lucataco/demofusion-enhance:5bcfe110 – Run with an API on Replicate

Version

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

lucataco /demofusion-enhance:5bcfe110

Playground API

Input

image

*file

Input image

scale

integer

Scale factor for input image

Default: 2

prompt

string

Shift + Return to add a new line

Input prompt

Default: "A high resolution photo"

auto_prompt

boolean

Select to use auto-generated CLIP prompt instead of using the above custom prompt

Default: false

negative_prompt

string

Shift + Return to add a new line

blurry, ugly, duplicate, poorly drawn, deformed, mosaicblurry, ugly, duplicate, poorly drawn, deformed, mosaic

Input Negative Prompt

Default: "blurry, ugly, duplicate, poorly drawn, deformed, mosaic"

num_inference_steps

integer

(minimum: 1, maximum: 500)

Number of denoising steps

Default: 40

guidance_scale

number

(minimum: 1, maximum: 50)

Scale for classifier-free guidance

Default: 8.5

view_batch_size

integer

The batch size for multiple denoising paths

Default: 16

stride

integer

The stride of moving local patches

Default: 64

cosine_scale_1

number

Control the strength of skip-residual

Default: 3

cosine_scale_2

number

Control the strength of dilated sampling

Default: 1

cosine_scale_3

number

Control the strength of the Gaussian filter

Default: 1

sigma

number

The standard value of the Gaussian filter

Default: 0.8

multi_decoder

boolean

Use multiple decoders

Default: false

seed

integer

Random seed. Leave blank to randomize the seed

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

npx create-replicate --model=lucataco/demofusion-enhance

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 lucataco/demofusion-enhance using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "lucataco/demofusion-enhance:5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e",
  {
    input: {
      image: "https://replicate.delivery/pbxt/K10oPBW66vKyg5N40mhCEzCGps3rcGrWTInarrtWa0oD9Eq1/lowres-dog.png",
      scale: 2,
      sigma: 0.8,
      prompt: "A high resolution photo",
      stride: 64,
      auto_prompt: true,
      multi_decoder: false,
      cosine_scale_1: 3,
      cosine_scale_2: 1,
      cosine_scale_3: 1,
      guidance_scale: 8.5,
      negative_prompt: "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
      view_batch_size: 16,
      num_inference_steps: 40
    }
  }
);
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 lucataco/demofusion-enhance using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "lucataco/demofusion-enhance:5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e",
    input={
        "image": "https://replicate.delivery/pbxt/K10oPBW66vKyg5N40mhCEzCGps3rcGrWTInarrtWa0oD9Eq1/lowres-dog.png",
        "scale": 2,
        "sigma": 0.8,
        "prompt": "A high resolution photo",
        "stride": 64,
        "auto_prompt": True,
        "multi_decoder": False,
        "cosine_scale_1": 3,
        "cosine_scale_2": 1,
        "cosine_scale_3": 1,
        "guidance_scale": 8.5,
        "negative_prompt": "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
        "view_batch_size": 16,
        "num_inference_steps": 40
    }
)
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 lucataco/demofusion-enhance 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": "5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e",
    "input": {
      "image": "https://replicate.delivery/pbxt/K10oPBW66vKyg5N40mhCEzCGps3rcGrWTInarrtWa0oD9Eq1/lowres-dog.png",
      "scale": 2,
      "sigma": 0.8,
      "prompt": "A high resolution photo",
      "stride": 64,
      "auto_prompt": true,
      "multi_decoder": false,
      "cosine_scale_1": 3,
      "cosine_scale_2": 1,
      "cosine_scale_3": 1,
      "guidance_scale": 8.5,
      "negative_prompt": "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
      "view_batch_size": 16,
      "num_inference_steps": 40
    }
  }' \
  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/lucataco/demofusion-enhance@sha256:5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e \
  -i 'image="https://replicate.delivery/pbxt/K10oPBW66vKyg5N40mhCEzCGps3rcGrWTInarrtWa0oD9Eq1/lowres-dog.png"' \
  -i 'scale=2' \
  -i 'sigma=0.8' \
  -i 'prompt="A high resolution photo"' \
  -i 'stride=64' \
  -i 'auto_prompt=true' \
  -i 'multi_decoder=false' \
  -i 'cosine_scale_1=3' \
  -i 'cosine_scale_2=1' \
  -i 'cosine_scale_3=1' \
  -i 'guidance_scale=8.5' \
  -i 'negative_prompt="blurry, ugly, duplicate, poorly drawn, deformed, mosaic"' \
  -i 'view_batch_size=16' \
  -i 'num_inference_steps=40'

