yuanxunlu/livespeechportraits:227c800d – Run with an API on Replicate

Version

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

yuanxunlu /livespeechportraits:227c800d

Playground API

Input

Video Player is loading.

Current Time 00:00:000

Duration 00:00:000

Loaded: 0%

Stream Type LIVE

Remaining Time 00:00:000

driving_audio

*file

driving audio, if the file is more than 20 seconds, only the first 20 seconds will be processed for video generation

talking_head

string

choose a talking head

Default: "May"

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

npx create-replicate --model=yuanxunlu/livespeechportraits

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

const output = await replicate.run(
  "yuanxunlu/livespeechportraits:227c800d5e1b6acda82ae57b7b34131fa1600fd43e74a5e62e2e958abe708cb2",
  {
    input: {
      talking_head: "May",
      driving_audio: "https://replicate.delivery/mgxm/0ce8702e-8f9b-4db9-bdaf-9be0526b54c1/00083.wav"
    }
  }
);

// To access the file URL:
console.log(output.url()); //=> "http://example.com"

// To write the file to disk:
fs.writeFile("my-image.png", 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 yuanxunlu/livespeechportraits using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "yuanxunlu/livespeechportraits:227c800d5e1b6acda82ae57b7b34131fa1600fd43e74a5e62e2e958abe708cb2",
    input={
        "talking_head": "May",
        "driving_audio": "https://replicate.delivery/mgxm/0ce8702e-8f9b-4db9-bdaf-9be0526b54c1/00083.wav"
    }
)
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 yuanxunlu/livespeechportraits 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": "227c800d5e1b6acda82ae57b7b34131fa1600fd43e74a5e62e2e958abe708cb2",
    "input": {
      "talking_head": "May",
      "driving_audio": "https://replicate.delivery/mgxm/0ce8702e-8f9b-4db9-bdaf-9be0526b54c1/00083.wav"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

