Readme
This model doesn't have a readme.
Make your video talk anything
Run this model in Node.js with one line of code:
npm install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import Replicate from "replicate";
const replicate = new Replicate({
auth: process.env.REPLICATE_API_TOKEN,
});
Run gauravk95/sadtalker-video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run(
"gauravk95/sadtalker-video:9804d1827f20dbc994c64eac2ac2fd835670209ec8a3dc3f2429c2d847414b11",
{
input: {
use_DAIN: false,
enhancer_region: "lip",
audio_input_path: "https://replicate.delivery/pbxt/KCCITEBY84VLXxmQTovjbsq0ruQw8kJ3hcbTyvVf0ukEsJQj/chinese_poem1.wav",
video_input_path: "https://replicate.delivery/pbxt/KCCITJNxqqvNnw2w5Qp0799vPPFy5qh3TZSm0gYo9lyvilQw/1.mp4"
}
}
);
// 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.
pip install replicate
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
import replicate
Run gauravk95/sadtalker-video using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run(
"gauravk95/sadtalker-video:9804d1827f20dbc994c64eac2ac2fd835670209ec8a3dc3f2429c2d847414b11",
input={
"use_DAIN": False,
"enhancer_region": "lip",
"audio_input_path": "https://replicate.delivery/pbxt/KCCITEBY84VLXxmQTovjbsq0ruQw8kJ3hcbTyvVf0ukEsJQj/chinese_poem1.wav",
"video_input_path": "https://replicate.delivery/pbxt/KCCITJNxqqvNnw2w5Qp0799vPPFy5qh3TZSm0gYo9lyvilQw/1.mp4"
}
)
print(output)
To learn more, take a look at the guide on getting started with Python.
REPLICATE_API_TOKEN
environment variable:export REPLICATE_API_TOKEN=<paste-your-token-here>
Find your API token in your account settings.
Run gauravk95/sadtalker-video 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": "gauravk95/sadtalker-video:9804d1827f20dbc994c64eac2ac2fd835670209ec8a3dc3f2429c2d847414b11",
"input": {
"use_DAIN": false,
"enhancer_region": "lip",
"audio_input_path": "https://replicate.delivery/pbxt/KCCITEBY84VLXxmQTovjbsq0ruQw8kJ3hcbTyvVf0ukEsJQj/chinese_poem1.wav",
"video_input_path": "https://replicate.delivery/pbxt/KCCITJNxqqvNnw2w5Qp0799vPPFy5qh3TZSm0gYo9lyvilQw/1.mp4"
}
}' \
https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Add a payment method to run this model.
By signing in, you agree to our
terms of service and privacy policy
{
"completed_at": "2024-01-09T11:03:10.776859Z",
"created_at": "2024-01-09T10:58:12.115946Z",
"data_removed": false,
"error": null,
"id": "2gcqfr3byhq2zr7kxbc7q55oyy",
"input": {
"use_DAIN": false,
"enhancer_region": "lip",
"audio_input_path": "https://replicate.delivery/pbxt/KCCITEBY84VLXxmQTovjbsq0ruQw8kJ3hcbTyvVf0ukEsJQj/chinese_poem1.wav",
"video_input_path": "https://replicate.delivery/pbxt/KCCITJNxqqvNnw2w5Qp0799vPPFy5qh3TZSm0gYo9lyvilQw/1.mp4"
},
"logs": "Start Predictions...\n3DMM Extraction for source image\nlandmark Det:: 0%| | 0/135 [00:00<?, ?it/s]\nlandmark Det:: 1%| | 1/135 [00:09<21:17, 9.53s/it]\nlandmark Det:: 1%|▏ | 2/135 [00:13<13:33, 6.11s/it]\nlandmark Det:: 6%|▌ | 8/135 [00:13<02:10, 1.03s/it]\nlandmark Det:: 10%|█ | 14/135 [00:13<00:58, 2.08it/s]\nlandmark Det:: 15%|█▍ | 20/135 [00:13<00:32, 3.59it/s]\nlandmark Det:: 19%|█▉ | 26/135 [00:13<00:19, 5.60it/s]\nlandmark Det:: 24%|██▎ | 32/135 [00:13<00:12, 8.20it/s]\nlandmark Det:: 28%|██▊ | 38/135 [00:13<00:08, 11.45it/s]\nlandmark Det:: 33%|███▎ | 44/135 [00:14<00:05, 15.38it/s]\nlandmark Det:: 37%|███▋ | 50/135 [00:14<00:04, 19.72it/s]\nlandmark Det:: 41%|████▏ | 56/135 [00:14<00:03, 24.29it/s]\nlandmark Det:: 46%|████▌ | 62/135 [00:14<00:02, 28.92it/s]\nlandmark Det:: 50%|█████ | 68/135 [00:14<00:02, 33.42it/s]\nlandmark Det:: 55%|█████▍ | 74/135 [00:14<00:01, 37.22it/s]\nlandmark Det:: 59%|█████▉ | 80/135 [00:14<00:01, 41.26it/s]\nlandmark Det:: 64%|██████▎ | 86/135 [00:14<00:01, 43.59it/s]\nlandmark Det:: 68%|██████▊ | 92/135 [00:15<00:00, 45.27it/s]\nlandmark Det:: 73%|███████▎ | 98/135 [00:15<00:00, 47.25it/s]\nlandmark Det:: 77%|███████▋ | 104/135 [00:15<00:00, 48.61it/s]\nlandmark Det:: 81%|████████▏ | 110/135 [00:15<00:00, 50.01it/s]\nlandmark Det:: 86%|████████▌ | 116/135 [00:15<00:00, 50.81it/s]\nlandmark Det:: 90%|█████████ | 122/135 [00:15<00:00, 50.96it/s]\nlandmark Det:: 95%|█████████▍| 128/135 [00:15<00:00, 50.16it/s]\nlandmark Det:: 99%|█████████▉| 134/135 [00:15<00:00, 49.98it/s]\nlandmark Det:: 100%|██████████| 135/135 [00:15<00:00, 8.52it/s]\n3DMM Extraction In Video:: 0%| | 0/135 [00:00<?, ?it/s]\n3DMM Extraction In Video:: 1%| | 1/135 [00:00<00:29, 4.59it/s]\n3DMM Extraction In Video:: 9%|▉ | 12/135 [00:00<00:02, 45.03it/s]\n3DMM Extraction In Video:: 17%|█▋ | 23/135 [00:00<00:01, 66.70it/s]\n3DMM Extraction In Video:: 24%|██▍ | 33/135 [00:00<00:01, 76.58it/s]\n3DMM Extraction In Video:: 33%|███▎ | 44/135 [00:00<00:01, 85.78it/s]\n3DMM Extraction In Video:: 41%|████ | 