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/lucataco/demofusion-enhance@sha256:5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e
curl -s -X POST \
  -H "Content-Type: application/json" \
  -d $'{
    "input": {
      "image": "https://replicate.delivery/pbxt/K10oPBW66vKyg5N40mhCEzCGps3rcGrWTInarrtWa0oD9Eq1/lowres-dog.png",
      "scale": 2,
      "sigma": 0.8,
      "prompt": "A high resolution photo",
      "stride": 64,
      "auto_prompt": true,
      "multi_decoder": false,
      "cosine_scale_1": 3,
      "cosine_scale_2": 1,
      "cosine_scale_3": 1,
      "guidance_scale": 8.5,
      "negative_prompt": "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
      "view_batch_size": 16,
      "num_inference_steps": 40
    }
  }' \
  http://localhost:5000/predictions

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

Output

We were unable to load these images. Please make sure the URLs are valid.

{
  "input": "https://replicate.delivery/pbxt/K10oPBW66vKyg5N40mhCEzCGps3rcGrWTInarrtWa0oD9Eq1/lowres-dog.png",
  "outut": "https://replicate.delivery/pbxt/kSFd5oH8lNoRKdDxlpoZeJM6TY7b6ggfExG1WlqF1ACz3UASA/out-2.png"
}

{
  "completed_at": "2023-12-08T22:43:00.547710Z",
  "created_at": "2023-12-08T22:41:27.466972Z",
  "data_removed": false,
  "error": null,
  "id": "uvz2uflbsyozfak6i5n6em4irq",
  "input": {
    "image": "https://replicate.delivery/pbxt/K10oPBW66vKyg5N40mhCEzCGps3rcGrWTInarrtWa0oD9Eq1/lowres-dog.png",
    "scale": 2,
    "sigma": 0.8,
    "prompt": "A high resolution photo",
    "stride": 64,
    "auto_prompt": true,
    "multi_decoder": false,
    "cosine_scale_1": 3,
    "cosine_scale_2": 1,
    "cosine_scale_3": 1,
    "guidance_scale": 8.5,
    "negative_prompt": "blurry, ugly, duplicate, poorly drawn, deformed, mosaic",
    "view_batch_size": 16,
    "num_inference_steps": 40
  },
  "logs": "Using seed: 3935140720\n  0%|          | 0/55 [00:00<?, ?it/s]\n 38%|███▊      | 21/55 [00:00<00:00, 96.59it/s]\n 84%|████████▎ | 46/55 [00:00<00:00, 156.27it/s]\n100%|██████████| 55/55 [00:00<00:00, 155.29it/s]\nFlavor chain:   0%|          | 0/32 [00:00<?, ?it/s]\nFlavor chain:   3%|▎         | 1/32 [00:01<00:59,  1.93s/it]\nFlavor chain:   6%|▋         | 2/32 [00:03<00:58,  1.95s/it]\nFlavor chain:   9%|▉         | 3/32 [00:05<00:56,  1.96s/it]\nFlavor chain:  12%|█▎        | 4/32 [00:07<00:55,  1.99s/it]\nFlavor chain:  16%|█▌        | 5/32 [00:09<00:54,  2.01s/it]\nFlavor chain:  19%|█▉        | 6/32 [00:12<00:53,  2.07s/it]\nFlavor chain:  22%|██▏       | 7/32 [00:14<00:53,  2.13s/it]\nFlavor chain:  25%|██▌       | 8/32 [00:16<00:52,  2.17s/it]\nFlavor chain:  28%|██▊       | 9/32 [00:18<00:50,  2.20s/it]\nFlavor chain:  31%|███▏      | 10/32 [00:21<00:48,  2.23s/it]\nFlavor