{
  "completed_at": "2021-10-09T23:06:01.112771Z",
  "created_at": "2021-10-09T23:04:41.190914Z",
  "data_removed": false,
  "error": null,
  "id": "zypzj2weq5ayhjw4lzusakwjqu",
  "input": {
    "talking_head": "May",
    "driving_audio": "https://replicate.delivery/mgxm/0ce8702e-8f9b-4db9-bdaf-9be0526b54c1/00083.wav"
  },
  "logs": "opt:\nNamespace(A2L_GMM_ndim=75, APC_frame_history=0, APC_hidden_size=512, APC_residual=False, APC_rnn_layers=3, FPS=60, LSTM_dropout=0, LSTM_hidden_size=256, LSTM_layers=3, LSTM_output_size=80, LSTM_residual=False, LSTM_sequence_length=60, audioRF_future=0, audioRF_history=60, audio_encoder='APC', batch_size=32, checkpoints_dir='./checkpoints/', dataroot='default_path', dataset_mode='audiovisual', dataset_names='default_name', eval=False, feature_decoder='LSTM', feature_dtype='pts3d', frame_future=18, frame_jump_stride=4, gpu_ids='0', ispts_norm=1, load_epoch='500', loss='L2', max_dataset_size=inf, model='audio2feature', name='Audio2Feature', num_threads=0, only_mouth=1, phase='test', predict_length=1, sample_rate=16000, sequence_length=240, serial_batches=False, suffix='', task='Audio2Feature', time_frame_length=1, use_delta_pts=1, verbose=False)\n----------------- Options ---------------\n             A2L_GMM_ndim: 75                            \n        APC_frame_history: 0                             \n          APC_hidden_size: 512                           \n             APC_residual: False                         \n           APC_rnn_layers: 3                             \n                      FPS: 60                            \n             LSTM_dropout: 0                             \n         LSTM_hidden_size: 256                           \n              LSTM_layers: 3                             \n         LSTM_output_size: 80                            \n            LSTM_residual: False                         \n     LSTM_sequence_length: 60                            \n           audioRF_future: 0                             \n          audioRF_history: 60                            \n            audio_encoder: APC                           \n               batch_size: 32                            \n          checkpoints_dir: ./checkpoints/                \n                 dataroot: default_path                  \n             dataset_mode: audiovisual                   \n            dataset_names: default_name                  \n                     eval: False                         \n          feature_decoder: LSTM                          \n            feature_dtype: pts3d                         \n             frame_future: 18                            \n        frame_jump_stride: 4                             \n                  gpu_ids: 0                             \n                  isTrain: False                         \t[default: None]\n               ispts_norm: 1                             \n               load_epoch: 500                           \n                     loss: L2                            \n         max_dataset_size: inf                           \n                    model: audio2feature                 \n                     name: Audio2Feature                 \n              num_threads: 0                             \n               only_mouth: 1                             \n                    phase: test                          \n           predict_length: 1                             \n              sample_rate: 16000                         \n          sequence_length: 240                           \n           serial_batches: False                         \n                   suffix:                               \n                     task: Audio2Feature                 \n        time_frame_length: 1                             \n            use_delta_pts: 1                             \n                  verbose: False                         \n----------------- End -------------------\n----------------- Options ---------------\n          A2H_GMM_ncenter: 1                             \n             A2H_GMM_ndim: 12                            \n        A2H_GMM_sigma_min: 0.03                          \n         A2H_wavenet_cond: True                          \nA2H_wavenet_cond_channels: 512                           \nA2H_wavenet_dilation_channels: 128                           \nA2H_wavenet_input_channels: 12                            \n  A2H_wavenet_kernel_size: 2                             \nA2H_wavenet_residual_blocks: 2                             \nA2H_wavenet_residual_channels: 128                           \nA2H_wavenet_residual_layers: 7                             \nA2H_wavenet_skip_channels: 256                           \n     A2H_wavenet_use_bias: True                          \n        APC_frame_history: 60                            \n          APC_hidden_size: 512                           \n             APC_residual: False                         \n           APC_rnn_layers: 3                             \n                      FPS: 60                            \n           audioRF_future: 0                             \n          audioRF_history: 60                            \n            audio_encoder: APC                           \n            audio_windows: 2                             \naudiofeature_input_channels: 80                            \n               batch_size: 32                            \n          checkpoints_dir: ./checkpoints/                \n                 dataroot: path                          \n             dataset_mode: audiovisual                   \n            dataset_names: name                          \n                     eval: False                         \n          feature_decoder: WaveNet                       \n             frame_future: 15                            \n        frame_jump_stride: 1                             \n                  gpu_ids: 0                             \n                  isTrain: False                         \t[default: None]\n               load_epoch: 500                           \n                     loss: GMM                           \n         max_dataset_size: inf                           \n                    model: audio2headpose                \n                     name: Audio2Headpose                \n              num_threads: 0                             \n                    phase: test                          \n           predict_length: 5                             \n              sample_rate: 16000                         \n          sequence_length: 240                           \n           serial_batches: False                         \n                   suffix:                               \n                     task: Audio2Headpose                \n        time_frame_length: 1                             \n                  verbose: False                         \n----------------- End -------------------\n------------ Options -------------\nbatch_size: 1\ncheckpoints_dir: ./checkpoints/\ndataroot: ./data/\ndataset_mode: face\ndataset_names: ['name']\ndebug: False\ndisplay_id: 0\ndisplay_winsize: 512\nfineSize: 512\nfp16: 0\ngpu_ids: [0]\ninput_nc: 1\nisH5: 1\nisMask: 0\nisTrain: False\nloadSize: 512\nload_pretrain:\nlocal_rank: 0\nmax_dataset_size: inf\nmodel: feature2face\nn_blocks_E: 3\nn_downsample_E: 3\nn_downsample_G: 8\nname: TestRender\nngf: 64\nngf_E: 16\nno_flip: 1\nnum_threads: 0\noutput_nc: 3\nphase: test\nresize_or_crop: scaleWidth\nserial_batches: False\nsuffix: .jpg\ntask: Feature2Face\ntest_dataset_names: ['name']\ntf_log: True\nverbose: False\n-------------- End ----------------\n---------- Loading Model: APC-------------\n---------- Loading Model: Audio2Feature -------------\ninitialize network with normal\nmodel [Audio2FeatureModel] was created\nloading the model from ./data/May/checkpoints/Audio2Feature.pkl\n---------- Networks initialized -------------\n[Network Audio2Feature] Total number of parameters : 3.064 M\n-----------------------------------------------\n---------- Loading Model: Audio2Headpose -------------\ninitialize network with normal\nmodel [Audio2HeadposeModel] was created\nloading the model from ./data/May/checkpoints/Audio2Headpose.pkl\n---------- Networks initialized -------------\n[Network Audio2Headpose] Total number of parameters : 4.267 M\n-----------------------------------------------\n---------- Loading Model: Feature2Face -------------\ndataset [FaceDataset] was created\n---------- Generator networks initialized -------------\n-------------------------------------------------------\ninitialize network with normal\nmodel [Feature2FaceModel] was created\nloading the model from ./data/May/checkpoints/Feature2Face.pkl\n---------- Networks initialized -------------\n[Network Feature2Face_G] Total number of parameters : 121.790 M\n-----------------------------------------------\nProcessing audio: 00083 ...\n1. Computing APC features...\n2. Manifold projection...\n\nLLE projection:   0%|          | 0/1374 [00:00<?, ?it/s]\n\nLLE projection: 100%|##########| 1374/1374 [00:00<00:00, 17595.52it/s]\n3. Audio2Mouth inference...\n4. Headpose inference...\n\ngenerating headpose:   0%|          | 0/672 [00:00<?, ?it/s]\n\ngenerating headpose:   1%|1         | 8/672 [00:00<00:09, 73.20it/s]\n\ngenerating headpose:   2%|2         | 16/672 [00:00<00:08, 73.92it/s]\n\ngenerating headpose:   4%|3         | 24/672 [00:00<00:08, 73.88it/s]\n\ngenerating headpose:   5%|4         | 32/672 [00:00<00:08, 74.02it/s]\n\ngenerating headpose:   6%|5         | 40/672 [00:00<00:08, 74.01it/s]\n\ngenerating headpose:   7%|7         | 48/672 [00:00<00:08, 73.90it/s]\n\ngenerating headpose:   8%|8         | 56/672 [00:00<00:08, 73.33it/s]\n\ngenerating headpose:  10%|9         | 64/672 [00:00<00:08, 73.49it/s]\n\ngenerating headpose:  11%|#         | 72/672 [00:00<00:08, 73.37it/s]\n\ngenerating headpose:  12%|#1        | 80/672 [00:01<00:08, 73.92it/s]\n\ngenerating headpose:  13%|#3        | 88/672 [00:01<00:07, 73.44it/s]\n\ngenerating headpose:  14%|#4        | 96/672 [00:01<00:07, 73.51it/s]\n\ngenerating headpose:  15%|#5        | 104/672 [00:01<00:07, 73.95it/s]\n\ngenerating headpose:  17%|#6        | 112/672 [00:01<00:07, 73.98it/s]\n\ngenerating headpose:  18%|#7        | 120/672 [00:01<00:07, 73.46it/s]\n\ngenerating headpose:  19%|#9        | 128/672 [00:01<00:07, 73.73it/s]\n\ngenerating headpose:  20%|##        | 136/672 [00:01<00:07, 74.46it/s]\n\ngenerating headpose:  21%|##1       | 144/672 [00:01<00:07, 75.02it/s]\n\ngenerating headpose:  23%|##2       | 152/672 [00:02<00:06, 74.76it/s]\n\ngenerating headpose:  24%|##3       | 160/672 [00:02<00:07, 73.12it/s]\n\ngenerating headpose:  25%|##5       | 168/672 [00:02<00:06, 73.12it/s]\n\ngenerating headpose:  26%|##6       | 176/672 [00:02<00:06, 73.15it/s]\n\ngenerating headpose:  27%|##7       | 184/672 [00:02<00:06, 71.85it/s]\n\ngenerating headpose:  29%|##8       | 192/672 [00:02<00:06, 72.80it/s]\n\ngenerating headpose:  30%|##9       | 200/672 [00:02<00:06, 73.38it/s]\n\ngenerating headpose:  31%|###       | 208/672 [00:02<00:06, 73.16it/s]\n\ngenerating headpose:  32%|###2      | 216/672 [00:02<00:06, 73.38it/s]\n\ngenerating headpose:  33%|###3      | 224/672 [00:03<00:06, 73.75it/s]\n\ngenerating headpose:  35%|###4      | 232/672 [00:03<00:06, 72.12it/s]\n\ngenerating headpose:  36%|###5      | 240/672 [00:03<00:05, 72.37it/s]\n\ngenerating headpose:  37%|###6      | 248/672 [00:03<00:05, 72.92it/s]\n\ngenerating headpose:  38%|###8      | 256/672 [00:03<00:05, 73.69it/s]\n\ngenerating headpose:  39%|###9      | 264/672 [00:03<00:05, 74.28it/s]\n\ngenerating headpose:  40%|####      | 272/672 [00:03<00:05, 73.73it/s]\n\ngenerating headpose:  42%|####1     | 280/672 [00:03<00:05, 73.95it/s]\n\ngenerating headpose:  43%|####2     | 288/672 [00:03<00:05, 74.11it/s]\n\ngenerating headpose:  44%|####4     | 296/672 [00:04<00:05, 74.29it/s]\n\ngenerating headpose:  45%|####5     | 304/672 [00:04<00:05, 72.79it/s]\n\ngenerating headpose:  46%|####6     | 312/672 [00:04<00:04, 73.03it/s]\n\ngenerating headpose:  48%|####7     | 320/672 [00:04<00:04, 73.52it/s]\n\ngenerating headpose:  49%|####8     | 328/672 [00:04<00:04, 73.64it/s]\n\ngenerating headpose:  50%|#####     | 336/672 [00:04<00:04, 73.40it/s]\n\ngenerating headpose:  51%|#####1    | 344/672 [00:04<00:04, 73.26it/s]\n\ngenerating headpose:  52%|#####2    | 352/672 [00:04<00:04, 73.42it/s]\n\ngenerating headpose:  54%|#####3    | 360/672 [00:04<00:04, 71.14it/s]\n\ngenerating headpose:  55%|#####4    | 368/672 [00:05<00:04, 70.78it/s]\n\ngenerating headpose:  56%|#####5    | 376/672 [00:05<00:04, 71.56it/s]\n\ngenerating headpose:  57%|#####7    | 384/672 [00:05<00:04, 71.92it/s]\n\ngenerating headpose:  58%|#####8    | 392/672 [00:05<00:03, 72.47it/s]\n\ngenerating headpose:  60%|#####9    | 400/672 [00:05<00:03, 71.35it/s]\n\ngenerating headpose:  61%|######    | 408/672 [00:05<00:03, 70.53it/s]\n\ngenerating headpose:  62%|######1   | 416/672 [00:05<00:03, 71.45it/s]\n\ngenerating headpose:  63%|######3   | 424/672 [00:05<00:03, 71.68it/s]\n\ngenerating headpose:  64%|######4   | 432/672 [00:05<00:03, 71.88it/s]\n\ngenerating headpose:  65%|######5   | 440/672 [00:06<00:03, 72.87it/s]\n\ngenerating headpose:  67%|######6   | 448/672 [00:06<00:03, 73.01it/s]\n\ngenerating headpose:  68%|######7   | 456/672 [00:06<00:02, 73.27it/s]\n\ngenerating headpose:  69%|######9   | 464/672 [00:06<00:02, 73.61it/s]\n\ngenerating headpose:  70%|#######   | 472/672 [00:06<00:02, 74.00it/s]\n\ngenerating headpose:  71%|#######1  | 480/672 [00:06<00:02, 74.31it/s]\n\ngenerating headpose:  73%|#######2  | 488/672 [00:06<00:02, 73.34it/s]\n\ngenerating headpose:  74%|#######3  | 496/672 [00:06<00:02, 73.28it/s]\n\ngenerating headpose:  75%|#######5  | 504/672 [00:06<00:02, 73.82it/s]\n\ngenerating headpose:  76%|#######6  | 512/672 [00:06<00:02, 74.55it/s]\n\ngenerating headpose:  77%|#######7  | 520/672 [00:07<00:02, 74.23it/s]\n\ngenerating headpose:  79%|#######8  | 528/672 [00:07<00:01, 72.96it/s]\n\ngenerating headpose:  80%|#######9  | 536/672 [00:07<00:01, 73.79it/s]\n\ngenerating headpose:  81%|########  | 544/672 [00:07<00:01, 74.38it/s]\n\ngenerating headpose:  82%|########2 | 552/672 [00:07<00:01, 74.99it/s]\n\ngenerating headpose:  83%|########3 | 560/672 [00:07<00:01, 74.55it/s]\n\ngenerating headpose:  85%|########4 | 568/672 [00:07<00:01, 74.74it/s]\n\ngenerating headpose:  86%|########5 | 576/672 [00:07<00:01, 75.02it/s]\n\ngenerating headpose:  87%|########6 | 584/672 [00:07<00:01, 74.91it/s]\n\ngenerating headpose:  88%|########8 | 592/672 [00:08<00:01, 75.34it/s]\n\ngenerating headpose:  89%|########9 | 600/672 [00:08<00:00, 75.07it/s]\n\ngenerating headpose:  90%|######### | 608/672 [00:08<00:00, 75.32it/s]\n\ngenerating headpose:  92%|#########1| 616/672 [00:08<00:00, 75.68it/s]\n\ngenerating headpose:  93%|#########2| 624/672 [00:08<00:00, 75.92it/s]\n\ngenerating headpose:  94%|#########4| 632/672 [00:08<00:00, 75.91it/s]\n\ngenerating headpose:  95%|#########5| 640/672 [00:08<00:00, 74.65it/s]\n\ngenerating headpose:  96%|#########6| 648/672 [00:08<00:00, 74.72it/s]\n\ngenerating headpose:  98%|#########7| 656/672 [00:08<00:00, 74.53it/s]\n\ngenerating headpose:  99%|#########8| 664/672 [00:09<00:00, 74.95it/s]\n\ngenerating headpose: 100%|##########| 672/672 [00:09<00:00, 74.67it/s]\n\ngenerating headpose: 100%|##########| 672/672 [00:09<00:00, 73.60it/s]\n5. Post-processing...\n\n  0%|          | 0/672 [00:00<?, ?it/s]\n\n100%|##########| 672/672 [00:00<00:00, 19551.15it/s]\n6. Image2Image translation & Saving results...