55/135 [00:00<00:00, 91.91it/s]\n3DMM Extraction In Video:: 50%|████▉ | 67/135 [00:00<00:00, 98.35it/s]\n3DMM Extraction In Video:: 58%|█████▊ | 78/135 [00:00<00:00, 100.93it/s]\n3DMM Extraction In Video:: 66%|██████▌ | 89/135 [00:01<00:00, 102.79it/s]\n3DMM Extraction In Video:: 75%|███████▍ | 101/135 [00:01<00:00, 105.55it/s]\n3DMM Extraction In Video:: 83%|████████▎ | 112/135 [00:01<00:00, 105.16it/s]\n3DMM Extraction In Video:: 92%|█████████▏| 124/135 [00:01<00:00, 107.35it/s]\n3DMM Extraction In Video:: 100%|██████████| 135/135 [00:01<00:00, 91.50it/s]\nmel:: 0%| | 0/136 [00:00<?, ?it/s]\nmel:: 100%|██████████| 136/136 [00:00<00:00, 39123.82it/s]\naudio2exp:: 0%| | 0/14 [00:00<?, ?it/s]\naudio2exp:: 57%|█████▋ | 8/14 [00:00<00:00, 78.85it/s]\naudio2exp:: 100%|██████████| 14/14 [00:00<00:00, 81.42it/s]\nFace Renderer:: 0%| | 0/136 [00:00<?, ?it/s]\nFace Renderer:: 1%| | 1/136 [00:00<01:46, 1.27it/s]\nFace Renderer:: 2%|▏ | 3/136 [00:00<00:32, 4.07it/s]\nFace Renderer:: 4%|▎ | 5/136 [00:01<00:19, 6.58it/s]\nFace Renderer:: 5%|▌ | 7/136 [00:01<00:14, 9.11it/s]\nFace Renderer:: 7%|▋ | 9/136 [00:01<00:11, 11.30it/s]\nFace Renderer:: 8%|▊ | 11/136 [00:01<00:09, 13.13it/s]\nFace Renderer:: 10%|▉ | 13/136 [00:01<00:08, 14.55it/s]\nFace Renderer:: 11%|█ | 15/136 [00:01<00:07, 15.70it/s]\nFace Renderer:: 12%|█▎ | 17/136 [00:01<00:07, 16.53it/s]\nFace Renderer:: 14%|█▍ | 19/136 [00:01<00:06, 17.15it/s]\nFace Renderer:: 15%|█▌ | 21/136 [00:01<00:06, 17.59it/s]\nFace Renderer:: 17%|█▋ | 23/136 [00:01<00:06, 17.89it/s]\nFace Renderer:: 18%|█▊ | 25/136 [00:02<00:06, 18.06it/s]\nFace Renderer:: 20%|█▉ | 27/136 [00:02<00:05, 18.31it/s]\nFace Renderer:: 21%|██▏ | 29/136 [00:02<00:05, 18.44it/s]\nFace Renderer:: 23%|██▎ | 31/136 [00:02<00:05, 18.53it/s]\nFace Renderer:: 24%|██▍ | 33/136 [00:02<00:05, 18.61it/s]\nFace Renderer:: 26%|██▌ | 35/136 [00:02<00:05, 18.59it/s]\nFace Renderer:: 27%|██▋ | 37/136 [00:02<00:05, 18.63it/s]\nFace Renderer:: 29%|██▊ | 39/136 [00:02<00:05, 18.51it/s]\nFace Renderer:: 30%|███ | 41/136 [00:02<00:05, 18.59it/s]\nFace Renderer:: 32%|███▏ | 43/136 [00:03<00:04, 18.64it/s]\nFace Renderer:: 33%|███▎ | 45/136 [00:03<00:04, 18.68it/s]\nFace Renderer:: 35%|███▍ | 47/136 [00:03<00:04, 18.70it/s]\nFace Renderer:: 36%|███▌ | 49/136 [00:03<00:04, 18.70it/s]\nFace Renderer:: 38%|███▊ | 51/136 [00:03<00:04, 18.69it/s]\nFace Renderer:: 39%|███▉ | 53/136 [00:03<00:04, 18.72it/s]\nFace Renderer:: 40%|████ | 55/136 [00:03<00:04, 18.51it/s]\nFace Renderer:: 42%|████▏ | 57/136 [00:03<00:04, 18.68it/s]\nFace Renderer:: 43%|████▎ | 59/136 [00:03<00:04, 18.66it/s]\nFace Renderer:: 45%|████▍ | 61/136 [00:04<00:04, 18.59it/s]\nFace Renderer:: 46%|████▋ | 63/136 [00:04<00:03, 18.57it/s]\nFace Renderer:: 48%|████▊ | 65/136 [00:04<00:03, 18.64it/s]\nFace Renderer:: 49%|████▉ | 67/136 [00:04<00:03, 18.65it/s]\nFace Renderer:: 51%|█████ | 69/136 [00:04<00:03, 18.69it/s]\nFace Renderer:: 52%|█████▏ | 71/136 [00:04<00:03, 18.68it/s]\nFace Renderer:: 54%|█████▎ | 73/136 [00:04<00:03, 18.71it/s]\nFace Renderer:: 55%|█████▌ | 75/136 [00:04<00:03, 18.73it/s]\nFace Renderer:: 57%|█████▋ | 77/136 [00:04<00:03, 18.68it/s]\nFace Renderer:: 58%|█████▊ | 79/136 [00:04<00:03, 18.69it/s]\nFace Renderer:: 60%|█████▉ | 81/136 [00:05<00:02, 18.72it/s]\nFace Renderer:: 61%|██████ | 83/136 [00:05<00:02, 18.76it/s]\nFace Renderer:: 62%|██████▎ | 85/136 [00:05<00:02, 18.73it/s]\nFace Renderer:: 64%|██████▍ | 87/136 [00:05<00:02, 18.49it/s]\nFace Renderer:: 65%|██████▌ | 89/136 [00:05<00:02, 18.53it/s]\nFace Renderer:: 67%|██████▋ | 91/136 [00:05<00:02, 18.55it/s]\nFace Renderer:: 68%|██████▊ | 93/136 [00:05<00:02, 18.63it/s]\nFace Renderer:: 70%|██████▉ | 95/136 [00:05<00:02, 18.68it/s]\nFace Renderer:: 71%|███████▏ | 97/136 [00:05<00:02, 18.70it/s]\nFace Renderer:: 73%|███████▎ | 99/136 [00:06<00:01, 18.72it/s]\nFace Renderer:: 74%|███████▍ | 101/136 [00:06<00:01, 18.71it/s]\nFace Renderer:: 76%|███████▌ | 103/136 [00:06<00:01, 18.77it/s]\nFace Renderer:: 77%|███████▋ | 105/136 [00:06<00:01, 18.74it/s]\nFace Renderer:: 79%|███████▊ | 107/136 [00:06<00:01, 18.74it/s]\nFace Renderer:: 80%|████████ | 109/136 [00:06<00:01, 18.62it/s]\nFace Renderer:: 82%|████████▏ | 111/136 [00:06<00:01, 18.65it/s]\nFace Renderer:: 83%|████████▎ | 113/136 [00:06<00:01, 18.44it/s]\nFace Renderer:: 85%|████████▍ | 115/136 [00:06<00:01, 18.46it/s]\nFace Renderer:: 86%|████████▌ | 117/136 [00:07<00:01, 18.53it/s]\nFace Renderer:: 88%|████████▊ | 119/136 [00:07<00:00, 18.59it/s]\nFace Renderer:: 89%|████████▉ | 121/136 [00:07<00:00, 18.65it/s]\nFace Renderer:: 90%|█████████ | 123/136 [00:07<00:00, 18.64it/s]\nFace Renderer:: 92%|█████████▏| 125/136 [00:07<00:00, 18.63it/s]\nFace Renderer:: 93%|█████████▎| 127/136 [00:07<00:00, 