chain:  34%|███▍      | 11/32 [00:23<00:47,  2.25s/it]\nFlavor chain:  34%|███▍      | 11/32 [00:25<00:49,  2.35s/it]\n  0%|          | 0/55 [00:00<?, ?it/s]\n 42%|████▏     | 23/55 [00:00<00:00, 229.65it/s]\n 89%|████████▉ | 49/55 [00:00<00:00, 242.37it/s]\n100%|██████████| 55/55 [00:00<00:00, 242.84it/s]\n  0%|          | 0/6 [00:00<?, ?it/s]\n100%|██████████| 6/6 [00:00<00:00, 240.03it/s]\n  0%|          | 0/50 [00:00<?, ?it/s]\n 64%|██████▍   | 32/50 [00:00<00:00, 313.64it/s]\n100%|██████████| 50/50 [00:00<00:00, 316.96it/s]\nPrompt:  araffe dog wearing a party hat and a bow tie, depicting a corgi made of fire, pexels, 256x256, at a birthday party, фото девушка курит, 2012, adopt, :6, corgi, niko oneshot riding a roomba, us\n### Phase Encoding ###\n  0%|          | 0/40 [00:00<?, ?it/s]\n0%|          | 0/40 [00:00<?, ?it/s]\n### Phase 1 Denoising ###\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:00<00:08,  4.42it/s]\n  5%|▌         | 2/40 [00:00<00:08,  4.42it/s]\n  8%|▊         | 3/40 [00:00<00:08,  4.41it/s]\n 10%|█         | 4/40 [00:00<00:08,  4.41it/s]\n 12%|█▎        | 5/40 [00:01<00:07,  4.40it/s]\n 15%|█▌        | 6/40 [00:01<00:07,  4.40it/s]\n 18%|█▊        | 7/40 [00:01<00:07,  4.40it/s]\n 20%|██        | 8/40 [00:01<00:07,  4.40it/s]\n 22%|██▎       | 9/40 [00:02<00:07,  4.40it/s]\n 25%|██▌       | 10/40 [00:02<00:06,  4.40it/s]\n 28%|██▊       | 11/40 [00:02<00:06,  4.40it/s]\n 30%|███       | 12/40 [00:02<00:06,  4.40it/s]\n 32%|███▎      | 13/40 [00:02<00:06,  4.40it/s]\n 35%|███▌      | 14/40 [00:03<00:05,  4.40it/s]\n 38%|███▊      | 15/40 [00:03<00:05,  4.40it/s]\n 40%|████      | 16/40 [00:03<00:05,  4.40it/s]\n 42%|████▎     | 17/40 [00:03<00:05,  4.40it/s]\n 45%|████▌     | 18/40 [00:04<00:04,  4.40it/s]\n 48%|████▊     | 19/40 [00:04<00:04,  4.40it/s]\n 50%|█████     | 20/40 [00:04<00:04,  4.40it/s]\n 52%|█████▎    | 21/40 [00:04<00:04,  4.40it/s]\n 55%|█████▌    | 22/40 [00:04<00:04,  4.40it/s]\n 57%|█████▊    | 23/40 [00:05<00:03,  4.40it/s]\n 60%|██████    | 24/40 [00:05<00:03,  4.39it/s]\n 62%|██████▎   | 25/40 [00:05<00:03,  4.39it/s]\n 65%|██████▌   | 26/40 [00:05<00:03,  4.39it/s]\n 68%|██████▊   | 27/40 [00:06<00:02,  4.39it/s]\n 70%|███████   | 28/40 [00:06<00:02,  4.39it/s]\n 72%|███████▎  | 29/40 [00:06<00:02,  4.39it/s]\n 75%|███████▌  | 30/40 [00:06<00:02,  4.39it/s]\n 78%|███████▊  | 31/40 [00:07<00:02,  4.40it/s]\n 80%|████████  | 32/40 [00:07<00:01,  4.40it/s]\n 82%|████████▎ | 33/40 [00:07<00:01,  4.40it/s]\n 85%|████████▌ | 34/40 [00:07<00:01,  4.40it/s]\n 88%|████████▊ | 35/40 [00:07<00:01,  4.40it/s]\n 90%|█████████ | 36/40 [00:08<00:00,  4.40it/s]\n 92%|█████████▎| 37/40 [00:08<00:00,  4.40it/s]\n 95%|█████████▌| 38/40 [00:08<00:00,  4.40it/s]\n 