\n\nImage2Image translation inference:   0%|          | 0/672 [00:00<?, ?it/s]\n\nImage2Image translation inference:   0%|          | 1/672 [00:00<01:13,  9.10it/s]\n\nImage2Image translation inference:   0%|          | 2/672 [00:00<01:11,  9.37it/s]\n\nImage2Image translation inference:   1%|          | 4/672 [00:00<01:05, 10.17it/s]\n\nImage2Image translation inference:   1%|          | 6/672 [00:00<01:01, 10.77it/s]\n\nImage2Image translation inference:   1%|1         | 8/672 [00:00<00:59, 11.09it/s]\n\nImage2Image translation inference:   1%|1         | 10/672 [00:00<00:58, 11.27it/s]\n\nImage2Image translation inference:   2%|1         | 12/672 [00:01<00:58, 11.24it/s]\n\nImage2Image translation inference:   2%|2         | 14/672 [00:01<00:58, 11.29it/s]\n\nImage2Image translation inference:   2%|2         | 16/672 [00:01<00:57, 11.34it/s]\n\nImage2Image translation inference:   3%|2         | 18/672 [00:01<00:57, 11.39it/s]\n\nImage2Image translation inference:   3%|2         | 20/672 [00:01<00:57, 11.40it/s]\n\nImage2Image translation inference:   3%|3         | 22/672 [00:01<00:57, 11.38it/s]\n\nImage2Image translation inference:   4%|3         | 24/672 [00:02<00:56, 11.41it/s]\n\nImage2Image translation inference:   4%|3         | 26/672 [00:02<00:56, 11.44it/s]\n\nImage2Image translation inference:   4%|4         | 28/672 [00:02<00:56, 11.44it/s]\n\nImage2Image translation inference:   4%|4         | 30/672 [00:02<00:55, 11.48it/s]\n\nImage2Image translation inference:   5%|4         | 32/672 [00:02<00:55, 11.43it/s]\n\nImage2Image translation inference:   5%|5         | 34/672 [00:03<00:55, 11.42it/s]\n\nImage2Image translation inference:   5%|5         | 36/672 [00:03<00:55, 11.45it/s]\n\nImage2Image translation inference:   6%|5         | 38/672 [00:03<00:55, 11.44it/s]\n\nImage2Image translation inference:   6%|5         | 40/672 [00:03<00:55, 11.41it/s]\n\nImage2Image translation inference:   6%|6         | 42/672 [00:03<00:55, 11.45it/s]\n\nImage2Image translation inference:   7%|6         | 44/672 [00:03<00:54, 11.45it/s]\n\nImage2Image translation inference:   7%|6         | 46/672 [00:04<00:54, 11.45it/s]\n\nImage2Image translation inference:   7%|7         | 48/672 [00:04<00:54, 11.43it/s]\n\nImage2Image translation inference:   7%|7         | 50/672 [00:04<00:54, 11.42it/s]\n\nImage2Image translation inference:   8%|7         | 52/672 [00:04<00:54, 11.44it/s]\n\nImage2Image translation inference:   8%|8         | 54/672 [00:04<00:54, 11.44it/s]\n\nImage2Image translation inference:   8%|8         | 56/672 [00:04<00:54, 11.38it/s]\n\nImage2Image translation inference:   9%|8         | 58/672 [00:05<00:53, 11.39it/s]\n\nImage2Image translation inference:   9%|8         | 60/672 [00:05<00:53, 11.41it/s]\n\nImage2Image translation inference:   9%|9         | 62/672 [00:05<00:53, 11.42it/s]\n\nImage2Image translation inference:  10%|9         | 64/672 [00:05<00:53, 11.44it/s]\n\nImage2Image translation inference:  10%|9         | 66/672 [00:05<00:52, 11.44it/s]\n\nImage2Image translation inference:  10%|#         | 68/672 [00:05<00:52, 11.47it/s]\n\nImage2Image translation inference:  10%|#         | 70/672 [00:06<00:52, 11.49it/s]\n\nImage2Image translation inference:  11%|#         | 72/672 [00:06<00:52, 11.41it/s]\n\nImage2Image translation inference:  11%|#1        | 74/672 [00:06<00:52, 11.42it/s]\n\nImage2Image translation inference:  11%|#1        | 76/672 [00:06<00:52, 11.41it/s]\n\nImage2Image translation inference:  12%|#1        | 78/672 [00:06<00:52, 11.41it/s]\n\nImage2Image translation inference:  12%|#1        | 80/672 [00:07<00:51, 11.41it/s]\n\nImage2Image translation inference:  12%|#2        | 82/672 [00:07<00:51, 11.41it/s]\n\nImage2Image translation inference:  12%|#2        | 84/672 [00:07<00:51, 11.45it/s]\n\nImage2Image translation inference:  13%|#2        | 86/672 [00:07<00:51, 11.42it/s]\n\nImage2Image translation inference:  13%|#3        | 88/672 [00:07<00:51, 11.45it/s]\n\nImage2Image translation inference:  13%|#3        | 90/672 [00:07<00:50, 11.45it/s]\n\nImage2Image translation inference:  14%|#3        | 92/672 [00:08<00:50, 11.46it/s]\n\nImage2Image translation inference:  14%|#3        | 94/672 [00:08<00:50, 11.45it/s]\n\nImage2Image translation inference:  14%|#4        | 96/672 [00:08<00:50, 11.41it/s]\n\nImage2Image translation inference:  15%|#4        | 98/672 [00:08<00:50, 11.42it/s]\n\nImage2Image translation inference:  15%|#4        | 100/672 [00:08<00:50, 11.43it/s]\n\nImage2Image translation inference:  15%|#5        | 102/672 [00:08<00:49, 11.40it/s]\n\nImage2Image translation inference:  15%|#5        | 104/672 [00:09<00:49, 11.38it/s]\n\nImage2Image translation inference:  16%|#5        | 106/672 [00:09<00:49, 11.41it/s]\n\nImage2Image translation inference:  16%|#6        | 108/672 [00:09<00:49, 11.41it/s]\n\nImage2Image translation inference:  16%|#6        | 110/672 [00:09<00:49, 11.45it/s]\n\nImage2Image translation inference:  17%|#6        | 112/672 [00:09<00:49, 11.43it/s]\n\nImage2Image translation inference:  17%|#6        | 114/672 [00:10<00:48, 11.44it/s]\n\nImage2Image translation inference:  17%|#7        | 116/672 [00:10<00:48, 11.41it/s]\n\nImage2Image translation inference:  18%|#7        | 118/672 [00:10<00:48, 11.32it/s]\n\nImage2Image translation inference:  18%|#7        | 120/672 [00:10<00:48, 11.29it/s]\n\nImage2Image translation inference:  18%|#8        | 122/672 [00:10<00:48, 11.28it/s]\n\nImage2Image translation inference:  18%|#8        | 124/672 [00:10<00:48, 11.30it/s]\n\nImage2Image translation inference:  19%|#8        | 126/672 [00:11<00:48, 11.31it/s]\n\nImage2Image translation inference:  19%|#9        | 128/672 [00:11<00:47, 11.35it/s]\n\nImage2Image translation inference:  19%|#9        | 130/672 [00:11<00:47, 11.34it/s]\n\nImage2Image translation inference:  20%|#9        | 132/672 [00:11<00:47, 11.38it/s]\n\nImage2Image translation inference:  20%|#9        | 134/672 [00:11<00:47, 11.39it/s]\n\nImage2Image translation inference:  20%|##        | 136/672 [00:11<00:47, 11.40it/s]\n\nImage2Image translation inference:  21%|##        | 138/672 [00:12<00:46, 11.40it/s]\n\nImage2Image translation inference:  21%|##        | 140/672 [00:12<00:46, 11.38it/s]\n\nImage2Image translation inference:  21%|##1       | 142/672 [00:12<00:46, 11.35it/s]\n\nImage2Image translation inference:  21%|##1       | 144/672 [00:12<00:46, 11.35it/s]\n\nImage2Image translation inference:  22%|##1       | 146/672 [00:12<00:46, 11.37it/s]\n\nImage2Image translation inference:  22%|##2       | 148/672 [00:13<00:46, 11.35it/s]\n\nImage2Image translation inference:  22%|##2       | 150/672 [00:13<00:46, 11.34it/s]\n\nImage2Image translation inference:  23%|##2       | 152/672 [00:13<00:45, 11.39it/s]\n\nImage2Image translation inference:  23%|##2       | 154/672 [00:13<00:45, 11.36it/s]\n\nImage2Image translation inference:  23%|##3       | 156/672 [00:13<00:45, 11.37it/s]\n\nImage2Image translation inference:  24%|##3       | 158/672 [00:13<00:45, 11.31it/s]\n\nImage2Image translation inference:  24%|##3       | 160/672 [00:14<00:45, 11.32it/s]\n\nImage2Image translation inference:  24%|##4       | 162/672 [00:14<00:45, 11.31it/s]\n\nImage2Image translation inference:  24%|##4       | 164/672 [00:14<00:44, 11.34it/s]\n\nImage2Image translation inference:  25%|##4       | 166/672 [00:14<00:44, 11.34it/s]\n\nImage2Image translation inference:  25%|##5       | 168/672 [00:14<00:44, 11.32it/s]\n\nImage2Image translation inference:  25%|##5       | 170/672 [00:14<00:44, 11.33it/s]\n\nImage2Image translation inference:  26%|##5       | 172/672 [00:15<00:44, 11.33it/s]\n\nImage2Image translation inference:  26%|##5       | 174/672 [00:15<00:43, 11.34it/s]\n\nImage2Image translation inference:  26%|##6       | 176/672 [00:15<00:43, 11.34it/s]\n\nImage2Image translation inference:  26%|##6       | 178/672 [00:15<00:43, 11.35it/s]\n\nImage2Image translation inference:  27%|##6       | 180/672 [00:15<00:43, 11.36it/s]\n\nImage2Image translation inference:  27%|##7       | 182/672 [00:16<00:43, 11.35it/s]\n\nImage2Image translation inference:  27%|##7       | 184/672 [00:16<00:42, 11.36it/s]\n\nImage2Image translation inference:  28%|##7       | 186/672 [00:16<00:42, 11.32it/s]\n\nImage2Image translation inference:  28%|##7       | 188/672 [00:16<00:42, 11.33it/s]\n\nImage2Image translation inference:  28%|##8       | 190/672 [00:16<00:42, 11.29it/s]\n\nImage2Image translation inference:  29%|##8       | 192/672 [00:16<00:42, 11.26it/s]\n\nImage2Image translation inference:  29%|##8       | 194/672 [00:17<00:42, 11.28it/s]\n\nImage2Image translation inference:  29%|##9       | 196/672 [00:17<00:42, 11.32it/s]\n\nImage2Image translation inference:  29%|##9       | 198/672 [00:17<00:41, 11.32it/s]\n\nImage2Image translation inference:  30%|##9       | 200/672 [00:17<00:41, 11.31it/s]\n\nImage2Image translation inference:  30%|###       | 202/672 [00:17<00:41, 11.33it/s]\n\nImage2Image translation inference:  30%|###       | 204/672 [00:17<00:41, 11.34it/s]\n\nImage2Image translation inference:  31%|###       | 206/672 [00:18<00:41, 11.33it/s]\n\nImage2Image translation inference:  31%|###       | 208/672 [00:18<00:41, 11.31it/s]\n\nImage2Image translation inference:  31%|###1      | 210/672 [00:18<00:40, 11.29it/s]\n\nImage2Image translation inference:  32%|###1      | 212/672 [00:18<00:40, 11.30it/s]\n\nImage2Image translation inference:  32%|###1      | 214/672 [00:18<00:40, 11.31it/s]\n\nImage2Image translation inference:  32%|###2      | 216/672 [00:19<00:40, 11.31it/s]\n\nImage2Image translation inference:  32%|###2      | 218/672 [00:19<00:40, 11.32it/s]\n\nImage2Image translation inference:  33%|###2      | 220/672 [00:19<00:39, 11.34it/s]\n\nImage2Image translation inference:  33%|###3      | 222/672 [00:19<00:39, 11.33it/s]\n\nImage2Image translation inference:  33%|###3      | 224/672 [00:19<00:39, 11.29it/s]\n\nImage2Image translation inference:  34%|###3      | 226/672 [00:19<00:39, 11.31it/s]\n\nImage2Image translation inference:  34%|###3      | 228/672 [00:20<00:39, 11.32it/s]\n\nImage2Image translation inference:  34%|###4      | 230/672 [00:20<00:39, 11.33it/s]\n\nImage2Image translation inference:  35%|###4      | 232/672 [00:20<00:38, 11.32it/s]\n\nImage2Image translation inference:  35%|###4      | 234/672 [00:20<00:38, 11.31it/s]\n\nImage2Image translation inference:  35%|###5      | 236/672 [00:20<00:38, 11.30it/s]\n\nImage2Image translation inference:  35%|###5      | 238/672 [00:20<00:38, 11.24it/s]\n\nImage2Image translation inference:  36%|###5      | 240/672 [00:21<00:38, 11.26it/s]\n\nImage2Image translation inference:  36%|###6      | 242/672 [00:21<00:38, 11.28it/s]\n\nImage2Image translation inference:  36%|###6      | 244/672 [00:21<00:37, 11.28it/s]\n\nImage2Image translation inference:  37%|###6      | 246/672 [00:21<00:37, 11.27it/s]\n\nImage2Image translation inference:  37%|###6      | 248/672 [00:21<00:37, 11.26it/s]\n\nImage2Image translation inference:  37%|###7      | 250/672 [00:22<00:37, 11.28it/s]\n\nImage2Image translation inference:  38%|###7      | 252/672 [00:22<00:37, 11.32it/s]\n\nImage2Image translation inference:  38%|###7      | 254/672 [00:22<00:36, 11.31it/s]\n\nImage2Image translation inference:  38%|###8      | 256/672 [00:22<00:36, 11.33it/s]\n\nImage2Image translation inference:  38%|###8      | 258/672 [00:22<00:36, 11.33it/s]\n\nImage2Image translation inference:  39%|###8      | 260/672 [00:22<00:36, 11.27it/s]\n\nImage2Image translation inference:  39%|###8      | 262/672 [00:23<00:36, 11.21it/s]\n\nImage2Image translation inference:  39%|###9      | 264/672 [00:23<00:36, 11.14it/s]\n\nImage2Image translation inference:  40%|###9      | 266/672 [00:23<00:36, 11.18it/s]\n\nImage2Image translation inference:  40%|###9      | 268/672 [00:23<00:36, 11.20it/s]\n\nImage2Image translation inference:  40%|####      | 270/672 [00:23<00:35, 11.19it/s]\n\nImage2Image translation inference:  40%|####      | 272/672 [00:23<00:35, 11.22it/s]\n\nImage2Image translation inference:  41%|####      | 274/672 [00:24<00:35, 11.27it/s]\n\nImage2Image translation inference:  41%|####1     | 276/672 [00:24<00:35, 11.28it/s]\n\nImage2Image translation inference:  41%|####1     | 278/672 [00:24<00:35, 11.24it/s]\n\nImage2Image translation inference:  42%|####1     | 280/672 [00:24<00:34, 11.24it/s]\n\nImage2Image translation inference:  42%|####1     | 282/672 [00:24<00:34, 11.24it/s]\n\nImage2Image translation inference:  42%|####2     | 284/672 [00:25<00:34, 11.27it/s]\n\nImage2Image translation inference:  43%|####2     | 286/672 [00:25<00:34, 11.27it/s]\n\nImage2Image translation inference:  43%|####2     | 288/672 [00:25<00:34, 11.26it/s]\n\nImage2Image translation inference:  43%|####3     | 290/672 [00:25<00:33, 11.26it/s]\n\nImage2Image translation inference:  43%|####3     | 292/672 [00:25<00:33, 11.21it/s]\n\nImage2Image translation inference:  44%|####3     | 294/672 [00:25<00:33, 11.22it/s]\n\nImage2Image translation inference:  44%|####4     | 296/672 [00:26<00:33, 11.23it/s]\n\nImage2Image translation inference:  44%|####4     | 298/672 [00:26<00:33, 11.25it/s]\n\nImage2Image translation inference:  45%|####4     | 300/672 [00:26<00:33, 11.27it/s]\n\nImage2Image translation inference:  45%|####4     | 302/672 [00:26<00:32, 11.23it/s]\n\nImage2Image translation inference:  45%|####5     | 304/672 [00:26<00:32, 11.19it/s]\n\nImage2Image translation inference:  46%|####5     | 306/672 [00:27<00:32, 11.21it/s]\n\nImage2Image translation inference:  46%|####5     | 308/672 [00:27<00:32, 11.22it/s]\n\nImage2Image translation inference:  46%|####6     | 310/672 [00:27<00:32, 11.24it/s]\n\nImage2Image translation inference:  46%|####6     | 312/672 [00:27<00:31, 11.25it/s]\n\nImage2Image translation inference:  47%|####6     | 314/672 [00:27<00:31, 11.25it/s]\n\nImage2Image translation inference:  47%|####7     | 316/672 [00:27<00:31, 11.21it/s]\n\nImage2Image translation inference:  47%|####7     | 318/672 [00:28<00:31, 11.17it/s]\n\nImage2Image translation inference:  48%|####7     | 320/672 [00:28<00:31, 11.17it/s]\n\nImage2Image translation inference:  48%|####7     | 322/672 [00:28<00:31, 11.19it/s]\n\nImage2Image translation inference:  48%|####8     | 324/672 [00:28<00:31, 11.22it/s]\n\nImage2Image translation inference:  49%|####8     | 326/672 [00:28<00:30, 11.20it/s]\n\nImage2Image translation inference:  49%|####8     | 328/672 [00:28<00:30, 11.18it/s]\n\nImage2Image translation inference:  49%|####9     | 330/672 [00:29<00:30, 11.21it/s]\n\nImage2Image translation inference:  49%|####9     | 332/672 [00:29<00:30, 11.09it/s]\n\nImage2Image translation inference:  50%|####9     | 334/672 [00:29<00:30, 11.14it/s]\n\nImage2Image translation inference:  50%|#####     | 336/672 [00:29<00:30, 11.18it/s]\n\nImage2Image translation inference:  50%|#####     | 338/672 [00:29<00:29, 11.19it/s]\n\nImage2Image translation inference:  51%|#####     | 340/672 [00:30<00:29, 11.19it/s]\n\nImage2Image translation inference:  51%|#####     | 342/672 [00:30<00:29, 11.18it/s]\n\nImage2Image translation inference:  51%|#####1    | 344/672 [00:30<00:29, 11.16it/s]\n\nImage2Image translation inference:  51%|#####1    | 346/672 [00:30<00:29, 11.18it/s]\n\nImage2Image translation inference:  52%|#####1    | 348/672 [00:30<00:29, 11.16it/s]\n\nImage2Image translation inference:  52%|#####2    | 350/672 [00:30<00:28, 11.18it/s]\n\nImage2Image translation inference:  52%|#####2    | 352/672 [00:31<00:28, 11.20it/s]\n\nImage2Image translation inference:  53%|#####2    | 354/672 [00:31<00:28, 11.16it/s]\n\nImage2Image translation inference:  53%|#####2    | 356/672 [00:31<00:28, 11.15it/s]\n\nImage2Image translation inference:  53%|#####3    | 358/672 [00:31<00:28, 11.16it/s]\n\nImage2Image translation inference:  54%|#####3    | 360/672 [00:31<00:27, 11.15it/s]\n\nImage2Image translation inference:  54%|#####3    | 362/672 [00:32<00:27, 11.14it/s]\n\nImage2Image translation inference:  54%|#####4    | 364/672 [00:32<00:27, 11.14it/s]\n\nImage2Image translation inference:  54%|#####4    | 366/672 [00:32<00:27, 11.14it/s]\n\nImage2Image translation inference:  55%|#####4    | 368/672 [00:32<00:27, 11.17it/s]\n\nImage2Image translation inference:  55%|#####5    | 370/672 [00:32<00:27, 11.19it/s]\n\nImage2Image translation inference:  55%|#####5    | 372/672 [00:32<00:26, 11.16it/s]\n\nImage2Image translation inference:  56%|#####5    | 374/672 [00:33<00:26, 11.16it/s]\n\nImage2Image translation inference:  56%|#####5    | 376/672 [00:33<00:26, 11.17it/s]\n\nImage2Image translation inference:  56%|#####6    | 378/672 [00:33<00:26, 11.19it/s]\n\nImage2Image translation inference:  57%|#####6    | 380/672 [00:33<00:26, 11.19it/s]\n\nImage2Image translation inference:  57%|#####6    | 382/672 [00:33<00:25, 11.19it/s]\n\nImage2Image translation inference:  57%|#####7    | 384/672 [00:33<00:25, 11.18it/s]\n\nImage2Image translation inference:  57%|#####7    | 386/672 [00:34<00:25, 11.14it/s]\n\nImage2Image translation inference:  58%|#####7    | 388/672 [00:34<00:25, 11.17it/s]\n\nImage2Image translation inference:  58%|#####8    | 390/672 [00:34<00:25, 11.17it/s]\n\nImage2Image translation inference:  58%|#####8    | 392/672 [00:34<00:25, 11.19it/s]\n\nImage2Image translation inference:  59%|#####8    | 394/672 [00:34<00:24, 11.15it/s]\n\nImage2Image translation inference:  59%|#####8    | 396/672 [00:35<00:24, 11.17it/s]\n\nImage2Image translation inference:  59%|#####9    | 398/672 [00:35<00:24, 11.09it/s]\n\nImage2Image translation inference:  60%|#####9    | 400/672 [00:35<00:24, 11.11it/s]\n\nImage2Image translation inference:  60%|#####9    | 402/672 [00:35<00:24, 11.14it/s]\n\nImage2Image translation inference:  60%|######    | 404/672 [00:35<00:24, 11.16it/s]\n\nImage2Image translation inference:  60%|######    | 406/672 [00:35<00:23, 11.21it/s]\n\nImage2Image translation inference:  61%|######    | 408/672 [00:36<00:23, 11.19it/s]\n\nImage2Image translation inference:  61%|######1   | 410/672 [00:36<00:23, 11.20it/s]\n\nImage2Image translation inference:  61%|######1   | 412/672 [00:36<00:23, 11.17it/s]\n\nImage2Image translation inference:  62%|######1   | 414/672 [00:36<00:23, 11.13it/s]\n\nImage2Image translation inference:  62%|######1   | 416/672 [00:36<00:22, 11.13it/s]\n\nImage2Image translation inference:  62%|######2   | 418/672 [00:37<00:22, 11.12it/s]\n\nImage2Image translation inference:  62%|######2   | 420/672 [00:37<00:22, 11.14it/s]\n\nImage2Image translation inference:  63%|######2   | 422/672 [00:37<00:22, 11.13it/s]\n\nImage2Image translation inference:  63%|######3   | 424/672 [00:37<00:22, 11.17it/s]\n\nImage2Image translation inference:  63%|######3   | 426/672 [00:37<00:21, 11.20it/s]\n\nImage2Image translation inference:  64%|######3   | 428/672 [00:37<00:21, 11.20it/s]\n\nImage2Image translation inference:  64%|######3   | 430/672 [00:38<00:21, 11.19it/s]\n\nImage2Image translation inference:  64%|######4   | 432/672 [00:38<00:21, 11.15it/s]\n\nImage2Image translation inference:  65%|######4   | 434/672 [00:38<00:21, 11.16it/s]\n\nImage2Image translation inference:  65%|######4   | 436/672 [00:38<00:21, 11.18it/s]\n\nImage2Image translation inference:  65%|######5   | 438/672 [00:38<00:20, 11.20it/s]\n\nImage2Image translation inference:  65%|######5   | 440/672 [00:39<00:20, 11.19it/s]\n\nImage2Image translation inference:  66%|######5   | 442/672 [00:39<00:20, 11.21it/s]\n\nImage2Image translation inference:  66%|######6   | 444/672 [00:39<00:20, 11.18it/s]\n\nImage2Image translation inference:  66%|######6   | 446/672 [00:39<00:20, 11.22it/s]\n\nImage2Image translation inference:  67%|######6   | 448/672 [00:39<00:19, 11.23it/s]\n\nImage2Image translation inference:  67%|######6   | 450/672 [00:39<00:19, 11.23it/s]\n\nImage2Image translation inference:  67%|######7   | 452/672 [00:40<00:19, 11.09it/s]\n\nImage2Image translation inference:  68%|######7   | 454/672 [00:40<00:19, 11.14it/s]\n\nImage2Image translation inference:  68%|######7   | 456/672 [00:40<00:19, 11.18it/s]\n\nImage2Image translation inference:  68%|######8   | 458/672 [00:40<00:19, 11.18it/s]\n\nImage2Image translation inference:  68%|######8   | 460/672 [00:40<00:19, 11.14it/s]\n\nImage2Image translation inference:  69%|######8   | 462/672 [00:40<00:18, 11.12it/s]\n\nImage2Image translation inference:  69%|######9   | 464/672 [00:41<00:18, 11.16it/s]\n\nImage2Image translation inference:  69%|######9   | 466/672 [00:41<00:18, 11.18it/s]\n\nImage2Image translation inference:  70%|######9   | 468/672 [00:41<00:18, 11.19it/s]\n\nImage2Image translation inference:  70%|######9   | 470/672 [00:41<00:18, 11.22it/s]\n\nImage2Image translation inference:  70%|#######   | 472/672 [00:41<00:17, 11.27it/s]\n\nImage2Image translation inference:  71%|#######   | 474/672 [00:42<00:17, 11.22it/s]\n\nImage2Image translation inference:  71%|#######   | 476/672 [00:42<00:17, 11.22it/s]\n\nImage2Image translation inference:  71%|#######1  | 478/672 [00:42<00:17, 11.21it/s]\n\nImage2Image translation inference:  71%|#######1  | 480/672 [00:42<00:17, 11.21it/s]\n\nImage2Image translation inference:  72%|#######1  | 482/672 [00:42<00:16, 11.21it/s]\n\nImage2Image translation inference:  72%|#######2  | 484/672 [00:42<00:16, 11.20it/s]\n\nImage2Image translation inference:  72%|#######2  | 486/672 [00:43<00:16, 11.19it/s]\n\nImage2Image translation inference:  73%|#######2  | 488/672 [00:43<00:17, 10.79it/s]\n\nImage2Image translation inference:  73%|#######2  | 490/672 [00:43<00:16, 10.90it/s]\n\nImage2Image translation inference:  73%|#######3  | 492/672 [00:43<00:16, 10.96it/s]\n\nImage2Image translation inference:  74%|#######3  | 494/672 [00:43<00:16, 10.98it/s]\n\nImage2Image translation inference:  74%|#######3  | 496/672 [00:44<00:15, 11.05it/s]\n\nImage2Image translation inference:  74%|#######4  | 498/672 [00:44<00:15, 11.11it/s]\n\nImage2Image translation inference:  74%|#######4  | 500/672 [00:44<00:15, 11.12it/s]\n\nImage2Image translation inference:  75%|#######4  | 502/672 [00:44<00:15, 11.14it/s]\n\nImage2Image translation inference:  75%|#######5  | 504/672 [00:44<00:15, 11.15it/s]\n\nImage2Image translation inference:  75%|#######5  | 506/672 [00:44<00:14, 11.12it/s]\n\nImage2Image translation inference:  76%|#######5  | 508/672 [00:45<00:14, 11.14it/s]\n\nImage2Image translation inference:  76%|#######5  | 510/672 [00:45<00:14, 11.14it/s]\n\nImage2Image translation inference:  76%|#######6  | 512/672 [00:45<00:14, 11.11it/s]\n\nImage2Image translation inference:  76%|#######6  | 514/672 [00:45<00:14, 11.15it/s]\n\nImage2Image translation inference:  77%|#######6  | 516/672 [00:45<00:13, 11.14it/s]\n\nImage2Image translation inference:  77%|#######7  | 518/672 [00:46<00:13, 11.16it/s]\n\nImage2Image translation inference:  77%|#######7  | 520/672 [00:46<00:13, 11.19it/s]\n\nImage2Image translation inference:  78%|#######7  | 522/672 [00:46<00:13, 11.20it/s]\n\nImage2Image translation inference:  78%|#######7  | 524/672 [00:46<00:13, 11.20it/s]\n\nImage2Image translation inference:  78%|#######8  | 526/672 [00:46<00:13, 11.18it/s]\n\nImage2Image translation inference:  79%|#######8  | 528/672 [00:46<00:12, 11.21it/s]\n\nImage2Image translation inference:  79%|#######8  | 530/672 [00:47<00:12, 11.19it/s]\n\nImage2Image translation inference:  79%|#######9  | 532/672 [00:47<00:12, 11.19it/s]\n\nImage2Image translation inference:  79%|#######9  | 534/672 [00:47<00:12, 11.21it/s]\n\nImage2Image translation inference:  80%|#######9  | 536/672 [00:47<00:12, 11.23it/s]\n\nImage2Image translation inference:  80%|########  | 538/672 [00:47<00:11, 11.24it/s]\n\nImage2Image translation inference:  80%|########  | 540/672 [00:47<00:11, 11.19it/s]\n\nImage2Image translation inference:  81%|########  | 542/672 [00:48<00:11, 11.10it/s]\n\nImage2Image translation inference:  81%|########  | 544/672 [00:48<00:11, 11.14it/s]\n\nImage2Image translation inference:  81%|########1 | 546/672 [00:48<00:11, 11.13it/s]\n\nImage2Image translation inference:  82%|########1 | 548/672 [00:48<00:11, 11.15it/s]\n\nImage2Image translation inference:  82%|########1 | 550/672 [00:48<00:10, 11.21it/s]\n\nImage2Image translation inference:  82%|########2 | 552/672 [00:49<00:10, 11.21it/s]\n\nImage2Image translation inference:  82%|########2 | 554/672 [00:49<00:10, 11.23it/s]\n\nImage2Image translation inference:  83%|########2 | 556/672 [00:49<00:10, 11.23it/s]\n\nImage2Image translation inference:  83%|########3 | 558/672 [00:49<00:10, 11.27it/s]\n\nImage2Image translation inference:  83%|########3 | 560/672 [00:49<00:09, 11.26it/s]\n\nImage2Image translation inference:  84%|########3 | 562/672 [00:49<00:09, 11.27it/s]\n\nImage2Image translation inference:  84%|########3 | 564/672 [00:50<00:09, 11.26it/s]\n\nImage2Image translation inference:  84%|########4 | 566/672 [00:50<00:09, 11.26it/s]\n\nImage2Image translation inference:  85%|########4 | 568/672 [00:50<00:09, 11.28it/s]\n\nImage2Image translation inference:  85%|########4 | 570/672 [00:50<00:09, 11.29it/s]\n\nImage2Image translation inference:  85%|########5 | 572/672 [00:50<00:08, 11.26it/s]\n\nImage2Image translation inference:  85%|########5 | 574/672 [00:51<00:08, 11.26it/s]\n\nImage2Image translation inference:  86%|########5 | 576/672 [00:51<00:08, 11.24it/s]\n\nImage2Image translation inference:  86%|########6 | 578/672 [00:51<00:08, 11.00it/s]\n\nImage2Image translation inference:  86%|########6 | 580/672 [00:51<00:08, 11.09it/s]\n\nImage2Image translation inference:  87%|########6 | 582/672 [00:51<00:08, 11.16it/s]\n\nImage2Image translation inference:  87%|########6 | 584/672 [00:51<00:07, 11.21it/s]\n\nImage2Image translation inference:  87%|########7 | 586/672 [00:52<00:07, 11.25it/s]\n\nImage2Image translation inference:  88%|########7 | 588/672 [00:52<00:07, 11.24it/s]\n\nImage2Image translation inference:  88%|########7 | 590/672 [00:52<00:07, 11.24it/s]\n\nImage2Image translation inference:  88%|########8 | 592/672 [00:52<00:07, 11.24it/s]\n\nImage2Image translation inference:  88%|########8 | 594/672 [00:52<00:06, 11.25it/s]\n\nImage2Image translation inference:  89%|########8 | 596/672 [00:52<00:06, 11.24it/s]\n\nImage2Image translation inference:  89%|########8 | 598/672 [00:53<00:06, 11.24it/s]\n\nImage2Image translation inference:  89%|########9 | 600/672 [00:53<00:06, 11.24it/s]\n\nImage2Image translation inference:  90%|########9 | 602/672 [00:53<00:06, 11.25it/s]\n\nImage2Image translation inference:  90%|########9 | 604/672 [00:53<00:06, 11.21it/s]\n\nImage2Image translation inference:  90%|######### | 606/672 [00:53<00:05, 11.20it/s]\n\nImage2Image translation inference:  90%|######### | 608/672 [00:54<00:05, 11.24it/s]\n\nImage2Image translation inference:  91%|######### | 610/672 [00:54<00:05, 11.25it/s]\n\nImage2Image translation inference:  91%|#########1| 612/672 [00:54<00:05, 11.27it/s]\n\nImage2Image translation inference:  91%|#########1| 614/672 [00:54<00:05, 11.24it/s]\n\nImage2Image translation inference:  92%|#########1| 616/672 [00:54<00:04, 11.25it/s]\n\nImage2Image translation inference:  92%|#########1| 618/672 [00:54<00:04, 11.24it/s]\n\nImage2Image translation inference:  92%|#########2| 620/672 [00:55<00:04, 11.23it/s]\n\nImage2Image translation inference:  93%|#########2| 622/672 [00:55<00:04, 11.22it/s]\n\nImage2Image translation inference:  93%|#########2| 624/672 [00:55<00:04, 11.20it/s]\n\nImage2Image translation inference:  93%|#########3| 626/672 [00:55<00:04, 11.22it/s]\n\nImage2Image translation inference:  93%|#########3| 628/672 [00:55<00:03, 11.19it/s]\n\nImage2Image translation inference:  94%|#########3| 630/672 [00:56<00:03, 11.19it/s]\n\nImage2Image translation inference:  94%|#########4| 632/672 [00:56<00:03, 11.23it/s]\n\nImage2Image translation inference:  94%|#########4| 634/672 [00:56<00:03, 11.25it/s]\n\nImage2Image translation inference:  95%|#########4| 636/672 [00:56<00:03, 11.23it/s]\n\nImage2Image translation inference:  95%|#########4| 638/672 [00:56<00:03, 11.23it/s]\n\nImage2Image translation inference:  95%|#########5| 640/672 [00:56<00:02, 11.21it/s]\n\nImage2Image translation inference:  96%|#########5| 642/672 [00:57<00:02, 11.21it/s]\n\nImage2Image translation inference:  96%|#########5| 644/672 [00:57<00:02, 11.22it/s]\n\nImage2Image translation inference:  96%|#########6| 646/672 [00:57<00:02, 11.27it/s]\n\nImage2Image translation inference:  96%|#########6| 648/672 [00:57<00:02, 11.28it/s]\n\nImage2Image translation inference:  97%|#########6| 650/672 [00:57<00:01, 11.28it/s]\n\nImage2Image translation inference:  97%|#########7| 652/672 [00:57<00:01, 11.30it/s]\n\nImage2Image translation inference:  97%|#########7| 654/672 [00:58<00:01, 11.26it/s]\n\nImage2Image translation inference:  98%|#########7| 656/672 [00:58<00:01, 11.27it/s]\n\nImage2Image translation inference:  98%|#########7| 658/672 [00:58<00:01, 11.24it/s]\n\nImage2Image translation inference:  98%|#########8| 660/672 [00:58<00:01, 11.26it/s]\n\nImage2Image translation inference:  99%|#########8| 662/672 [00:58<00:00, 11.25it/s]\n\nImage2Image translation inference:  99%|#########8| 664/672 [00:59<00:00, 11.25it/s]\n\nImage2Image translation inference:  99%|#########9| 666/672 [00:59<00:00, 11.23it/s]\n\nImage2Image translation inference:  99%|#########9| 668/672 [00:59<00:00, 11.26it/s]\n\nImage2Image translation inference: 100%|#########9| 670/672 [00:59<00:00, 11.24it/s]\n\nImage2Image translation inference: 100%|##########| 672/672 [00:59<00:00, 11.23it/s]\n\nImage2Image translation inference: 100%|##########| 672/672 [00:59<00:00, 11.25it/s]\n\nwriting video:   0%|          | 0/672 [00:00<?, ?it/s]\n\nwriting video:   3%|3         | 23/672 [00:00<00:02, 225.21it/s]\n\nwriting video:   7%|6         | 46/672 [00:00<00:02, 226.18it/s]\n\nwriting video:  10%|#         | 70/672 [00:00<00:02, 229.29it/s]\n\nwriting video:  14%|#4        | 95/672 [00:00<00:02, 234.53it/s]\n\nwriting video:  18%|#7        | 119/672 [00:00<00:02, 235.56it/s]\n\nwriting video:  21%|##1       | 143/672 [00:00<00:02, 235.87it/s]\n\nwriting video:  25%|##4       | 167/672 [00:00<00:02, 235.72it/s]\n\nwriting video:  28%|##8       | 191/672 [00:00<00:02, 235.96it/s]\n\nwriting video:  32%|###2      | 216/672 [00:00<00:01, 237.31it/s]\n\nwriting video:  36%|###5      | 240/672 [00:01<00:01, 236.43it/s]\n\nwriting video:  39%|###9      | 264/672 [00:01<00:01, 236.42it/s]\n\nwriting video:  43%|####2     | 288/672 [00:01<00:01, 236.57it/s]\n\nwriting video:  46%|####6     | 312/672 [00:01<00:01, 234.63it/s]\n\nwriting video:  50%|#####     | 336/672 [00:01<00:01, 234.17it/s]\n\nwriting video:  54%|#####3    | 360/672 [00:01<00:01, 230.24it/s]\n\nwriting video:  57%|#####7    | 384/672 [00:01<00:01, 229.25it/s]\n\nwriting video:  61%|######    | 408/672 [00:01<00:01, 229.96it/s]\n\nwriting video:  64%|######4   | 432/672 [00:01<00:01, 230.35it/s]\n\nwriting video:  68%|######8   | 457/672 [00:01<00:00, 233.33it/s]\n\nwriting video:  72%|#######1  | 481/672 [00:02<00:00, 231.95it/s]\n\nwriting video:  75%|#######5  | 505/672 [00:02<00:00, 231.40it/s]\n\nwriting video:  79%|#######8  | 530/672 [00:02<00:00, 234.05it/s]\n\nwriting video:  82%|########2 | 554/672 [00:02<00:00, 234.48it/s]\n\nwriting video:  86%|########6 | 578/672 [00:02<00:00, 234.70it/s]\n\nwriting video:  90%|########9 | 602/672 [00:02<00:00, 233.52it/s]\n\nwriting video:  93%|#########3| 626/672 [00:02<00:00, 232.72it/s]\n\nwriting video:  97%|#########6| 650/672 [00:02<00:00, 234.30it/s]\n\nwriting video: 100%|##########| 672/672 [00:02<00:00, 233.69it/s]\n\ndeleting intermediate images:   0%|          | 0/1344 [00:00<?, ?it/s]\n\ndeleting intermediate images: 100%|##########| 1344/1344 [00:00<00:00, 25067.68it/s]\nFinish!",
  "metrics": {
    "total_time": 79.921857
  },
  "output": [
    {
      "file": "https://replicate.delivery/mgxm/84f3da39-9b5c-4575-9fb9-0397fe0e85e0/out.mp4"
    }
  ],
  "started_at": "2021-12-07T13:44:10.839039Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/zypzj2weq5ayhjw4lzusakwjqu",
    "cancel": "https://api.replicate.com/v1/predictions/zypzj2weq5ayhjw4lzusakwjqu/cancel"
  },
  "version": "2008bf55045c01ec79eb16b678ab84ffa3633a118b429c46bf07f718689c46f8"
}