18.58it/s]\nFace Renderer:: 95%|█████████▍| 129/136 [00:07<00:00, 18.53it/s]\nFace Renderer:: 96%|█████████▋| 131/136 [00:07<00:00, 18.54it/s]\nFace Renderer:: 98%|█████████▊| 133/136 [00:07<00:00, 18.63it/s]\nFace Renderer:: 99%|█████████▉| 135/136 [00:07<00:00, 18.68it/s]\nFace Renderer:: 99%|█████████▉| 135/136 [00:07<00:00, 16.89it/s]\nffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nInput #0, mov,mp4,m4a,3gp,3g2,mj2, from 'results/2024_01_09_11.01.46/temp_tmpiuycqk491##tmpy824i3jtchinese_poem1.mp4':\nMetadata:\nmajor_brand : isom\nminor_version : 512\ncompatible_brands: isomiso2avc1mp41\nencoder : Lavf58.29.100\nDuration: 00:00:05.40, start: 0.000000, bitrate: 69 kb/s\nStream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 256x256, 66 kb/s, 25 fps, 25 tbr, 12800 tbn, 50 tbc (default)\nMetadata:\nhandler_name : VideoHandler\nvendor_id : [0][0][0][0]\nGuessed Channel Layout for Input Stream #1.0 : mono\nInput #1, wav, from 'results/2024_01_09_11.01.46/tmpy824i3jtchinese_poem1.wav':\nDuration: 00:00:05.40, bitrate: 256 kb/s\nStream #1:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s\nStream mapping:\nStream #0:0 -> #0:0 (copy)\nStream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native))\nPress [q] to stop, [?] for help\nOutput #0, mp4, to 'bab057ca-1797-4081-af8f-efd4d5d799ca.mp4':\nMetadata:\nmajor_brand : isom\nminor_version : 512\ncompatible_brands: isomiso2avc1mp41\nencoder : Lavf58.76.100\nStream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 256x256, q=2-31, 66 kb/s, 25 fps, 25 tbr, 12800 tbn, 12800 tbc (default)\nMetadata:\nhandler_name : VideoHandler\nvendor_id : [0][0][0][0]\nStream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 16000 Hz, mono, fltp, 69 kb/s\nMetadata:\nencoder : Lavc58.134.100 aac\nframe= 0 fps=0.0 q=-1.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 135 fps=0.0 q=-1.0 Lsize= 92kB time=00:00:05.37 bitrate= 140.8kbits/s speed= 308x\nvideo:44kB audio:44kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 5.446096%\n[aac @ 0x5563e2ed36c0] Qavg: 42759.586\nThe generated video is named tmpiuycqk491##tmpy824i3jtchinese_poem1.mp4 in results/2024_01_09_11.01.46\nOpenCV: FFMPEG: tag 0x5634504d/'MP4V' is not supported with codec id 12 and format 'mp4 / MP4 (MPEG-4 Part 14)'\nOpenCV: FFMPEG: fallback to use tag 0x7634706d/'mp4v'\nfaceClone:: 0%| | 0/135 [00:00<?, ?it/s]\nfaceClone:: 1%| | 1/135 [00:01<03:09, 1.41s/it]\nfaceClone:: 1%|▏ | 2/135 [00:01<01:45, 1.27it/s]\nfaceClone:: 2%|▏ | 3/135 [00:02<01:18, 1.68it/s]\nfaceClone:: 3%|▎ | 4/135 [00:02<01:05, 2.00it/s]\nfaceClone:: 4%|▎ | 5/135 [00:02<00:59, 2.20it/s]\nfaceClone:: 4%|▍ | 6/135 [00:03<00:55, 2.34it/s]\nfaceClone:: 5%|▌ | 7/135 [00:03<00:52, 2.44it/s]\nfaceClone:: 6%|▌ | 8/135 [00:03<00:50, 2.53it/s]\nfaceClone:: 7%|▋ | 9/135 [00:04<00:48, 2.59it/s]\nfaceClone:: 7%|▋ | 10/135 [00:04<00:47, 2.61it/s]\nfaceClone:: 8%|▊ | 11/135 [00:05<00:46, 2.66it/s]\nfaceClone:: 9%|▉ | 12/135 [00:05<00:45, 2.69it/s]\nfaceClone:: 10%|▉ | 13/135 [00:05<00:44, 2.71it/s]\nfaceClone:: 10%|█ | 14/135 [00:06<00:44, 2.74it/s]\nfaceClone:: 11%|█ | 15/135 [00:06<00:44, 2.71it/s]\nfaceClone:: 12%|█▏ | 16/135 [00:06<00:44, 2.70it/s]\nfaceClone:: 13%|█▎ | 17/135 [00:07<00:43, 2.69it/s]\nfaceClone:: 13%|█▎ | 18/135 [00:07<00:43, 2.71it/s]\nfaceClone:: 14%|█▍ | 19/135 [00:08<00:42, 2.73it/s]\nfaceClone:: 15%|█▍ | 20/135 [00:08<00:42, 2.73it/s]\nfaceClone:: 16%|█▌ | 21/135 [00:08<00:43, 2.61it/s]\nfaceClone:: 16%|█▋ | 22/135 [00:09<00:44, 2.51it/s]\nfaceClone:: 17%|█▋ | 23/135 [00:09<00:44, 2.53it/s]\nfaceClone:: 18%|█▊ | 24/135 [00:09<00:42, 2.62it/s]\nfaceClone:: 19%|█▊ | 25/135 [00:10<00:41, 2.63it/s]\nfaceClone:: 19%|█▉ | 26/135 [00:10<00:41, 2.63it/s]\nfaceClone:: 20%|██ | 27/135 [00:11<00:40, 2.65it/s]\nfaceClone:: 21%|██ | 28/135 [00:11<00:40, 2.65it/s]\nfaceClone:: 21%|██▏ | 29/135 [00:11<00:40, 2.65it/s]\nfaceClone:: 22%|██▏ | 30/135 [00:12<00:39, 2.66it/s]\nfaceClone:: 23%|██▎ | 31/135 [00:12<00:38, 2.67it/s]\nfaceClone:: 24%|██▎ | 32/135 [00:12<00:38, 2.70it/s]\nfaceClone:: 24%|██▍ | 33/135 [00:13<00:37, 2.72it/s]\nfaceClone:: 25%|██▌ | 34/135 [00:13<00:36, 2.74it/s]\nfaceClone:: 26%|██▌ | 35/135 [00:14<00:36, 2.75it/s]\nfaceClone:: 27%|██▋ | 36/135 [00:14<00:36, 2.74it/s]\nfaceClone:: 27%|██▋ | 37/135 [00:14<00:35, 2.72it/s]\nfaceClone:: 28%|██▊ | 38/135 [00:15<00:35, 2.70it/s]\nfaceClone:: 29%|██▉ | 39/135 [00:15<00:35, 2.68it/s]\nfaceClone:: 30%|██▉ | 40/135 [00:15<00:35, 2.66it/s]\nfaceClone:: 30%|███ | 41/135 [00:16<00:35, 2.67it/s]\nfaceClone:: 31%|███ | 42/135 [00:16<00:35, 2.66it/s]\nfaceClone:: 32%|███▏ | 43/135 [00:17<00:34, 2.68it/s]\nfaceClone:: 33%|███▎ | 44/135 [00:17<00:33, 2.70it/s]\nfaceClone:: 33%|███▎ | 45/135 [00:17<00:33, 2.70it/s]\nfaceClone:: 34%|███▍ | 46/135 [00:18<00:32, 2.70it/s]\nfaceClone:: 35%|███▍ | 47/135 [00:18<00:33, 2.63it/s]\nfaceClone:: 36%|███▌ | 48/135 [00:18<00:34, 2.53it/s]\nfaceClone:: 36%|███▋ | 49/135 [00:19<00:33, 2.54it/s]\nfaceClone:: 37%|███▋ | 50/135 [00:19<00:32, 2.59it/s]\nfaceClone:: 38%|███▊ | 51/135 [00:20<00:32, 2.61it/s]\nfaceClone:: 39%|███▊ | 52/135 [00:20<00:31, 2.62it/s]\nfaceClone:: 39%|███▉ | 53/135 [00:20<00:31, 2.61it/s]\nfaceClone:: 40%|████ | 54/135 [00:21<00:30, 2.64it/s]\nfaceClone:: 41%|████ | 55/135 [00:21<00:30, 2.66it/s]\nfaceClone:: 41%|████▏ | 56/135 [00:21<00:29, 2.63it/s]\nfaceClone:: 42%|████▏ | 57/135 [00:22<00:29, 2.64it/s]\nfaceClone:: 43%|████▎ | 58/135 [00:22<00:29, 2.64it/s]\nfaceClone:: 44%|████▎ | 59/135 [00:23<00:28, 2.63it/s]\nfaceClone:: 44%|████▍ | 60/135 [00:23<00:29, 2.58it/s]\nfaceClone:: 45%|████▌ | 61/135 [00:23<00:29, 2.54it/s]\nfaceClone:: 46%|████▌ | 62/135 [00:24<00:28, 2.55it/s]\nfaceClone:: 47%|████▋ | 63/135 [00:24<00:28, 2.52it/s]\nfaceClone:: 47%|████▋ | 64/135 [00:25<00:28, 2.49it/s]\nfaceClone:: 48%|████▊ | 65/135 [00:25<00:29, 2.41it/s]\nfaceClone:: 49%|████▉ | 66/135 [00:26<00:28, 2.38it/s]\nfaceClone:: 50%|████▉ | 67/135 [00:26<00:28, 2.38it/s]\nfaceClone:: 50%|█████ | 68/135 [00:26<00:27, 2.39it/s]\nfaceClone:: 51%|█████ | 69/135 [00:27<00:27, 2.41it/s]\nfaceClone:: 52%|█████▏ | 70/135 [00:27<00:27, 2.40it/s]\nfaceClone:: 53%|█████▎ | 71/135 [00:28<00:25, 2.47it/s]\nfaceClone:: 53%|█████▎ | 72/135 [00:28<00:24, 2.52it/s]\nfaceClone:: 54%|█████▍ | 73/135 [00:28<00:24, 2.55it/s]\nfaceClone:: 55%|█████▍ | 74/135 [00:29<00:23, 2.57it/s]\nfaceClone:: 56%|█████▌ | 75/135 [00:29<00:23, 2.60it/s]\nfaceClone:: 56%|█████▋ | 76/135 [00:29<00:22, 2.62it/s]\nfaceClone:: 57%|█████▋ | 77/135 [00:30<00:23, 2.51it/s]\nfaceClone:: 58%|█████▊ | 78/135 [00:30<00:23, 2.47it/s]\nfaceClone:: 59%|█████▊ | 79/135 [00:31<00:22, 2.47it/s]\nfaceClone:: 59%|█████▉ | 80/135 [00:31<00:21, 2.53it/s]\nfaceClone:: 60%|██████ | 81/135 [00:31<00:21, 2.54it/s]\nfaceClone:: 61%|██████ | 82/135 [00:32<00:20, 2.58it/s]\nfaceClone:: 61%|██████▏ | 83/135 [00:32<00:20, 2.51it/s]\nfaceClone:: 62%|██████▏ | 84/135 [00:33<00:20, 2.43it/s]\nfaceClone:: 63%|██████▎ | 85/135 [00:33<00:20, 2.43it/s]\nfaceClone:: 64%|██████▎ | 86/135 [00:34<00:20, 2.40it/s]\nfaceClone:: 64%|██████▍ | 87/135 [00:34<00:20, 2.38it/s]\nfaceClone:: 65%|██████▌ | 88/135 [00:34<00:19, 2.37it/s]\nfaceClone:: 66%|██████▌ | 89/135 [00:35<00:19, 2.35it/s]\nfaceClone:: 67%|██████▋ | 90/135 [00:35<00:19, 2.35it/s]\nfaceClone:: 67%|██████▋ | 91/135 [00:36<00:18, 2.44it/s]\nfaceClone:: 68%|██████▊ | 92/135 [00:36<00:17, 2.50it/s]\nfaceClone:: 69%|██████▉ | 93/135 [00:36<00:16, 2.53it/s]\nfaceClone:: 70%|██████▉ | 94/135 [00:37<00:15, 2.57it/s]\nfaceClone:: 70%|███████ | 95/135 [00:37<00:15, 2.58it/s]\nfaceClone:: 71%|███████ | 96/135 [00:38<00:15, 2.58it/s]\nfaceClone:: 72%|███████▏ | 97/135 [00:38<00:14, 2.60it/s]\nfaceClone:: 73%|███████▎ | 98/135 [00:38<00:14, 2.62it/s]\nfaceClone:: 73%|███████▎ | 99/135 [00:39<00:13, 2.63it/s]\nfaceClone:: 74%|███████▍ | 100/135 [00:39<00:13, 2.61it/s]\nfaceClone:: 75%|███████▍ | 101/135 [00:39<00:12, 2.63it/s]\nfaceClone:: 76%|███████▌ | 102/135 [00:40<00:12, 2.64it/s]\nfaceClone:: 76%|███████▋ | 103/135 [00:40<00:12, 2.64it/s]\nfaceClone:: 77%|███████▋ | 104/135 [00:41<00:11, 2.66it/s]\nfaceClone:: 78%|███████▊ | 105/135 [00:41<00:11, 2.69it/s]\nfaceClone:: 79%|███████▊ | 106/135 [00:41<00:10, 2.67it/s]\nfaceClone:: 79%|███████▉ | 107/135 [00:42<00:10, 2.69it/s]\nfaceClone:: 80%|████████ | 108/135 [00:42<00:10, 2.68it/s]\nfaceClone:: 81%|████████ | 109/135 [00:42<00:09, 2.70it/s]\nfaceClone:: 81%|████████▏ | 110/135 [00:43<00:09, 2.67it/s]\nfaceClone:: 82%|████████▏ | 111/135 [00:43<00:08, 2.69it/s]\nfaceClone:: 83%|████████▎ | 112/135 [00:44<00:08, 2.66it/s]\nfaceClone:: 84%|████████▎ | 113/135 [00:44<00:08, 2.66it/s]\nfaceClone:: 84%|████████▍ | 114/135 [00:44<00:07, 2.66it/s]\nfaceClone:: 85%|████████▌ | 115/135 [00:45<00:07, 2.68it/s]\nfaceClone:: 86%|████████▌ | 116/135 [00:45<00:07, 2.64it/s]\nfaceClone:: 87%|████████▋ | 117/135 [00:45<00:06, 2.64it/s]\nfaceClone:: 87%|████████▋ | 118/135 [00:46<00:06, 2.66it/s]\nfaceClone:: 88%|████████▊ | 119/135 [00:46<00:05, 2.69it/s]\nfaceClone:: 89%|████████▉ | 120/135 [00:47<00:05, 2.70it/s]\nfaceClone:: 90%|████████▉ | 121/135 [00:47<00:05, 2.71it/s]\nfaceClone:: 90%|█████████ | 122/135 [00:47<00:04, 2.71it/s]\nfaceClone:: 91%|█████████ | 123/135 [00:48<00:04, 2.69it/s]\nfaceClone:: 92%|█████████▏| 124/135 [00:48<00:04, 2.71it/s]\nfaceClone:: 93%|█████████▎| 125/135 [00:48<00:03, 2.69it/s]\nfaceClone:: 93%|█████████▎| 126/135 [00:49<00:03, 2.70it/s]\nfaceClone:: 94%|█████████▍| 127/135 [00:49<00:02, 2.71it/s]\nfaceClone:: 95%|█████████▍| 