98%|█████████▊| 39/40 [00:08<00:00,  4.40it/s]\n### Phase 1 Decoding ###\n100%|██████████| 40/40 [00:09<00:00,  4.40it/s]\n100%|██████████| 40/40 [00:09<00:00,  4.30it/s]\n### Phase 2 Denoising ###\n  0%|          | 0/40 [00:00<?, ?it/s]\n  2%|▎         | 1/40 [00:01<00:50,  1.29s/it]\n  5%|▌         | 2/40 [00:02<00:48,  1.29s/it]\n  8%|▊         | 3/40 [00:03<00:47,  1.29s/it]\n 10%|█         | 4/40 [00:05<00:46,  1.29s/it]\n 12%|█▎        | 5/40 [00:06<00:45,  1.29s/it]\n 15%|█▌        | 6/40 [00:07<00:43,  1.29s/it]\n 18%|█▊        | 7/40 [00:09<00:42,  1.29s/it]\n 20%|██        | 8/40 [00:10<00:41,  1.29s/it]\n 22%|██▎       | 9/40 [00:11<00:39,  1.29s/it]\n 25%|██▌       | 10/40 [00:12<00:38,  1.29s/it]\n 28%|██▊       | 11/40 [00:14<00:37,  1.29s/it]\n 30%|███       | 12/40 [00:15<00:36,  1.29s/it]\n 32%|███▎      | 13/40 [00:16<00:34,  1.29s/it]\n 35%|███▌      | 14/40 [00:18<00:33,  1.29s/it]\n 38%|███▊      | 15/40 [00:19<00:32,  1.29s/it]\n 40%|████      | 16/40 [00:20<00:30,  1.29s/it]\n 42%|████▎     | 17/40 [00:21<00:29,  1.29s/it]\n 45%|████▌     | 18/40 [00:23<00:28,  1.29s/it]\n 48%|████▊     | 19/40 [00:24<00:27,  1.29s/it]\n 50%|█████     | 20/40 [00:25<00:25,  1.29s/it]\n 52%|█████▎    | 21/40 [00:27<00:24,  1.29s/it]\n 55%|█████▌    | 22/40 [00:28<00:23,  1.29s/it]\n 57%|█████▊    | 23/40 [00:29<00:21,  1.29s/it]\n 60%|██████    | 24/40 [00:30<00:20,  1.29s/it]\n 62%|██████▎   | 25/40 [00:32<00:19,  1.29s/it]\n 65%|██████▌   | 26/40 [00:33<00:18,  1.29s/it]\n 68%|██████▊   | 27/40 [00:34<00:16,  1.29s/it]\n 70%|███████   | 28/40 [00:36<00:15,  1.29s/it]\n 72%|███████▎  | 29/40 [00:37<00:14,  1.29s/it]\n 75%|███████▌  | 30/40 [00:38<00:12,  1.29s/it]\n 78%|███████▊  | 31/40 [00:39<00:11,  1.29s/it]\n 80%|████████  | 32/40 [00:41<00:10,  1.29s/it]\n 82%|████████▎ | 33/40 [00:42<00:09,  1.29s/it]\n 85%|████████▌ | 34/40 [00:43<00:07,  1.29s/it]\n 88%|████████▊ | 35/40 [00:45<00:06,  1.29s/it]\n 90%|█████████ | 36/40 [00:46<00:05,  1.29s/it]\n 92%|█████████▎| 37/40 [00:47<00:03,  1.29s/it]\n 95%|█████████▌| 38/40 [00:49<00:02,  1.29s/it]\n 98%|█████████▊| 39/40 [00:50<00:01,  1.29s/it]\n### Phase 2 Decoding ###\n100%|██████████| 40/40 [00:51<00:00,  1.29s/it]\n100%|██████████| 40/40 [00:52<00:00,  1.31s/it]",
  "metrics": {
    "predict_time": 93.043527,
    "total_time": 93.080738
  },
  "output": "https://replicate.delivery/pbxt/kSFd5oH8lNoRKdDxlpoZeJM6TY7b6ggfExG1WlqF1ACz3UASA/out-2.png",
  "started_at": "2023-12-08T22:41:27.504183Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/uvz2uflbsyozfak6i5n6em4irq",
    "cancel": "https://api.replicate.com/v1/predictions/uvz2uflbsyozfak6i5n6em4irq/cancel"
  },
  "version": "5bcfe11066c820e8c08232c6efa3c8a7ab2cd667ad136ca173633f352170691e"
}