Tweak itReport

opt:
Namespace(A2L_GMM_ndim=75, APC_frame_history=0, APC_hidden_size=512, APC_residual=False, APC_rnn_layers=3, FPS=60, LSTM_dropout=0, LSTM_hidden_size=256, LSTM_layers=3, LSTM_output_size=80, LSTM_residual=False, LSTM_sequence_length=60, audioRF_future=0, audioRF_history=60, audio_encoder='APC', batch_size=32, checkpoints_dir='./checkpoints/', dataroot='default_path', dataset_mode='audiovisual', dataset_names='default_name', eval=False, feature_decoder='LSTM', feature_dtype='pts3d', frame_future=18, frame_jump_stride=4, gpu_ids='0', ispts_norm=1, load_epoch='500', loss='L2', max_dataset_size=inf, model='audio2feature', name='Audio2Feature', num_threads=0, only_mouth=1, phase='test', predict_length=1, sample_rate=16000, sequence_length=240, serial_batches=False, suffix='', task='Audio2Feature', time_frame_length=1, use_delta_pts=1, verbose=False)
----------------- Options ---------------
             A2L_GMM_ndim: 75                            
        APC_frame_history: 0                             
          APC_hidden_size: 512                           
             APC_residual: False                         
           APC_rnn_layers: 3                             
                      FPS: 60                            
             LSTM_dropout: 0                             
         LSTM_hidden_size: 256                           
              LSTM_layers: 3                             
         LSTM_output_size: 80                            
            LSTM_residual: False                         
     LSTM_sequence_length: 60                            
           audioRF_future: 0                             
          audioRF_history: 60                            
            audio_encoder: APC                           
               batch_size: 32                            
          checkpoints_dir: ./checkpoints/                
                 dataroot: default_path                  
             dataset_mode: audiovisual                   
            dataset_names: default_name                  
                     eval: False                         
          feature_decoder: LSTM                          
            feature_dtype: pts3d                         
             frame_future: 18                            
        frame_jump_stride: 4                             
                  gpu_ids: 0                             
                  isTrain: False                         	[default: None]
               ispts_norm: 1                             
               load_epoch: 500                           
                     loss: L2                            
         max_dataset_size: inf                           
                    model: audio2feature                 
                     name: Audio2Feature                 
              num_threads: 0                             
               only_mouth: 1                             
                    phase: test                          
           predict_length: 1                             
              sample_rate: 16000                         
          sequence_length: 240                           
           serial_batches: False                         
                   suffix:                               
                     task: Audio2Feature                 
        time_frame_length: 1                             
            use_delta_pts: 1                             
                  verbose: False                         
----------------- End -------------------
----------------- Options ---------------
          A2H_GMM_ncenter: 1                             
             A2H_GMM_ndim: 12                            
        A2H_GMM_sigma_min: 0.03                          
         A2H_wavenet_cond: True                          
A2H_wavenet_cond_channels: 512                           
A2H_wavenet_dilation_channels: 128                           
A2H_wavenet_input_channels: 12                            
  A2H_wavenet_kernel_size: 2                             
A2H_wavenet_residual_blocks: 2                             
A2H_wavenet_residual_channels: 128                           
A2H_wavenet_residual_layers: 7                             
A2H_wavenet_skip_channels: 256                           
     A2H_wavenet_use_bias: True                          
        APC_frame_history: 60                            
          APC_hidden_size: 512                           
             APC_residual: False                         
           APC_rnn_layers: 3                             
                      FPS: 60                            
           audioRF_future: 0                             
          audioRF_history: 60                            
            audio_encoder: APC                           
            audio_windows: 2                             
audiofeature_input_channels: 80                            
               batch_size: 32                            
          checkpoints_dir: ./checkpoints/                
                 dataroot: path                          
             dataset_mode: audiovisual                   
            dataset_names: name                          
                     eval: False                         
          feature_decoder: WaveNet                       
             frame_future: 15                            
        frame_jump_stride: 1                             
                  gpu_ids: 0                             
                  isTrain: False                         	[default: None]
               load_epoch: 500                           
                     loss: GMM                           
         max_dataset_size: inf                           
                    model: audio2headpose                
                     name: Audio2Headpose                
              num_threads: 0                             
                    phase: test                          
           predict_length: 5                             
              sample_rate: 16000                         
          sequence_length: 240                           
           serial_batches: False                         
                   suffix:                               
                     task: Audio2Headpose                
        time_frame_length: 1                             
                  verbose: False                         
----------------- End -------------------
------------ Options -------------
batch_size: 1
checkpoints_dir: ./checkpoints/
dataroot: ./data/
dataset_mode: face
dataset_names: ['name']
debug: False
display_id: 0
display_winsize: 512
fineSize: 512
fp16: 0
gpu_ids: [0]
input_nc: 1
isH5: 1
isMask: 0
isTrain: False
loadSize: 512
load_pretrain:
local_rank: 0
max_dataset_size: inf
model: feature2face
n_blocks_E: 3
n_downsample_E: 3
n_downsample_G: 8
name: TestRender
ngf: 64
ngf_E: 16
no_flip: 1
num_threads: 0
output_nc: 3
phase: test
resize_or_crop: scaleWidth
serial_batches: False
suffix: .jpg
task: Feature2Face
test_dataset_names: ['name']
tf_log: True
verbose: False
-------------- End ----------------
---------- Loading Model: APC-------------
---------- Loading Model: Audio2Feature -------------
initialize network with normal
model [Audio2FeatureModel] was created
loading the model from ./data/May/checkpoints/Audio2Feature.pkl
---------- Networks initialized -------------
[Network Audio2Feature] Total number of parameters : 3.064 M
-----------------------------------------------
---------- Loading Model: Audio2Headpose -------------
initialize network with normal
model [Audio2HeadposeModel] was created
loading the model from ./data/May/checkpoints/Audio2Headpose.pkl
---------- Networks initialized -------------
[Network Audio2Headpose] Total number of parameters : 4.267 M
-----------------------------------------------
---------- Loading Model: Feature2Face -------------
dataset [FaceDataset] was created
---------- Generator networks initialized -------------
-------------------------------------------------------
initialize network with normal
model [Feature2FaceModel] was created
loading the model from ./data/May/checkpoints/Feature2Face.pkl
---------- Networks initialized -------------
[Network Feature2Face_G] Total number of parameters : 121.790 M
-----------------------------------------------
Processing audio: 00083 ...
1. Computing APC features...
2. Manifold projection...

LLE projection:   0%|          | 0/1374 [00:00<?, ?it/s]

LLE projection: 100%|##########| 1374/1374 [00:00<00:00, 17595.52it/s]
3. Audio2Mouth inference...
4. Headpose inference...

generating headpose:   0%|          | 0/672 [00:00<?, ?it/s]

generating headpose:   1%|1         | 8/672 [00:00<00:09, 73.20it/s]

generating headpose:   2%|2         | 16/672 [00:00<00:08, 73.92it/s]

generating headpose:   4%|3         | 24/672 [00:00<00:08, 73.88it/s]

generating headpose:   5%|4         | 32/672 [00:00<00:08, 74.02it/s]

generating headpose:   6%|5         | 40/672 [00:00<00:08, 74.01it/s]

generating headpose:   7%|7         | 48/672 [00:00<00:08, 73.90it/s]

generating headpose:   8%|8         | 56/672 [00:00<00:08, 73.33it/s]

generating headpose:  10%|9         | 64/672 [00:00<00:08, 73.49it/s]

generating headpose:  11%|#         | 72/672 [00:00<00:08, 73.37it/s]

generating headpose:  12%|#1        | 80/672 [00:01<00:08, 73.92it/s]

generating headpose:  13%|#3        | 88/672 [00:01<00:07, 73.44it/s]

generating headpose:  14%|#4        | 96/672 [00:01<00:07, 73.51it/s]

generating headpose:  15%|#5        | 104/672 [00:01<00:07, 73.95it/s]

generating headpose:  17%|#6        | 112/672 [00:01<00:07, 73.98it/s]

generating headpose:  18%|#7        | 120/672 [00:01<00:07, 73.46it/s]

generating headpose:  19%|#9        | 128/672 [00:01<00:07, 73.73it/s]

generating headpose:  20%|##        | 136/672 [00:01<00:07, 74.46it/s]

generating headpose:  21%|##1       | 144/672 [00:01<00:07, 75.02it/s]

generating headpose:  23%|##2       | 152/672 [00:02<00:06, 74.76it/s]

generating headpose:  24%|##3       | 160/672 [00:02<00:07, 73.12it/s]

generating headpose:  25%|##5       | 168/672 [00:02<00:06, 73.12it/s]

generating headpose:  26%|##6       | 176/672 [00:02<00:06, 73.15it/s]

generating headpose:  27%|##7       | 184/672 [00:02<00:06, 71.85it/s]

generating headpose:  29%|##8       | 192/672 [00:02<00:06, 72.80it/s]

generating headpose:  30%|##9       | 200/672 [00:02<00:06, 73.38it/s]

generating headpose:  31%|###       | 208/672 [00:02<00:06, 73.16it/s]

generating headpose:  32%|###2      | 216/672 [00:02<00:06, 73.38it/s]

generating headpose:  33%|###3      | 224/672 [00:03<00:06, 73.75it/s]

generating headpose:  35%|###4      | 232/672 [00:03<00:06, 72.12it/s]

generating headpose:  36%|###5      | 240/672 [00:03<00:05, 72.37it/s]

generating headpose:  37%|###6      | 248/672 [00:03<00:05, 72.92it/s]

generating headpose:  38%|###8      | 256/672 [00:03<00:05, 73.69it/s]

generating headpose:  39%|###9      | 264/672 [00:03<00:05, 74.28it/s]

generating headpose:  40%|####      | 272/672 [00:03<00:05, 73.73it/s]

generating headpose:  42%|####1     | 280/672 [00:03<00:05, 73.95it/s]

generating headpose:  43%|####2     | 288/672 [00:03<00:05, 74.11it/s]

generating headpose:  44%|####4     | 296/672 [00:04<00:05, 74.29it/s]

generating headpose:  45%|####5     | 304/672 [00:04<00:05, 72.79it/s]

generating headpose:  46%|####6     | 312/672 [00:04<00:04, 73.03it/s]