128/135 [00:50<00:02, 2.71it/s]\nfaceClone:: 96%|█████████▌| 129/135 [00:50<00:02, 2.69it/s]\nfaceClone:: 96%|█████████▋| 130/135 [00:50<00:01, 2.69it/s]\nfaceClone:: 97%|█████████▋| 131/135 [00:51<00:01, 2.70it/s]\nfaceClone:: 98%|█████████▊| 132/135 [00:51<00:01, 2.67it/s]\nfaceClone:: 99%|█████████▊| 133/135 [00:51<00:00, 2.68it/s]\nfaceClone:: 99%|█████████▉| 134/135 [00:52<00:00, 2.64it/s]\nfaceClone:: 100%|██████████| 135/135 [00:52<00:00, 2.64it/s]\nfaceClone:: 100%|██████████| 135/135 [00:52<00:00, 2.56it/s]\nffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nInput #0, mov,mp4,m4a,3gp,3g2,mj2, from '4ce1cfac-74fa-4bbd-87f5-95ff48f17cfe.mp4':\nMetadata:\nmajor_brand : isom\nminor_version : 512\ncompatible_brands: isomiso2mp41\nencoder : Lavf59.27.100\nDuration: 00:00:05.40, start: 0.000000, bitrate: 600 kb/s\nStream #0:0(und): Video: mpeg4 (Simple Profile) (mp4v / 0x7634706D), yuv420p, 700x700 [SAR 1:1 DAR 1:1], 598 kb/s, 25 fps, 25 tbr, 12800 tbn, 25 tbc (default)\nMetadata:\nhandler_name : VideoHandler\nvendor_id : [0][0][0][0]\nGuessed Channel Layout for Input Stream #1.0 : mono\nInput #1, wav, from 'results/2024_01_09_11.01.46/tmpy824i3jtchinese_poem1.wav':\nDuration: 00:00:05.40, bitrate: 256 kb/s\nStream #1:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s\nStream mapping:\nStream #0:0 -> #0:0 (mpeg4 (native) -> h264 (libx264))\nStream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native))\nPress [q] to stop, [?] for help\n[libx264 @ 0x55c33629d900] using SAR=1/1\n[libx264 @ 0x55c33629d900] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2\n[libx264 @ 0x55c33629d900] profile High, level 3.1, 4:2:0, 8-bit\n[libx264 @ 0x55c33629d900] 264 - core 163 r3060 5db6aa6 - H.264/MPEG-4 AVC codec - Copyleft 2003-2021 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=15 lookahead_threads=2 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\nOutput #0, mp4, to 'results/2024_01_09_11.01.46/tmpiuycqk491##tmpy824i3jtchinese_poem1_full.mp4':\nMetadata:\nmajor_brand : isom\nminor_version : 512\ncompatible_brands: isomiso2mp41\nencoder : Lavf58.76.100\nStream #0:0(und): Video: h264 (avc1 / 0x31637661), yuv420p(progressive), 700x700 [SAR 1:1 DAR 1:1], q=2-31, 25 fps, 12800 tbn (default)\nMetadata:\nhandler_name : VideoHandler\nvendor_id : [0][0][0][0]\nencoder : Lavc58.134.100 libx264\nSide data:\ncpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\nStream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 16000 Hz, mono, fltp, 69 kb/s\nMetadata:\nencoder : Lavc58.134.100 aac\nframe= 1 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 135 fps=0.0 q=-1.0 Lsize= 281kB time=00:00:05.37 bitrate= 428.6kbits/s speed=11.2x\nvideo:233kB audio:44kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.691295%\n[libx264 @ 0x55c33629d900] frame I:1 Avg QP:18.57 size: 11753\n[libx264 @ 0x55c33629d900] frame P:58 Avg QP:20.29 size: 2937\n[libx264 @ 0x55c33629d900] frame B:76 Avg QP:22.27 size: 728\n[libx264 @ 0x55c33629d900] consecutive B-frames: 15.6% 26.7% 4.4% 53.3%\n[libx264 @ 0x55c33629d900] mb I I16..4: 29.2% 70.1% 0.6%\n[libx264 @ 0x55c33629d900] mb P I16..4: 1.3% 4.8% 0.1% P16..4: 27.3% 5.9% 2.8% 0.0% 0.0% skip:57.8%\n[libx264 @ 0x55c33629d900] mb B I16..4: 0.3% 1.0% 0.0% B16..8: 25.6% 0.6% 0.0% direct: 0.3% skip:72.1% L0:48.8% L1:50.5% BI: 0.7%\n[libx264 @ 0x55c33629d900] 8x8 transform intra:76.1% inter:89.4%\n[libx264 @ 0x55c33629d900] coded y,uvDC,uvAC intra: 34.0% 37.2% 3.7% inter: 3.5% 4.8% 0.0%\n[libx264 @ 0x55c33629d900] i16 v,h,dc,p: 40% 38% 15% 7%\n[libx264 @ 0x55c33629d900] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 29% 24% 40% 1% 1% 1% 1% 1% 1%\n[libx264 @ 0x55c33629d900] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 37% 29% 15% 2% 4% 3% 6% 2% 1%\n[libx264 @ 0x55c33629d900] i8c dc,h,v,p: 52% 24% 22% 2%\n[libx264 @ 0x55c33629d900] Weighted P-Frames: Y:0.0% UV:0.0%\n[libx264 @ 0x55c33629d900] ref P L0: 70.2% 6.3% 17.0% 6.5%\n[libx264 @ 0x55c33629d900] ref B L0: 79.2% 17.1% 3.7%\n[libx264 @ 0x55c33629d900] ref B L1: 96.0% 4.0%\n[libx264 @ 0x55c33629d900] kb/s:351.74\n[aac @ 0x55c33629f8c0] Qavg: 42759.586\nThe generated video is named results/2024_01_09_11.01.46/tmpiuycqk491##tmpy824i3jtchinese_poem1_full.mp4",
"metrics": {
"predict_time": 85.466151,
"total_time": 298.660913
},
"output": "https://replicate.delivery/pbxt/V4nS713QznroGBkIif1lAQVC7DSi9mikcZKfXb7VzBedPbVkA/out.mp4",
"started_at": "2024-01-09T11:01:45.310708Z",
"status": "succeeded",
"urls": {
"get": "https://api.replicate.com/v1/predictions/2gcqfr3byhq2zr7kxbc7q55oyy",
"cancel": "https://api.replicate.com/v1/predictions/2gcqfr3byhq2zr7kxbc7q55oyy/cancel"
},
"version": "9804d1827f20dbc994c64eac2ac2fd835670209ec8a3dc3f2429c2d847414b11"
}
Start Predictions...