Generated in

1 minute 33 seconds

Tweak itReport

Using seed: 3935140720
  0%|          | 0/55 [00:00<?, ?it/s]
 38%|███▊      | 21/55 [00:00<00:00, 96.59it/s]
 84%|████████▎ | 46/55 [00:00<00:00, 156.27it/s]
100%|██████████| 55/55 [00:00<00:00, 155.29it/s]
Flavor chain:   0%|          | 0/32 [00:00<?, ?it/s]
Flavor chain:   3%|▎         | 1/32 [00:01<00:59,  1.93s/it]
Flavor chain:   6%|▋         | 2/32 [00:03<00:58,  1.95s/it]
Flavor chain:   9%|▉         | 3/32 [00:05<00:56,  1.96s/it]
Flavor chain:  12%|█▎        | 4/32 [00:07<00:55,  1.99s/it]
Flavor chain:  16%|█▌        | 5/32 [00:09<00:54,  2.01s/it]
Flavor chain:  19%|█▉        | 6/32 [00:12<00:53,  2.07s/it]
Flavor chain:  22%|██▏       | 7/32 [00:14<00:53,  2.13s/it]
Flavor chain:  25%|██▌       | 8/32 [00:16<00:52,  2.17s/it]
Flavor chain:  28%|██▊       | 9/32 [00:18<00:50,  2.20s/it]
Flavor chain:  31%|███▏      | 10/32 [00:21<00:48,  2.23s/it]
Flavor chain:  34%|███▍      | 11/32 [00:23<00:47,  2.25s/it]
Flavor chain:  34%|███▍      | 11/32 [00:25<00:49,  2.35s/it]
  0%|          | 0/55 [00:00<?, ?it/s]
 42%|████▏     | 23/55 [00:00<00:00, 229.65it/s]
 89%|████████▉ | 49/55 [00:00<00:00, 242.37it/s]
100%|██████████| 55/55 [00:00<00:00, 242.84it/s]
  0%|          | 0/6 [00:00<?, ?it/s]
100%|██████████| 6/6 [00:00<00:00, 240.03it/s]
  0%|          | 0/50 [00:00<?, ?it/s]
 64%|██████▍   | 32/50 [00:00<00:00, 313.64it/s]
100%|██████████| 50/50 [00:00<00:00, 316.96it/s]
Prompt:  araffe dog wearing a party hat and a bow tie, depicting a corgi made of fire, pexels, 256x256, at a birthday party, фото девушка курит, 2012, adopt, :6, corgi, niko oneshot riding a roomba, us
### Phase Encoding ###
  0%|          | 0/40 [00:00<?, ?it/s]
0%|          | 0/40 [00:00<?, ?it/s]
### Phase 1 Denoising ###
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:00<00:08,  4.42it/s]
  5%|▌         | 2/40 [00:00<00:08,  4.42it/s]
  8%|▊         | 3/40 [00:00<00:08,  4.41it/s]
 10%|█         | 4/40 [00:00<00:08,  4.41it/s]
 12%|█▎        | 5/40 [00:01<00:07,  4.40it/s]
 15%|█▌        | 6/40 [00:01<00:07,  4.40it/s]
 18%|█▊        | 7/40 [00:01<00:07,  4.40it/s]
 20%|██        | 8/40 [00:01<00:07,  4.40it/s]
 22%|██▎       | 9/40 [00:02<00:07,  4.40it/s]
 25%|██▌       | 10/40 [00:02<00:06,  4.40it/s]
 28%|██▊       | 11/40 [00:02<00:06,  4.40it/s]
 30%|███       | 12/40 [00:02<00:06,  4.40it/s]
 32%|███▎      | 13/40 [00:02<00:06,  4.40it/s]
 35%|███▌      | 14/40 [00:03<00:05,  4.40it/s]
 38%|███▊      | 15/40 [00:03<00:05,  4.40it/s]
 40%|████      | 16/40 [00:03<00:05,  4.40it/s]
 42%|████▎     | 17/40 [00:03<00:05,  4.40it/s]
 45%|████▌     | 18/40 [00:04<00:04,  4.40it/s]
 48%|████▊     | 19/40 [00:04<00:04,  4.40it/s]
 50%|█████     | 20/40 [00:04<00:04,  4.40it/s]
 52%|█████▎    | 21/40 [00:04<00:04,  4.40it/s]
 55%|█████▌    | 22/40 [00:04<00:04,  4.40it/s]
 57%|█████▊    | 23/40 [00:05<00:03,  4.40it/s]