generating headpose:  48%|####7     | 320/672 [00:04<00:04, 73.52it/s]

generating headpose:  49%|####8     | 328/672 [00:04<00:04, 73.64it/s]

generating headpose:  50%|#####     | 336/672 [00:04<00:04, 73.40it/s]

generating headpose:  51%|#####1    | 344/672 [00:04<00:04, 73.26it/s]

generating headpose:  52%|#####2    | 352/672 [00:04<00:04, 73.42it/s]

generating headpose:  54%|#####3    | 360/672 [00:04<00:04, 71.14it/s]

generating headpose:  55%|#####4    | 368/672 [00:05<00:04, 70.78it/s]

generating headpose:  56%|#####5    | 376/672 [00:05<00:04, 71.56it/s]

generating headpose:  57%|#####7    | 384/672 [00:05<00:04, 71.92it/s]

generating headpose:  58%|#####8    | 392/672 [00:05<00:03, 72.47it/s]

generating headpose:  60%|#####9    | 400/672 [00:05<00:03, 71.35it/s]

generating headpose:  61%|######    | 408/672 [00:05<00:03, 70.53it/s]

generating headpose:  62%|######1   | 416/672 [00:05<00:03, 71.45it/s]

generating headpose:  63%|######3   | 424/672 [00:05<00:03, 71.68it/s]

generating headpose:  64%|######4   | 432/672 [00:05<00:03, 71.88it/s]

generating headpose:  65%|######5   | 440/672 [00:06<00:03, 72.87it/s]

generating headpose:  67%|######6   | 448/672 [00:06<00:03, 73.01it/s]

generating headpose:  68%|######7   | 456/672 [00:06<00:02, 73.27it/s]

generating headpose:  69%|######9   | 464/672 [00:06<00:02, 73.61it/s]

generating headpose:  70%|#######   | 472/672 [00:06<00:02, 74.00it/s]

generating headpose:  71%|#######1  | 480/672 [00:06<00:02, 74.31it/s]

generating headpose:  73%|#######2  | 488/672 [00:06<00:02, 73.34it/s]

generating headpose:  74%|#######3  | 496/672 [00:06<00:02, 73.28it/s]

generating headpose:  75%|#######5  | 504/672 [00:06<00:02, 73.82it/s]

generating headpose:  76%|#######6  | 512/672 [00:06<00:02, 74.55it/s]

generating headpose:  77%|#######7  | 520/672 [00:07<00:02, 74.23it/s]

generating headpose:  79%|#######8  | 528/672 [00:07<00:01, 72.96it/s]

generating headpose:  80%|#######9  | 536/672 [00:07<00:01, 73.79it/s]

generating headpose:  81%|########  | 544/672 [00:07<00:01, 74.38it/s]

generating headpose:  82%|########2 | 552/672 [00:07<00:01, 74.99it/s]

generating headpose:  83%|########3 | 560/672 [00:07<00:01, 74.55it/s]

generating headpose:  85%|########4 | 568/672 [00:07<00:01, 74.74it/s]

generating headpose:  86%|########5 | 576/672 [00:07<00:01, 75.02it/s]

generating headpose:  87%|########6 | 584/672 [00:07<00:01, 74.91it/s]

generating headpose:  88%|########8 | 592/672 [00:08<00:01, 75.34it/s]

generating headpose:  89%|########9 | 600/672 [00:08<00:00, 75.07it/s]

generating headpose:  90%|######### | 608/672 [00:08<00:00, 75.32it/s]

generating headpose:  92%|#########1| 616/672 [00:08<00:00, 75.68it/s]

generating headpose:  93%|#########2| 624/672 [00:08<00:00, 75.92it/s]

generating headpose:  94%|#########4| 632/672 [00:08<00:00, 75.91it/s]

generating headpose:  95%|#########5| 640/672 [00:08<00:00, 74.65it/s]

generating headpose:  96%|#########6| 648/672 [00:08<00:00, 74.72it/s]

generating headpose:  98%|#########7| 656/672 [00:08<00:00, 74.53it/s]

generating headpose:  99%|#########8| 664/672 [00:09<00:00, 74.95it/s]

generating headpose: 100%|##########| 672/672 [00:09<00:00, 74.67it/s]

generating headpose: 100%|##########| 672/672 [00:09<00:00, 73.60it/s]
5. Post-processing...

  0%|          | 0/672 [00:00<?, ?it/s]

100%|##########| 672/672 [00:00<00:00, 19551.15it/s]
6. Image2Image translation & Saving results...

Image2Image translation inference:   0%|          | 0/672 [00:00<?, ?it/s]

Image2Image translation inference:   0%|          | 1/672 [00:00<01:13,  9.10it/s]

Image2Image translation inference:   0%|          | 2/672 [00:00<01:11,  9.37it/s]

Image2Image translation inference:   1%|          | 4/672 [00:00<01:05, 10.17it/s]

Image2Image translation inference:   1%|          | 6/672 [00:00<01:01, 10.77it/s]

Image2Image translation inference:   1%|1         | 8/672 [00:00<00:59, 11.09it/s]

Image2Image translation inference:   1%|1         | 10/672 [00:00<00:58, 11.27it/s]

Image2Image translation inference:   2%|1         | 12/672 [00:01<00:58, 11.24it/s]

Image2Image translation inference:   2%|2         | 14/672 [00:01<00:58, 11.29it/s]

Image2Image translation inference:   2%|2         | 16/672 [00:01<00:57, 11.34it/s]

Image2Image translation inference:   3%|2         | 18/672 [00:01<00:57, 11.39it/s]

Image2Image translation inference:   3%|2         | 20/672 [00:01<00:57, 11.40it/s]

Image2Image translation inference:   3%|3         | 22/672 [00:01<00:57, 11.38it/s]

Image2Image translation inference:   4%|3         | 24/672 [00:02<00:56, 11.41it/s]

Image2Image translation inference:   4%|3         | 26/672 [00:02<00:56, 11.44it/s]

Image2Image translation inference:   4%|4         | 28/672 [00:02<00:56, 11.44it/s]

Image2Image translation inference:   4%|4         | 30/672 [00:02<00:55, 11.48it/s]

Image2Image translation inference:   5%|4         | 32/672 [00:02<00:55, 11.43it/s]

Image2Image translation inference:   5%|5         | 34/672 [00:03<00:55, 11.42it/s]

Image2Image translation inference:   5%|5         | 36/672 [00:03<00:55, 11.45it/s]

Image2Image translation inference:   6%|5         | 38/672 [00:03<00:55, 11.44it/s]

Image2Image translation inference:   6%|5         | 40/672 [00:03<00:55, 11.41it/s]

Image2Image translation inference:   6%|6         | 42/672 [00:03<00:55, 11.45it/s]

Image2Image translation inference:   7%|6         | 44/672 [00:03<00:54, 11.45it/s]

Image2Image translation inference:   7%|6         | 46/672 [00:04<00:54, 11.45it/s]

Image2Image translation inference:   7%|7         | 48/672 [00:04<00:54, 11.43it/s]

Image2Image translation inference:   7%|7         | 50/672 [00:04<00:54, 11.42it/s]

Image2Image translation inference:   8%|7         | 52/672 [00:04<00:54, 11.44it/s]

Image2Image translation inference:   8%|8         | 54/672 [00:04<00:54, 11.44it/s]

Image2Image translation inference:   8%|8         | 56/672 [00:04<00:54, 11.38it/s]

Image2Image translation inference:   9%|8         | 58/672 [00:05<00:53, 11.39it/s]

Image2Image translation inference:   9%|8         | 60/672 [00:05<00:53, 11.41it/s]

Image2Image translation inference:   9%|9         | 62/672 [00:05<00:53, 11.42it/s]

Image2Image translation inference:  10%|9         | 64/672 [00:05<00:53, 11.44it/s]

Image2Image translation inference:  10%|9         | 66/672 [00:05<00:52, 11.44it/s]

Image2Image translation inference:  10%|#         | 68/672 [00:05<00:52, 11.47it/s]

Image2Image translation inference:  10%|#         | 70/672 [00:06<00:52, 11.49it/s]

Image2Image translation inference:  11%|#         | 72/672 [00:06<00:52, 11.41it/s]

Image2Image translation inference:  11%|#1        | 74/672 [00:06<00:52, 11.42it/s]

Image2Image translation inference:  11%|#1        | 76/672 [00:06<00:52, 11.41it/s]

Image2Image translation inference:  12%|#1        | 78/672 [00:06<00:52, 11.41it/s]

Image2Image translation inference:  12%|#1        | 80/672 [00:07<00:51, 11.41it/s]

Image2Image translation inference:  12%|#2        | 82/672 [00:07<00:51, 11.41it/s]

Image2Image translation inference:  12%|#2        | 84/672 [00:07<00:51, 11.45it/s]

Image2Image translation inference:  13%|#2        | 86/672 [00:07<00:51, 11.42it/s]

Image2Image translation inference:  13%|#3        | 88/672 [00:07<00:51, 11.45it/s]

Image2Image translation inference:  13%|#3        | 90/672 [00:07<00:50, 11.45it/s]

Image2Image translation inference:  14%|#3        | 92/672 [00:08<00:50, 11.46it/s]

Image2Image translation inference:  14%|#3        | 94/672 [00:08<00:50, 11.45it/s]

Image2Image translation inference:  14%|#4        | 96/672 [00:08<00:50, 11.41it/s]

Image2Image translation inference:  15%|#4        | 98/672 [00:08<00:50, 11.42it/s]

Image2Image translation inference:  15%|#4        | 100/672 [00:08<00:50, 11.43it/s]

Image2Image translation inference:  15%|#5        | 102/672 [00:08<00:49, 11.40it/s]

Image2Image translation inference:  15%|#5        | 104/672 [00:09<00:49, 11.38it/s]

Image2Image translation inference:  16%|#5        | 106/672 [00:09<00:49, 11.41it/s]

Image2Image translation inference:  16%|#6        | 108/672 [00:09<00:49, 11.41it/s]

Image2Image translation inference:  16%|#6        | 110/672 [00:09<00:49, 11.45it/s]

Image2Image translation inference:  17%|#6        | 112/672 [00:09<00:49, 11.43it/s]

Image2Image translation inference:  17%|#6        | 114/672 [00:10<00:48, 11.44it/s]

Image2Image translation inference:  17%|#7        | 116/672 [00:10<00:48, 11.41it/s]

Image2Image translation inference:  18%|#7        | 118/672 [00:10<00:48, 11.32it/s]

Image2Image translation inference:  18%|#7        | 120/672 [00:10<00:48, 11.29it/s]

Image2Image translation inference:  18%|#8        | 122/672 [00:10<00:48, 11.28it/s]

Image2Image translation inference:  18%|#8        | 124/672 [00:10<00:48, 11.30it/s]

Image2Image translation inference:  19%|#8        | 126/672 [00:11<00:48, 11.31it/s]

Image2Image translation inference:  19%|#9        | 128/672 [00:11<00:47, 11.35it/s]

Image2Image translation inference:  19%|#9        | 130/672 [00:11<00:47, 11.34it/s]

Image2Image translation inference:  20%|#9        | 132/672 [00:11<00:47, 11.38it/s]

Image2Image translation inference:  20%|#9        | 134/672 [00:11<00:47, 11.39it/s]

Image2Image translation inference:  20%|##        | 136/672 [00:11<00:47, 11.40it/s]

Image2Image translation inference:  21%|##        | 138/672 [00:12<00:46, 11.40it/s]

Image2Image translation inference:  21%|##        | 140/672 [00:12<00:46, 11.38it/s]

Image2Image translation inference:  21%|##1       | 142/672 [00:12<00:46, 11.35it/s]

Image2Image translation inference:  21%|##1       | 144/672 [00:12<00:46, 11.35it/s]

Image2Image translation inference:  22%|##1       | 146/672 [00:12<00:46, 11.37it/s]

Image2Image translation inference:  22%|##2       | 148/672 [00:13<00:46, 11.35it/s]

Image2Image translation inference:  22%|##2       | 150/672 [00:13<00:46, 11.34it/s]

Image2Image translation inference:  23%|##2       | 152/672 [00:13<00:45, 11.39it/s]

Image2Image translation inference:  23%|##2       | 154/672 [00:13<00:45, 11.36it/s]

Image2Image translation inference:  23%|##3       | 156/672 [00:13<00:45, 11.37it/s]

Image2Image translation inference:  24%|##3       | 158/672 [00:13<00:45, 11.31it/s]

Image2Image translation inference:  24%|##3       | 160/672 [00:14<00:45, 11.32it/s]

Image2Image translation inference:  24%|##4       | 162/672 [00:14<00:45, 11.31it/s]

Image2Image translation inference:  24%|##4       | 164/672 [00:14<00:44, 11.34it/s]

Image2Image translation inference:  25%|##4       | 166/672 [00:14<00:44, 11.34it/s]

Image2Image translation inference:  25%|##5       | 168/672 [00:14<00:44, 11.32it/s]

Image2Image translation inference:  25%|##5       | 170/672 [00:14<00:44, 11.33it/s]

Image2Image translation inference:  26%|##5       | 172/672 [00:15<00:44, 11.33it/s]

Image2Image translation inference:  26%|##5       | 174/672 [00:15<00:43, 11.34it/s]

Image2Image translation inference:  26%|##6       | 176/672 [00:15<00:43, 11.34it/s]

Image2Image translation inference:  26%|##6       | 178/672 [00:15<00:43, 11.35it/s]

Image2Image translation inference:  27%|##6       | 180/672 [00:15<00:43, 11.36it/s]

Image2Image translation inference:  27%|##7       | 182/672 [00:16<00:43, 11.35it/s]

Image2Image translation inference:  27%|##7       | 184/672 [00:16<00:42, 11.36it/s]