3DMM Extraction for source image
landmark Det:: 0%| | 0/135 [00:00<?, ?it/s]
landmark Det:: 1%| | 1/135 [00:09<21:17, 9.53s/it]
landmark Det:: 1%|▏ | 2/135 [00:13<13:33, 6.11s/it]
landmark Det:: 6%|▌ | 8/135 [00:13<02:10, 1.03s/it]
landmark Det:: 10%|█ | 14/135 [00:13<00:58, 2.08it/s]
landmark Det:: 15%|█▍ | 20/135 [00:13<00:32, 3.59it/s]
landmark Det:: 19%|█▉ | 26/135 [00:13<00:19, 5.60it/s]
landmark Det:: 24%|██▎ | 32/135 [00:13<00:12, 8.20it/s]
landmark Det:: 28%|██▊ | 38/135 [00:13<00:08, 11.45it/s]
landmark Det:: 33%|███▎ | 44/135 [00:14<00:05, 15.38it/s]
landmark Det:: 37%|███▋ | 50/135 [00:14<00:04, 19.72it/s]
landmark Det:: 41%|████▏ | 56/135 [00:14<00:03, 24.29it/s]
landmark Det:: 46%|████▌ | 62/135 [00:14<00:02, 28.92it/s]
landmark Det:: 50%|█████ | 68/135 [00:14<00:02, 33.42it/s]
landmark Det:: 55%|█████▍ | 74/135 [00:14<00:01, 37.22it/s]
landmark Det:: 59%|█████▉ | 80/135 [00:14<00:01, 41.26it/s]
landmark Det:: 64%|██████▎ | 86/135 [00:14<00:01, 43.59it/s]
landmark Det:: 68%|██████▊ | 92/135 [00:15<00:00, 45.27it/s]
landmark Det:: 73%|███████▎ | 98/135 [00:15<00:00, 47.25it/s]
landmark Det:: 77%|███████▋ | 104/135 [00:15<00:00, 48.61it/s]
landmark Det:: 81%|████████▏ | 110/135 [00:15<00:00, 50.01it/s]
landmark Det:: 86%|████████▌ | 116/135 [00:15<00:00, 50.81it/s]
landmark Det:: 90%|█████████ | 122/135 [00:15<00:00, 50.96it/s]
landmark Det:: 95%|█████████▍| 128/135 [00:15<00:00, 50.16it/s]
landmark Det:: 99%|█████████▉| 134/135 [00:15<00:00, 49.98it/s]
landmark Det:: 100%|██████████| 135/135 [00:15<00:00, 8.52it/s]
3DMM Extraction In Video:: 0%| | 0/135 [00:00<?, ?it/s]
3DMM Extraction In Video:: 1%| | 1/135 [00:00<00:29, 4.59it/s]
3DMM Extraction In Video:: 9%|▉ | 12/135 [00:00<00:02, 45.03it/s]
3DMM Extraction In Video:: 17%|█▋ | 23/135 [00:00<00:01, 66.70it/s]
3DMM Extraction In Video:: 24%|██▍ | 33/135 [00:00<00:01, 76.58it/s]
3DMM Extraction In Video:: 33%|███▎ | 44/135 [00:00<00:01, 85.78it/s]
3DMM Extraction In Video:: 41%|████ | 55/135 [00:00<00:00, 91.91it/s]
3DMM Extraction In Video:: 50%|████▉ | 67/135 [00:00<00:00, 98.35it/s]
3DMM Extraction In Video:: 58%|█████▊ | 78/135 [00:00<00:00, 100.93it/s]
3DMM Extraction In Video:: 66%|██████▌ | 89/135 [00:01<00:00, 102.79it/s]
3DMM Extraction In Video:: 75%|███████▍ | 101/135 [00:01<00:00, 105.55it/s]
3DMM Extraction In Video:: 83%|████████▎ | 112/135 [00:01<00:00, 105.16it/s]
3DMM Extraction In Video:: 92%|█████████▏| 124/135 [00:01<00:00, 107.35it/s]
3DMM Extraction In Video:: 100%|██████████| 135/135 [00:01<00:00, 91.50it/s]
mel:: 0%| | 0/136 [00:00<?, ?it/s]
mel:: 100%|██████████| 136/136 [00:00<00:00, 39123.82it/s]
audio2exp:: 0%| | 0/14 [00:00<?, ?it/s]
audio2exp:: 57%|█████▋ | 8/14 [00:00<00:00, 78.85it/s]
audio2exp:: 100%|██████████| 14/14 [00:00<00:00, 81.42it/s]
Face Renderer:: 0%| | 0/136 [00:00<?, ?it/s]
Face Renderer:: 1%| | 1/136 [00:00<01:46, 1.27it/s]
Face Renderer:: 2%|▏ | 3/136 [00:00<00:32, 4.07it/s]
Face Renderer:: 4%|▎ | 5/136 [00:01<00:19, 6.58it/s]
Face Renderer:: 5%|▌ | 7/136 [00:01<00:14, 9.11it/s]
Face Renderer:: 7%|▋ | 9/136 [00:01<00:11, 11.30it/s]
Face Renderer:: 8%|▊ | 11/136 [00:01<00:09, 13.13it/s]
Face Renderer:: 10%|▉ | 13/136 [00:01<00:08, 14.55it/s]
Face Renderer:: 11%|█ | 15/136 [00:01<00:07, 15.70it/s]
Face Renderer:: 12%|█▎ | 17/136 [00:01<00:07, 16.53it/s]
Face Renderer:: 14%|█▍ | 19/136 [00:01<00:06, 17.15it/s]
Face Renderer:: 15%|█▌ | 21/136 [00:01<00:06, 17.59it/s]
Face Renderer:: 17%|█▋ | 23/136 [00:01<00:06, 17.89it/s]
Face Renderer:: 18%|█▊ | 25/136 [00:02<00:06, 18.06it/s]
Face Renderer:: 20%|█▉ | 27/136 [00:02<00:05, 18.31it/s]
Face Renderer:: 21%|██▏ | 29/136 [00:02<00:05, 18.44it/s]
Face Renderer:: 23%|██▎ | 31/136 [00:02<00:05, 18.53it/s]
Face Renderer:: 24%|██▍ | 33/136 [00:02<00:05, 18.61it/s]
Face Renderer:: 26%|██▌ | 35/136 [00:02<00:05, 18.59it/s]
Face Renderer:: 27%|██▋ | 37/136 [00:02<00:05, 18.63it/s]
Face Renderer:: 29%|██▊ | 39/136 [00:02<00:05, 18.51it/s]
Face Renderer:: 30%|███ | 41/136 [00:02<00:05, 18.59it/s]
Face Renderer:: 32%|███▏ | 43/136 [00:03<00:04, 18.64it/s]
Face Renderer:: 33%|███▎ | 45/136 [00:03<00:04, 18.68it/s]
Face Renderer:: 35%|███▍ | 47/136 [00:03<00:04, 18.70it/s]
Face Renderer:: 36%|███▌ | 49/136 [00:03<00:04, 18.70it/s]
Face Renderer:: 38%|███▊ | 51/136 [00:03<00:04, 18.69it/s]
Face Renderer:: 39%|███▉ | 53/136 [00:03<00:04, 18.72it/s]
Face Renderer:: 40%|████ | 55/136 [00:03<00:04, 18.51it/s]
Face Renderer:: 42%|████▏ | 57/136 [00:03<00:04, 18.68it/s]
Face Renderer:: 43%|████▎ | 59/136 [00:03<00:04, 18.66it/s]
Face Renderer:: 45%|████▍ | 61/136 [00:04<00:04, 18.59it/s]
Face Renderer:: 46%|████▋ | 63/136 [00:04<00:03, 18.57it/s]
Face Renderer:: 48%|████▊ | 65/136 [00:04<00:03, 18.64it/s]
Face Renderer:: 49%|████▉ | 67/136 [00:04<00:03, 18.65it/s]
Face Renderer:: 51%|█████ | 69/136 [00:04<00:03, 18.69it/s]
Face Renderer:: 52%|█████▏ | 71/136 [00:04<00:03, 18.68it/s]
Face Renderer:: 54%|█████▎ | 73/136 [00:04<00:03, 18.71it/s]