 60%|██████    | 24/40 [00:05<00:03,  4.39it/s]
 62%|██████▎   | 25/40 [00:05<00:03,  4.39it/s]
 65%|██████▌   | 26/40 [00:05<00:03,  4.39it/s]
 68%|██████▊   | 27/40 [00:06<00:02,  4.39it/s]
 70%|███████   | 28/40 [00:06<00:02,  4.39it/s]
 72%|███████▎  | 29/40 [00:06<00:02,  4.39it/s]
 75%|███████▌  | 30/40 [00:06<00:02,  4.39it/s]
 78%|███████▊  | 31/40 [00:07<00:02,  4.40it/s]
 80%|████████  | 32/40 [00:07<00:01,  4.40it/s]
 82%|████████▎ | 33/40 [00:07<00:01,  4.40it/s]
 85%|████████▌ | 34/40 [00:07<00:01,  4.40it/s]
 88%|████████▊ | 35/40 [00:07<00:01,  4.40it/s]
 90%|█████████ | 36/40 [00:08<00:00,  4.40it/s]
 92%|█████████▎| 37/40 [00:08<00:00,  4.40it/s]
 95%|█████████▌| 38/40 [00:08<00:00,  4.40it/s]
 98%|█████████▊| 39/40 [00:08<00:00,  4.40it/s]
### Phase 1 Decoding ###
100%|██████████| 40/40 [00:09<00:00,  4.40it/s]
100%|██████████| 40/40 [00:09<00:00,  4.30it/s]
### Phase 2 Denoising ###
  0%|          | 0/40 [00:00<?, ?it/s]
  2%|▎         | 1/40 [00:01<00:50,  1.29s/it]
  5%|▌         | 2/40 [00:02<00:48,  1.29s/it]
  8%|▊         | 3/40 [00:03<00:47,  1.29s/it]
 10%|█         | 4/40 [00:05<00:46,  1.29s/it]
 12%|█▎        | 5/40 [00:06<00:45,  1.29s/it]
 15%|█▌        | 6/40 [00:07<00:43,  1.29s/it]
 18%|█▊        | 7/40 [00:09<00:42,  1.29s/it]
 20%|██        | 8/40 [00:10<00:41,  1.29s/it]
 22%|██▎       | 9/40 [00:11<00:39,  1.29s/it]
 25%|██▌       | 10/40 [00:12<00:38,  1.29s/it]
 28%|██▊       | 11/40 [00:14<00:37,  1.29s/it]
 30%|███       | 12/40 [00:15<00:36,  1.29s/it]
 32%|███▎      | 13/40 [00:16<00:34,  1.29s/it]
 35%|███▌      | 14/40 [00:18<00:33,  1.29s/it]
 38%|███▊      | 15/40 [00:19<00:32,  1.29s/it]
 40%|████      | 16/40 [00:20<00:30,  1.29s/it]
 42%|████▎     | 17/40 [00:21<00:29,  1.29s/it]
 45%|████▌     | 18/40 [00:23<00:28,  1.29s/it]
 48%|████▊     | 19/40 [00:24<00:27,  1.29s/it]
 50%|█████     | 20/40 [00:25<00:25,  1.29s/it]
 52%|█████▎    | 21/40 [00:27<00:24,  1.29s/it]
 55%|█████▌    | 22/40 [00:28<00:23,  1.29s/it]
 57%|█████▊    | 23/40 [00:29<00:21,  1.29s/it]
 60%|██████    | 24/40 [00:30<00:20,  1.29s/it]
 62%|██████▎   | 25/40 [00:32<00:19,  1.29s/it]
 65%|██████▌   | 26/40 [00:33<00:18,  1.29s/it]
 68%|██████▊   | 27/40 [00:34<00:16,  1.29s/it]
 70%|███████   | 28/40 [00:36<00:15,  1.29s/it]
 72%|███████▎  | 29/40 [00:37<00:14,  1.29s/it]
 75%|███████▌  | 30/40 [00:38<00:12,  1.29s/it]
 78%|███████▊  | 31/40 [00:39<00:11,  1.29s/it]
 80%|████████  | 32/40 [00:41<00:10,  1.29s/it]
 82%|████████▎ | 33/40 [00:42<00:09,  1.29s/it]
 85%|████████▌ | 34/40 [00:43<00:07,  1.29s/it]
 88%|████████▊ | 35/40 [00:45<00:06,  1.29s/it]
 90%|█████████ | 36/40 [00:46<00:05,  1.29s/it]
 92%|█████████▎| 37/40 [00:47<00:03,  1.29s/it]
 95%|█████████▌| 38/40 [00:49<00:02,  1.29s/it]
 98%|█████████▊| 39/40 [00:50<00:01,  1.29s/it]
### Phase 2 Decoding ###
100%|██████████| 40/40 [00:51<00:00,  1.29s/it]
100%|██████████| 40/40 [00:52<00:00,  1.31s/it]