Image2Image translation inference:  28%|##7       | 186/672 [00:16<00:42, 11.32it/s]

Image2Image translation inference:  28%|##7       | 188/672 [00:16<00:42, 11.33it/s]

Image2Image translation inference:  28%|##8       | 190/672 [00:16<00:42, 11.29it/s]

Image2Image translation inference:  29%|##8       | 192/672 [00:16<00:42, 11.26it/s]

Image2Image translation inference:  29%|##8       | 194/672 [00:17<00:42, 11.28it/s]

Image2Image translation inference:  29%|##9       | 196/672 [00:17<00:42, 11.32it/s]

Image2Image translation inference:  29%|##9       | 198/672 [00:17<00:41, 11.32it/s]

Image2Image translation inference:  30%|##9       | 200/672 [00:17<00:41, 11.31it/s]

Image2Image translation inference:  30%|###       | 202/672 [00:17<00:41, 11.33it/s]

Image2Image translation inference:  30%|###       | 204/672 [00:17<00:41, 11.34it/s]

Image2Image translation inference:  31%|###       | 206/672 [00:18<00:41, 11.33it/s]

Image2Image translation inference:  31%|###       | 208/672 [00:18<00:41, 11.31it/s]

Image2Image translation inference:  31%|###1      | 210/672 [00:18<00:40, 11.29it/s]

Image2Image translation inference:  32%|###1      | 212/672 [00:18<00:40, 11.30it/s]

Image2Image translation inference:  32%|###1      | 214/672 [00:18<00:40, 11.31it/s]

Image2Image translation inference:  32%|###2      | 216/672 [00:19<00:40, 11.31it/s]

Image2Image translation inference:  32%|###2      | 218/672 [00:19<00:40, 11.32it/s]

Image2Image translation inference:  33%|###2      | 220/672 [00:19<00:39, 11.34it/s]

Image2Image translation inference:  33%|###3      | 222/672 [00:19<00:39, 11.33it/s]

Image2Image translation inference:  33%|###3      | 224/672 [00:19<00:39, 11.29it/s]

Image2Image translation inference:  34%|###3      | 226/672 [00:19<00:39, 11.31it/s]

Image2Image translation inference:  34%|###3      | 228/672 [00:20<00:39, 11.32it/s]

Image2Image translation inference:  34%|###4      | 230/672 [00:20<00:39, 11.33it/s]

Image2Image translation inference:  35%|###4      | 232/672 [00:20<00:38, 11.32it/s]

Image2Image translation inference:  35%|###4      | 234/672 [00:20<00:38, 11.31it/s]

Image2Image translation inference:  35%|###5      | 236/672 [00:20<00:38, 11.30it/s]

Image2Image translation inference:  35%|###5      | 238/672 [00:20<00:38, 11.24it/s]

Image2Image translation inference:  36%|###5      | 240/672 [00:21<00:38, 11.26it/s]

Image2Image translation inference:  36%|###6      | 242/672 [00:21<00:38, 11.28it/s]

Image2Image translation inference:  36%|###6      | 244/672 [00:21<00:37, 11.28it/s]

Image2Image translation inference:  37%|###6      | 246/672 [00:21<00:37, 11.27it/s]

Image2Image translation inference:  37%|###6      | 248/672 [00:21<00:37, 11.26it/s]

Image2Image translation inference:  37%|###7      | 250/672 [00:22<00:37, 11.28it/s]

Image2Image translation inference:  38%|###7      | 252/672 [00:22<00:37, 11.32it/s]

Image2Image translation inference:  38%|###7      | 254/672 [00:22<00:36, 11.31it/s]

Image2Image translation inference:  38%|###8      | 256/672 [00:22<00:36, 11.33it/s]

Image2Image translation inference:  38%|###8      | 258/672 [00:22<00:36, 11.33it/s]

Image2Image translation inference:  39%|###8      | 260/672 [00:22<00:36, 11.27it/s]

Image2Image translation inference:  39%|###8      | 262/672 [00:23<00:36, 11.21it/s]

Image2Image translation inference:  39%|###9      | 264/672 [00:23<00:36, 11.14it/s]

Image2Image translation inference:  40%|###9      | 266/672 [00:23<00:36, 11.18it/s]

Image2Image translation inference:  40%|###9      | 268/672 [00:23<00:36, 11.20it/s]

Image2Image translation inference:  40%|####      | 270/672 [00:23<00:35, 11.19it/s]

Image2Image translation inference:  40%|####      | 272/672 [00:23<00:35, 11.22it/s]

Image2Image translation inference:  41%|####      | 274/672 [00:24<00:35, 11.27it/s]

Image2Image translation inference:  41%|####1     | 276/672 [00:24<00:35, 11.28it/s]

Image2Image translation inference:  41%|####1     | 278/672 [00:24<00:35, 11.24it/s]

Image2Image translation inference:  42%|####1     | 280/672 [00:24<00:34, 11.24it/s]

Image2Image translation inference:  42%|####1     | 282/672 [00:24<00:34, 11.24it/s]

Image2Image translation inference:  42%|####2     | 284/672 [00:25<00:34, 11.27it/s]

Image2Image translation inference:  43%|####2     | 286/672 [00:25<00:34, 11.27it/s]

Image2Image translation inference:  43%|####2     | 288/672 [00:25<00:34, 11.26it/s]

Image2Image translation inference:  43%|####3     | 290/672 [00:25<00:33, 11.26it/s]

Image2Image translation inference:  43%|####3     | 292/672 [00:25<00:33, 11.21it/s]

Image2Image translation inference:  44%|####3     | 294/672 [00:25<00:33, 11.22it/s]

Image2Image translation inference:  44%|####4     | 296/672 [00:26<00:33, 11.23it/s]

Image2Image translation inference:  44%|####4     | 298/672 [00:26<00:33, 11.25it/s]

Image2Image translation inference:  45%|####4     | 300/672 [00:26<00:33, 11.27it/s]

Image2Image translation inference:  45%|####4     | 302/672 [00:26<00:32, 11.23it/s]

Image2Image translation inference:  45%|####5     | 304/672 [00:26<00:32, 11.19it/s]

Image2Image translation inference:  46%|####5     | 306/672 [00:27<00:32, 11.21it/s]

Image2Image translation inference:  46%|####5     | 308/672 [00:27<00:32, 11.22it/s]

Image2Image translation inference:  46%|####6     | 310/672 [00:27<00:32, 11.24it/s]

Image2Image translation inference:  46%|####6     | 312/672 [00:27<00:31, 11.25it/s]

Image2Image translation inference:  47%|####6     | 314/672 [00:27<00:31, 11.25it/s]

Image2Image translation inference:  47%|####7     | 316/672 [00:27<00:31, 11.21it/s]

Image2Image translation inference:  47%|####7     | 318/672 [00:28<00:31, 11.17it/s]

Image2Image translation inference:  48%|####7     | 320/672 [00:28<00:31, 11.17it/s]

Image2Image translation inference:  48%|####7     | 322/672 [00:28<00:31, 11.19it/s]

Image2Image translation inference:  48%|####8     | 324/672 [00:28<00:31, 11.22it/s]

Image2Image translation inference:  49%|####8     | 326/672 [00:28<00:30, 11.20it/s]

Image2Image translation inference:  49%|####8     | 328/672 [00:28<00:30, 11.18it/s]

Image2Image translation inference:  49%|####9     | 330/672 [00:29<00:30, 11.21it/s]

Image2Image translation inference:  49%|####9     | 332/672 [00:29<00:30, 11.09it/s]

Image2Image translation inference:  50%|####9     | 334/672 [00:29<00:30, 11.14it/s]

Image2Image translation inference:  50%|#####     | 336/672 [00:29<00:30, 11.18it/s]

Image2Image translation inference:  50%|#####     | 338/672 [00:29<00:29, 11.19it/s]

Image2Image translation inference:  51%|#####     | 340/672 [00:30<00:29, 11.19it/s]

Image2Image translation inference:  51%|#####     | 342/672 [00:30<00:29, 11.18it/s]

Image2Image translation inference:  51%|#####1    | 344/672 [00:30<00:29, 11.16it/s]

Image2Image translation inference:  51%|#####1    | 346/672 [00:30<00:29, 11.18it/s]

Image2Image translation inference:  52%|#####1    | 348/672 [00:30<00:29, 11.16it/s]

Image2Image translation inference:  52%|#####2    | 350/672 [00:30<00:28, 11.18it/s]

Image2Image translation inference:  52%|#####2    | 352/672 [00:31<00:28, 11.20it/s]

Image2Image translation inference:  53%|#####2    | 354/672 [00:31<00:28, 11.16it/s]

Image2Image translation inference:  53%|#####2    | 356/672 [00:31<00:28, 11.15it/s]

Image2Image translation inference:  53%|#####3    | 358/672 [00:31<00:28, 11.16it/s]

Image2Image translation inference:  54%|#####3    | 360/672 [00:31<00:27, 11.15it/s]

Image2Image translation inference:  54%|#####3    | 362/672 [00:32<00:27, 11.14it/s]

Image2Image translation inference:  54%|#####4    | 364/672 [00:32<00:27, 11.14it/s]

Image2Image translation inference:  54%|#####4    | 366/672 [00:32<00:27, 11.14it/s]

Image2Image translation inference:  55%|#####4    | 368/672 [00:32<00:27, 11.17it/s]

Image2Image translation inference:  55%|#####5    | 370/672 [00:32<00:27, 11.19it/s]

Image2Image translation inference:  55%|#####5    | 372/672 [00:32<00:26, 11.16it/s]

Image2Image translation inference:  56%|#####5    | 374/672 [00:33<00:26, 11.16it/s]

Image2Image translation inference:  56%|#####5    | 376/672 [00:33<00:26, 11.17it/s]

Image2Image translation inference:  56%|#####6    | 378/672 [00:33<00:26, 11.19it/s]

Image2Image translation inference:  57%|#####6    | 380/672 [00:33<00:26, 11.19it/s]

Image2Image translation inference:  57%|#####6    | 382/672 [00:33<00:25, 11.19it/s]

Image2Image translation inference:  57%|#####7    | 384/672 [00:33<00:25, 11.18it/s]

Image2Image translation inference:  57%|#####7    | 386/672 [00:34<00:25, 11.14it/s]

Image2Image translation inference:  58%|#####7    | 388/672 [00:34<00:25, 11.17it/s]

Image2Image translation inference:  58%|#####8    | 390/672 [00:34<00:25, 11.17it/s]

Image2Image translation inference:  58%|#####8    | 392/672 [00:34<00:25, 11.19it/s]

Image2Image translation inference:  59%|#####8    | 394/672 [00:34<00:24, 11.15it/s]

Image2Image translation inference:  59%|#####8    | 396/672 [00:35<00:24, 11.17it/s]

Image2Image translation inference:  59%|#####9    | 398/672 [00:35<00:24, 11.09it/s]

Image2Image translation inference:  60%|#####9    | 400/672 [00:35<00:24, 11.11it/s]

Image2Image translation inference:  60%|#####9    | 402/672 [00:35<00:24, 11.14it/s]

Image2Image translation inference:  60%|######    | 404/672 [00:35<00:24, 11.16it/s]

Image2Image translation inference:  60%|######    | 406/672 [00:35<00:23, 11.21it/s]

Image2Image translation inference:  61%|######    | 408/672 [00:36<00:23, 11.19it/s]

Image2Image translation inference:  61%|######1   | 410/672 [00:36<00:23, 11.20it/s]

Image2Image translation inference:  61%|######1   | 412/672 [00:36<00:23, 11.17it/s]

Image2Image translation inference:  62%|######1   | 414/672 [00:36<00:23, 11.13it/s]

Image2Image translation inference:  62%|######1   | 416/672 [00:36<00:22, 11.13it/s]

Image2Image translation inference:  62%|######2   | 418/672 [00:37<00:22, 11.12it/s]

Image2Image translation inference:  62%|######2   | 420/672 [00:37<00:22, 11.14it/s]

Image2Image translation inference:  63%|######2   | 422/672 [00:37<00:22, 11.13it/s]

Image2Image translation inference:  63%|######3   | 424/672 [00:37<00:22, 11.17it/s]

Image2Image translation inference:  63%|######3   | 426/672 [00:37<00:21, 11.20it/s]

Image2Image translation inference:  64%|######3   | 428/672 [00:37<00:21, 11.20it/s]

Image2Image translation inference:  64%|######3   | 430/672 [00:38<00:21, 11.19it/s]

Image2Image translation inference:  64%|######4   | 432/672 [00:38<00:21, 11.15it/s]

Image2Image translation inference:  65%|######4   | 434/672 [00:38<00:21, 11.16it/s]

Image2Image translation inference:  65%|######4   | 436/672 [00:38<00:21, 11.18it/s]

Image2Image translation inference:  65%|######5   | 438/672 [00:38<00:20, 11.20it/s]

Image2Image translation inference:  65%|######5   | 440/672 [00:39<00:20, 11.19it/s]

Image2Image translation inference:  66%|######5   | 442/672 [00:39<00:20, 11.21it/s]

Image2Image translation inference:  66%|######6   | 444/672 [00:39<00:20, 11.18it/s]

Image2Image translation inference:  66%|######6   | 446/672 [00:39<00:20, 11.22it/s]

Image2Image translation inference:  67%|######6   | 448/672 [00:39<00:19, 11.23it/s]

Image2Image translation inference:  67%|######6   | 450/672 [00:39<00:19, 11.23it/s]

Image2Image translation inference:  67%|######7   | 452/672 [00:40<00:19, 11.09it/s]

Image2Image translation inference:  68%|######7   | 454/672 [00:40<00:19, 11.14it/s]

Image2Image translation inference:  68%|######7   | 456/672 [00:40<00:19, 11.18it/s]