Face Renderer:: 55%|█████▌ | 75/136 [00:04<00:03, 18.73it/s]
Face Renderer:: 57%|█████▋ | 77/136 [00:04<00:03, 18.68it/s]
Face Renderer:: 58%|█████▊ | 79/136 [00:04<00:03, 18.69it/s]
Face Renderer:: 60%|█████▉ | 81/136 [00:05<00:02, 18.72it/s]
Face Renderer:: 61%|██████ | 83/136 [00:05<00:02, 18.76it/s]
Face Renderer:: 62%|██████▎ | 85/136 [00:05<00:02, 18.73it/s]
Face Renderer:: 64%|██████▍ | 87/136 [00:05<00:02, 18.49it/s]
Face Renderer:: 65%|██████▌ | 89/136 [00:05<00:02, 18.53it/s]
Face Renderer:: 67%|██████▋ | 91/136 [00:05<00:02, 18.55it/s]
Face Renderer:: 68%|██████▊ | 93/136 [00:05<00:02, 18.63it/s]
Face Renderer:: 70%|██████▉ | 95/136 [00:05<00:02, 18.68it/s]
Face Renderer:: 71%|███████▏ | 97/136 [00:05<00:02, 18.70it/s]
Face Renderer:: 73%|███████▎ | 99/136 [00:06<00:01, 18.72it/s]
Face Renderer:: 74%|███████▍ | 101/136 [00:06<00:01, 18.71it/s]
Face Renderer:: 76%|███████▌ | 103/136 [00:06<00:01, 18.77it/s]
Face Renderer:: 77%|███████▋ | 105/136 [00:06<00:01, 18.74it/s]
Face Renderer:: 79%|███████▊ | 107/136 [00:06<00:01, 18.74it/s]
Face Renderer:: 80%|████████ | 109/136 [00:06<00:01, 18.62it/s]
Face Renderer:: 82%|████████▏ | 111/136 [00:06<00:01, 18.65it/s]
Face Renderer:: 83%|████████▎ | 113/136 [00:06<00:01, 18.44it/s]
Face Renderer:: 85%|████████▍ | 115/136 [00:06<00:01, 18.46it/s]
Face Renderer:: 86%|████████▌ | 117/136 [00:07<00:01, 18.53it/s]
Face Renderer:: 88%|████████▊ | 119/136 [00:07<00:00, 18.59it/s]
Face Renderer:: 89%|████████▉ | 121/136 [00:07<00:00, 18.65it/s]
Face Renderer:: 90%|█████████ | 123/136 [00:07<00:00, 18.64it/s]
Face Renderer:: 92%|█████████▏| 125/136 [00:07<00:00, 18.63it/s]
Face Renderer:: 93%|█████████▎| 127/136 [00:07<00:00, 18.58it/s]
Face Renderer:: 95%|█████████▍| 129/136 [00:07<00:00, 18.53it/s]
Face Renderer:: 96%|█████████▋| 131/136 [00:07<00:00, 18.54it/s]
Face Renderer:: 98%|█████████▊| 133/136 [00:07<00:00, 18.63it/s]
Face Renderer:: 99%|█████████▉| 135/136 [00:07<00:00, 18.68it/s]
Face Renderer:: 99%|█████████▉| 135/136 [00:07<00:00, 16.89it/s]
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil 56. 70.100 / 56. 70.100
libavcodec 58.134.100 / 58.134.100
libavformat 58. 76.100 / 58. 76.100
libavdevice 58. 13.100 / 58. 13.100
libavfilter 7.110.100 / 7.110.100
libswscale 5. 9.100 / 5. 9.100
libswresample 3. 9.100 / 3. 9.100
libpostproc 55. 9.100 / 55. 9.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'results/2024_01_09_11.01.46/temp_tmpiuycqk491##tmpy824i3jtchinese_poem1.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf58.29.100
Duration: 00:00:05.40, start: 0.000000, bitrate: 69 kb/s
Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 256x256, 66 kb/s, 25 fps, 25 tbr, 12800 tbn, 50 tbc (default)
Metadata:
handler_name : VideoHandler
vendor_id : [0][0][0][0]
Guessed Channel Layout for Input Stream #1.0 : mono
Input #1, wav, from 'results/2024_01_09_11.01.46/tmpy824i3jtchinese_poem1.wav':
Duration: 00:00:05.40, bitrate: 256 kb/s
Stream #1:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (copy)
Stream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native))
Press [q] to stop, [?] for help
Output #0, mp4, to 'bab057ca-1797-4081-af8f-efd4d5d799ca.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf58.76.100
Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 256x256, q=2-31, 66 kb/s, 25 fps, 25 tbr, 12800 tbn, 12800 tbc (default)
Metadata:
handler_name : VideoHandler
vendor_id : [0][0][0][0]
Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 16000 Hz, mono, fltp, 69 kb/s
Metadata:
encoder : Lavc58.134.100 aac
frame= 0 fps=0.0 q=-1.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x
frame= 135 fps=0.0 q=-1.0 Lsize= 92kB time=00:00:05.37 bitrate= 140.8kbits/s speed= 308x
video:44kB audio:44kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 5.446096%
[aac @ 0x5563e2ed36c0] Qavg: 42759.586
The generated video is named tmpiuycqk491##tmpy824i3jtchinese_poem1.mp4 in results/2024_01_09_11.01.46
OpenCV: FFMPEG: tag 0x5634504d/'MP4V' is not supported with codec id 12 and format 'mp4 / MP4 (MPEG-4 Part 14)'
OpenCV: FFMPEG: fallback to use tag 0x7634706d/'mp4v'
faceClone:: 0%| | 0/135 [00:00<?, ?it/s]
faceClone:: 1%| | 1/135 [00:01<03:09, 1.41s/it]
faceClone:: 1%|▏ | 2/135 [00:01<01:45, 1.27it/s]
faceClone:: 2%|▏ | 3/135 [00:02<01:18, 1.68it/s]
faceClone:: 3%|▎ | 4/135 [00:02<01:05, 2.00it/s]
faceClone:: 4%|▎ | 5/135 [00:02<00:59, 2.20it/s]
faceClone:: 4%|▍ | 6/135 [00:03<00:55, 2.34it/s]
faceClone:: 5%|▌ | 7/135 [00:03<00:52, 2.44it/s]
faceClone:: 6%|▌ | 8/135 [00:03<00:50, 2.53it/s]
faceClone:: 7%|▋ | 9/135 [00:04<00:48, 2.59it/s]
faceClone:: 7%|▋ | 10/135 [00:04<00:47, 2.61it/s]
faceClone:: 8%|▊ | 11/135 [00:05<00:46, 2.66it/s]
faceClone:: 9%|▉ | 12/135 [00:05<00:45, 2.69it/s]
faceClone:: 10%|▉ | 13/135 [00:05<00:44, 2.71it/s]
faceClone:: 10%|█ | 14/135 [00:06<00:44, 2.74it/s]
faceClone:: 11%|█ | 15/135 [00:06<00:44, 2.71it/s]
faceClone:: 12%|█▏ | 16/135 [00:06<00:44, 2.70it/s]
