<00:13,  4.93it/s]
 35%|███▌      | 35/100 [00:09<00:13,  4.93it/s]
 36%|███▌      | 36/100 [00:09<00:12,  4.94it/s]
 37%|███▋      | 37/100 [00:09<00:12,  4.94it/s]
 38%|███▊      | 38/100 [00:09<00:12,  4.93it/s]
 39%|███▉      | 39/100 [00:09<00:12,  4.94it/s]
 40%|████      | 40/100 [00:10<00:12,  4.94it/s]
 41%|████      | 41/100 [00:10<00:11,  4.94it/s]
 42%|████▏     | 42/100 [00:10<00:11,  4.94it/s]
 43%|████▎     | 43/100 [00:10<00:11,  4.94it/s]
 44%|████▍     | 44/100 [00:10<00:11,  4.93it/s]
 45%|████▌     | 45/100 [00:11<00:11,  4.93it/s]
 46%|████▌     | 46/100 [00:11<00:10,  4.92it/s]
 47%|████▋     | 47/100 [00:11<00:10,  4.91it/s]
 48%|████▊     | 48/100 [00:11<00:10,  4.92it/s]
 49%|████▉     | 49/100 [00:11<00:10,  4.93it/s]
 50%|█████     | 50/100 [00:12<00:10,  4.93it/s]
 51%|█████     | 51/100 [00:12<00:09,  4.93it/s]
 52%|█████▏    | 52/100 [00:12<00:09,  4.92it/s]
 53%|█████▎    | 53/100 [00:12<00:09,  4.92it/s]
 54%|█████▍    | 54/100 [00:12<00:09,  4.94it/s]
 55%|█████▌    | 55/100 [00:13<00:09,  4.93it/s]
 56%|█████▌    | 56/100 [00:13<00:08,  4.93it/s]
 57%|█████▋    | 57/100 [00:13<00:08,  4.92it/s]
 58%|█████▊    | 58/100 [00:13<00:08,  4.93it/s]
 59%|█████▉    | 59/100 [00:13<00:08,  4.93it/s]
 60%|██████    | 60/100 [00:14<00:08,  4.93it/s]
 61%|██████    | 61/100 [00:14<00:07,  4.92it/s]
 62%|██████▏   | 62/100 [00:14<00:07,  4.91it/s]
 63%|██████▎   | 63/100 [00:14<00:07,  4.91it/s]
 64%|██████▍   | 64/100 [00:14<00:07,  4.90it/s]
 65%|██████▌   | 65/100 [00:15<00:07,  4.89it/s]
 66%|██████▌   | 66/100 [00:15<00:06,  4.88it/s]
 67%|██████▋   | 67/100 [00:15<00:06,  4.88it/s]
 68%|██████▊   | 68/100 [00:15<00:06,  4.88it/s]
 69%|██████▉   | 69/100 [00:15<00:06,  4.88it/s]
 70%|███████   | 70/100 [00:16<00:06,  4.88it/s]
 71%|███████   | 71/100 [00:16<00:05,  4.89it/s]
 72%|███████▏  | 72/100 [00:16<00:05,  4.89it/s]
 73%|███████▎  | 73/100 [00:16<00:05,  4.90it/s]
 74%|███████▍  | 74/100 [00:16<00:05,  4.89it/s]
 75%|███████▌  | 75/100 [00:17<00:05,  4.88it/s]
 76%|███████▌  | 76/100 [00:17<00:04,  4.87it/s]
 77%|███████▋  | 77/100 [00:17<00:04,  4.86it/s]
 78%|███████▊  | 78/100 [00:17<00:04,  4.87it/s]
 79%|███████▉  | 79/100 [00:17<00:04,  4.87it/s]
 80%|████████  | 80/100 [00:18<00:04,  4.88it/s]
 81%|████████  | 81/100 [00:18<00:03,  4.89it/s]
 82%|████████▏ | 82/100 [00:18<00:03,  4.88it/s]
 83%|████████▎ | 83/100 [00:18<00:03,  4.88it/s]
 84%|████████▍ | 84/100 [00:19<00:03,  4.87it/s]
 85%|████████▌ | 85/100 [00:19<00:03,  4.86it/s]
 86%|████████▌ | 86/100 [00:19<00:02,  4.86it/s]
 87%|████████▋ | 87/100 [00:19<00:02,  4.86it/s]
 88%|████████▊ | 88/100 [00:19<00:02,  4.86it/s]
 89%|████████▉ | 89/100 [00:20<00:02,  4.87it/s]
 90%|█████████ | 90/100 [00:20<00:02,  4.88it/s]
 91%|█████████ | 91/100 [00:20<00:01,  4.86it/s]
 92%|█████████▏| 92/100 [00:20<00:01,  4.86it/s]
 93%|█████████▎| 93/100 [00:20<00:01,  4.86it/s]
 94%|█████████▍| 94/100 [00:21<00:01,  4.85it/s]
 95%|█████████▌| 95/100 [00:21<00:01,  4.86it/s]
 96%|█████████▌| 96/100 [00:21<00:00,  4.86it/s]
 97%|█████████▋| 97/100 [00:21<00:00,  4.86it/s]
 98%|█████████▊| 98/100 [00:21<00:00,  4.86it/s]
Saving final sample/s
 99%|█████████▉| 99/100 [00:22<00:00,  4.85it/s]
100%|██████████| 100/100 [00:22<00:00,  3.24it/s]
100%|██████████| 100/100 [00:22<00:00,  4.42it/s]