Image2Image translation inference:  68%|######8   | 458/672 [00:40<00:19, 11.18it/s]

Image2Image translation inference:  68%|######8   | 460/672 [00:40<00:19, 11.14it/s]

Image2Image translation inference:  69%|######8   | 462/672 [00:40<00:18, 11.12it/s]

Image2Image translation inference:  69%|######9   | 464/672 [00:41<00:18, 11.16it/s]

Image2Image translation inference:  69%|######9   | 466/672 [00:41<00:18, 11.18it/s]

Image2Image translation inference:  70%|######9   | 468/672 [00:41<00:18, 11.19it/s]

Image2Image translation inference:  70%|######9   | 470/672 [00:41<00:18, 11.22it/s]

Image2Image translation inference:  70%|#######   | 472/672 [00:41<00:17, 11.27it/s]

Image2Image translation inference:  71%|#######   | 474/672 [00:42<00:17, 11.22it/s]

Image2Image translation inference:  71%|#######   | 476/672 [00:42<00:17, 11.22it/s]

Image2Image translation inference:  71%|#######1  | 478/672 [00:42<00:17, 11.21it/s]

Image2Image translation inference:  71%|#######1  | 480/672 [00:42<00:17, 11.21it/s]

Image2Image translation inference:  72%|#######1  | 482/672 [00:42<00:16, 11.21it/s]

Image2Image translation inference:  72%|#######2  | 484/672 [00:42<00:16, 11.20it/s]

Image2Image translation inference:  72%|#######2  | 486/672 [00:43<00:16, 11.19it/s]

Image2Image translation inference:  73%|#######2  | 488/672 [00:43<00:17, 10.79it/s]

Image2Image translation inference:  73%|#######2  | 490/672 [00:43<00:16, 10.90it/s]

Image2Image translation inference:  73%|#######3  | 492/672 [00:43<00:16, 10.96it/s]

Image2Image translation inference:  74%|#######3  | 494/672 [00:43<00:16, 10.98it/s]

Image2Image translation inference:  74%|#######3  | 496/672 [00:44<00:15, 11.05it/s]

Image2Image translation inference:  74%|#######4  | 498/672 [00:44<00:15, 11.11it/s]

Image2Image translation inference:  74%|#######4  | 500/672 [00:44<00:15, 11.12it/s]

Image2Image translation inference:  75%|#######4  | 502/672 [00:44<00:15, 11.14it/s]

Image2Image translation inference:  75%|#######5  | 504/672 [00:44<00:15, 11.15it/s]

Image2Image translation inference:  75%|#######5  | 506/672 [00:44<00:14, 11.12it/s]

Image2Image translation inference:  76%|#######5  | 508/672 [00:45<00:14, 11.14it/s]

Image2Image translation inference:  76%|#######5  | 510/672 [00:45<00:14, 11.14it/s]

Image2Image translation inference:  76%|#######6  | 512/672 [00:45<00:14, 11.11it/s]

Image2Image translation inference:  76%|#######6  | 514/672 [00:45<00:14, 11.15it/s]

Image2Image translation inference:  77%|#######6  | 516/672 [00:45<00:13, 11.14it/s]

Image2Image translation inference:  77%|#######7  | 518/672 [00:46<00:13, 11.16it/s]

Image2Image translation inference:  77%|#######7  | 520/672 [00:46<00:13, 11.19it/s]

Image2Image translation inference:  78%|#######7  | 522/672 [00:46<00:13, 11.20it/s]

Image2Image translation inference:  78%|#######7  | 524/672 [00:46<00:13, 11.20it/s]

Image2Image translation inference:  78%|#######8  | 526/672 [00:46<00:13, 11.18it/s]

Image2Image translation inference:  79%|#######8  | 528/672 [00:46<00:12, 11.21it/s]

Image2Image translation inference:  79%|#######8  | 530/672 [00:47<00:12, 11.19it/s]

Image2Image translation inference:  79%|#######9  | 532/672 [00:47<00:12, 11.19it/s]

Image2Image translation inference:  79%|#######9  | 534/672 [00:47<00:12, 11.21it/s]

Image2Image translation inference:  80%|#######9  | 536/672 [00:47<00:12, 11.23it/s]

Image2Image translation inference:  80%|########  | 538/672 [00:47<00:11, 11.24it/s]

Image2Image translation inference:  80%|########  | 540/672 [00:47<00:11, 11.19it/s]

Image2Image translation inference:  81%|########  | 542/672 [00:48<00:11, 11.10it/s]

Image2Image translation inference:  81%|########  | 544/672 [00:48<00:11, 11.14it/s]

Image2Image translation inference:  81%|########1 | 546/672 [00:48<00:11, 11.13it/s]

Image2Image translation inference:  82%|########1 | 548/672 [00:48<00:11, 11.15it/s]

Image2Image translation inference:  82%|########1 | 550/672 [00:48<00:10, 11.21it/s]

Image2Image translation inference:  82%|########2 | 552/672 [00:49<00:10, 11.21it/s]

Image2Image translation inference:  82%|########2 | 554/672 [00:49<00:10, 11.23it/s]

Image2Image translation inference:  83%|########2 | 556/672 [00:49<00:10, 11.23it/s]

Image2Image translation inference:  83%|########3 | 558/672 [00:49<00:10, 11.27it/s]

Image2Image translation inference:  83%|########3 | 560/672 [00:49<00:09, 11.26it/s]

Image2Image translation inference:  84%|########3 | 562/672 [00:49<00:09, 11.27it/s]

Image2Image translation inference:  84%|########3 | 564/672 [00:50<00:09, 11.26it/s]

Image2Image translation inference:  84%|########4 | 566/672 [00:50<00:09, 11.26it/s]

Image2Image translation inference:  85%|########4 | 568/672 [00:50<00:09, 11.28it/s]

Image2Image translation inference:  85%|########4 | 570/672 [00:50<00:09, 11.29it/s]

Image2Image translation inference:  85%|########5 | 572/672 [00:50<00:08, 11.26it/s]

Image2Image translation inference:  85%|########5 | 574/672 [00:51<00:08, 11.26it/s]

Image2Image translation inference:  86%|########5 | 576/672 [00:51<00:08, 11.24it/s]

Image2Image translation inference:  86%|########6 | 578/672 [00:51<00:08, 11.00it/s]

Image2Image translation inference:  86%|########6 | 580/672 [00:51<00:08, 11.09it/s]

Image2Image translation inference:  87%|########6 | 582/672 [00:51<00:08, 11.16it/s]

Image2Image translation inference:  87%|########6 | 584/672 [00:51<00:07, 11.21it/s]

Image2Image translation inference:  87%|########7 | 586/672 [00:52<00:07, 11.25it/s]

Image2Image translation inference:  88%|########7 | 588/672 [00:52<00:07, 11.24it/s]

Image2Image translation inference:  88%|########7 | 590/672 [00:52<00:07, 11.24it/s]

Image2Image translation inference:  88%|########8 | 592/672 [00:52<00:07, 11.24it/s]

Image2Image translation inference:  88%|########8 | 594/672 [00:52<00:06, 11.25it/s]

Image2Image translation inference:  89%|########8 | 596/672 [00:52<00:06, 11.24it/s]

Image2Image translation inference:  89%|########8 | 598/672 [00:53<00:06, 11.24it/s]

Image2Image translation inference:  89%|########9 | 600/672 [00:53<00:06, 11.24it/s]

Image2Image translation inference:  90%|########9 | 602/672 [00:53<00:06, 11.25it/s]

Image2Image translation inference:  90%|########9 | 604/672 [00:53<00:06, 11.21it/s]

Image2Image translation inference:  90%|######### | 606/672 [00:53<00:05, 11.20it/s]

Image2Image translation inference:  90%|######### | 608/672 [00:54<00:05, 11.24it/s]

Image2Image translation inference:  91%|######### | 610/672 [00:54<00:05, 11.25it/s]

Image2Image translation inference:  91%|#########1| 612/672 [00:54<00:05, 11.27it/s]

Image2Image translation inference:  91%|#########1| 614/672 [00:54<00:05, 11.24it/s]

Image2Image translation inference:  92%|#########1| 616/672 [00:54<00:04, 11.25it/s]

Image2Image translation inference:  92%|#########1| 618/672 [00:54<00:04, 11.24it/s]

Image2Image translation inference:  92%|#########2| 620/672 [00:55<00:04, 11.23it/s]

Image2Image translation inference:  93%|#########2| 622/672 [00:55<00:04, 11.22it/s]

Image2Image translation inference:  93%|#########2| 624/672 [00:55<00:04, 11.20it/s]

Image2Image translation inference:  93%|#########3| 626/672 [00:55<00:04, 11.22it/s]

Image2Image translation inference:  93%|#########3| 628/672 [00:55<00:03, 11.19it/s]

Image2Image translation inference:  94%|#########3| 630/672 [00:56<00:03, 11.19it/s]

Image2Image translation inference:  94%|#########4| 632/672 [00:56<00:03, 11.23it/s]

Image2Image translation inference:  94%|#########4| 634/672 [00:56<00:03, 11.25it/s]

Image2Image translation inference:  95%|#########4| 636/672 [00:56<00:03, 11.23it/s]

Image2Image translation inference:  95%|#########4| 638/672 [00:56<00:03, 11.23it/s]

Image2Image translation inference:  95%|#########5| 640/672 [00:56<00:02, 11.21it/s]

Image2Image translation inference:  96%|#########5| 642/672 [00:57<00:02, 11.21it/s]

Image2Image translation inference:  96%|#########5| 644/672 [00:57<00:02, 11.22it/s]

Image2Image translation inference:  96%|#########6| 646/672 [00:57<00:02, 11.27it/s]

Image2Image translation inference:  96%|#########6| 648/672 [00:57<00:02, 11.28it/s]

Image2Image translation inference:  97%|#########6| 650/672 [00:57<00:01, 11.28it/s]

Image2Image translation inference:  97%|#########7| 652/672 [00:57<00:01, 11.30it/s]

Image2Image translation inference:  97%|#########7| 654/672 [00:58<00:01, 11.26it/s]

Image2Image translation inference:  98%|#########7| 656/672 [00:58<00:01, 11.27it/s]

Image2Image translation inference:  98%|#########7| 658/672 [00:58<00:01, 11.24it/s]

Image2Image translation inference:  98%|#########8| 660/672 [00:58<00:01, 11.26it/s]

Image2Image translation inference:  99%|#########8| 662/672 [00:58<00:00, 11.25it/s]

Image2Image translation inference:  99%|#########8| 664/672 [00:59<00:00, 11.25it/s]

Image2Image translation inference:  99%|#########9| 666/672 [00:59<00:00, 11.23it/s]

Image2Image translation inference:  99%|#########9| 668/672 [00:59<00:00, 11.26it/s]

Image2Image translation inference: 100%|#########9| 670/672 [00:59<00:00, 11.24it/s]

Image2Image translation inference: 100%|##########| 672/672 [00:59<00:00, 11.23it/s]

Image2Image translation inference: 100%|##########| 672/672 [00:59<00:00, 11.25it/s]

writing video:   0%|          | 0/672 [00:00<?, ?it/s]

writing video:   3%|3         | 23/672 [00:00<00:02, 225.21it/s]

writing video:   7%|6         | 46/672 [00:00<00:02, 226.18it/s]

writing video:  10%|#         | 70/672 [00:00<00:02, 229.29it/s]

writing video:  14%|#4        | 95/672 [00:00<00:02, 234.53it/s]

writing video:  18%|#7        | 119/672 [00:00<00:02, 235.56it/s]

writing video:  21%|##1       | 143/672 [00:00<00:02, 235.87it/s]

writing video:  25%|##4       | 167/672 [00:00<00:02, 235.72it/s]

writing video:  28%|##8       | 191/672 [00:00<00:02, 235.96it/s]

writing video:  32%|###2      | 216/672 [00:00<00:01, 237.31it/s]

writing video:  36%|###5      | 240/672 [00:01<00:01, 236.43it/s]

writing video:  39%|###9      | 264/672 [00:01<00:01, 236.42it/s]

writing video:  43%|####2     | 288/672 [00:01<00:01, 236.57it/s]

writing video:  46%|####6     | 312/672 [00:01<00:01, 234.63it/s]

writing video:  50%|#####     | 336/672 [00:01<00:01, 234.17it/s]

writing video:  54%|#####3    | 360/672 [00:01<00:01, 230.24it/s]

writing video:  57%|#####7    | 384/672 [00:01<00:01, 229.25it/s]

writing video:  61%|######    | 408/672 [00:01<00:01, 229.96it/s]

writing video:  64%|######4   | 432/672 [00:01<00:01, 230.35it/s]

writing video:  68%|######8   | 457/672 [00:01<00:00, 233.33it/s]

writing video:  72%|#######1  | 481/672 [00:02<00:00, 231.95it/s]

writing video:  75%|#######5  | 505/672 [00:02<00:00, 231.40it/s]

writing video:  79%|#######8  | 530/672 [00:02<00:00, 234.05it/s]

writing video:  82%|########2 | 554/672 [00:02<00:00, 234.48it/s]

writing video:  86%|########6 | 578/672 [00:02<00:00, 234.70it/s]

writing video:  90%|########9 | 602/672 [00:02<00:00, 233.52it/s]

writing video:  93%|#########3| 626/672 [00:02<00:00, 232.72it/s]

writing video:  97%|#########6| 650/672 [00:02<00:00, 234.30it/s]

writing video: 100%|##########| 672/672 [00:02<00:00, 233.69it/s]

deleting intermediate images:   0%|          | 0/1344 [00:00<?, ?it/s]

deleting intermediate images: 100%|##########| 1344/1344 [00:00<00:00, 25067.68it/s]
Finish!

This output was created using a different version of the model, yuanxunlu/livespeechportraits:2008bf55.