faceClone:: 13%|█▎ | 17/135 [00:07<00:43, 2.69it/s]
faceClone:: 13%|█▎ | 18/135 [00:07<00:43, 2.71it/s]
faceClone:: 14%|█▍ | 19/135 [00:08<00:42, 2.73it/s]
faceClone:: 15%|█▍ | 20/135 [00:08<00:42, 2.73it/s]
faceClone:: 16%|█▌ | 21/135 [00:08<00:43, 2.61it/s]
faceClone:: 16%|█▋ | 22/135 [00:09<00:44, 2.51it/s]
faceClone:: 17%|█▋ | 23/135 [00:09<00:44, 2.53it/s]
faceClone:: 18%|█▊ | 24/135 [00:09<00:42, 2.62it/s]
faceClone:: 19%|█▊ | 25/135 [00:10<00:41, 2.63it/s]
faceClone:: 19%|█▉ | 26/135 [00:10<00:41, 2.63it/s]
faceClone:: 20%|██ | 27/135 [00:11<00:40, 2.65it/s]
faceClone:: 21%|██ | 28/135 [00:11<00:40, 2.65it/s]
faceClone:: 21%|██▏ | 29/135 [00:11<00:40, 2.65it/s]
faceClone:: 22%|██▏ | 30/135 [00:12<00:39, 2.66it/s]
faceClone:: 23%|██▎ | 31/135 [00:12<00:38, 2.67it/s]
faceClone:: 24%|██▎ | 32/135 [00:12<00:38, 2.70it/s]
faceClone:: 24%|██▍ | 33/135 [00:13<00:37, 2.72it/s]
faceClone:: 25%|██▌ | 34/135 [00:13<00:36, 2.74it/s]
faceClone:: 26%|██▌ | 35/135 [00:14<00:36, 2.75it/s]
faceClone:: 27%|██▋ | 36/135 [00:14<00:36, 2.74it/s]
faceClone:: 27%|██▋ | 37/135 [00:14<00:35, 2.72it/s]
faceClone:: 28%|██▊ | 38/135 [00:15<00:35, 2.70it/s]
faceClone:: 29%|██▉ | 39/135 [00:15<00:35, 2.68it/s]
faceClone:: 30%|██▉ | 40/135 [00:15<00:35, 2.66it/s]
faceClone:: 30%|███ | 41/135 [00:16<00:35, 2.67it/s]
faceClone:: 31%|███ | 42/135 [00:16<00:35, 2.66it/s]
faceClone:: 32%|███▏ | 43/135 [00:17<00:34, 2.68it/s]
faceClone:: 33%|███▎ | 44/135 [00:17<00:33, 2.70it/s]
faceClone:: 33%|███▎ | 45/135 [00:17<00:33, 2.70it/s]
faceClone:: 34%|███▍ | 46/135 [00:18<00:32, 2.70it/s]
faceClone:: 35%|███▍ | 47/135 [00:18<00:33, 2.63it/s]
faceClone:: 36%|███▌ | 48/135 [00:18<00:34, 2.53it/s]
faceClone:: 36%|███▋ | 49/135 [00:19<00:33, 2.54it/s]
faceClone:: 37%|███▋ | 50/135 [00:19<00:32, 2.59it/s]
faceClone:: 38%|███▊ | 51/135 [00:20<00:32, 2.61it/s]
faceClone:: 39%|███▊ | 52/135 [00:20<00:31, 2.62it/s]
faceClone:: 39%|███▉ | 53/135 [00:20<00:31, 2.61it/s]
faceClone:: 40%|████ | 54/135 [00:21<00:30, 2.64it/s]
faceClone:: 41%|████ | 55/135 [00:21<00:30, 2.66it/s]
faceClone:: 41%|████▏ | 56/135 [00:21<00:29, 2.63it/s]
faceClone:: 42%|████▏ | 57/135 [00:22<00:29, 2.64it/s]
faceClone:: 43%|████▎ | 58/135 [00:22<00:29, 2.64it/s]
faceClone:: 44%|████▎ | 59/135 [00:23<00:28, 2.63it/s]
faceClone:: 44%|████▍ | 60/135 [00:23<00:29, 2.58it/s]
faceClone:: 45%|████▌ | 61/135 [00:23<00:29, 2.54it/s]
faceClone:: 46%|████▌ | 62/135 [00:24<00:28, 2.55it/s]
faceClone:: 47%|████▋ | 63/135 [00:24<00:28, 2.52it/s]
faceClone:: 47%|████▋ | 64/135 [00:25<00:28, 2.49it/s]
faceClone:: 48%|████▊ | 65/135 [00:25<00:29, 2.41it/s]
faceClone:: 49%|████▉ | 66/135 [00:26<00:28, 2.38it/s]
faceClone:: 50%|████▉ | 67/135 [00:26<00:28, 2.38it/s]
faceClone:: 50%|█████ | 68/135 [00:26<00:27, 2.39it/s]
faceClone:: 51%|█████ | 69/135 [00:27<00:27, 2.41it/s]
faceClone:: 52%|█████▏ | 70/135 [00:27<00:27, 2.40it/s]
faceClone:: 53%|█████▎ | 71/135 [00:28<00:25, 2.47it/s]
faceClone:: 53%|█████▎ | 72/135 [00:28<00:24, 2.52it/s]
faceClone:: 54%|█████▍ | 73/135 [00:28<00:24, 2.55it/s]
faceClone:: 55%|█████▍ | 74/135 [00:29<00:23, 2.57it/s]
faceClone:: 56%|█████▌ | 75/135 [00:29<00:23, 2.60it/s]
faceClone:: 56%|█████▋ | 76/135 [00:29<00:22, 2.62it/s]
faceClone:: 57%|█████▋ | 77/135 [00:30<00:23, 2.51it/s]
faceClone:: 58%|█████▊ | 78/135 [00:30<00:23, 2.47it/s]
faceClone:: 59%|█████▊ | 79/135 [00:31<00:22, 2.47it/s]
faceClone:: 59%|█████▉ | 80/135 [00:31<00:21, 2.53it/s]
faceClone:: 60%|██████ | 81/135 [00:31<00:21, 2.54it/s]
faceClone:: 61%|██████ | 82/135 [00:32<00:20, 2.58it/s]
faceClone:: 61%|██████▏ | 83/135 [00:32<00:20, 2.51it/s]
faceClone:: 62%|██████▏ | 84/135 [00:33<00:20, 2.43it/s]
faceClone:: 63%|██████▎ | 85/135 [00:33<00:20, 2.43it/s]
faceClone:: 64%|██████▎ | 86/135 [00:34<00:20, 2.40it/s]
faceClone:: 64%|██████▍ | 87/135 [00:34<00:20, 2.38it/s]
faceClone:: 65%|██████▌ | 88/135 [00:34<00:19, 2.37it/s]
faceClone:: 66%|██████▌ | 89/135 [00:35<00:19, 2.35it/s]
faceClone:: 67%|██████▋ | 90/135 [00:35<00:19, 2.35it/s]
faceClone:: 67%|██████▋ | 91/135 [00:36<00:18, 2.44it/s]
faceClone:: 68%|██████▊ | 92/135 [00:36<00:17, 2.50it/s]
faceClone:: 69%|██████▉ | 93/135 [00:36<00:16, 2.53it/s]
faceClone:: 70%|██████▉ | 94/135 [00:37<00:15, 2.57it/s]
faceClone:: 70%|███████ | 95/135 [00:37<00:15, 2.58it/s]
faceClone:: 71%|███████ | 96/135 [00:38<00:15, 2.58it/s]
faceClone:: 72%|███████▏ | 97/135 [00:38<00:14, 2.60it/s]
faceClone:: 73%|███████▎ | 98/135 [00:38<00:14, 2.62it/s]
faceClone:: 73%|███████▎ | 99/135 [00:39<00:13, 2.63it/s]
faceClone:: 74%|███████▍ | 100/135 [00:39<00:13, 2.61it/s]
faceClone:: 75%|███████▍ | 101/135 [00:39<00:12, 2.63it/s]
faceClone:: 76%|███████▌ | 102/135 [00:40<00:12, 2.64it/s]
faceClone:: 76%|███████▋ | 103/135 [00:40<00:12, 2.64it/s]
faceClone:: 77%|███████▋ | 104/135 [00:41<00:11, 2.66it/s]
faceClone:: 78%|███████▊ | 105/135 [00:41<00:11, 2.69it/s]
faceClone:: 79%|███████▊ | 106/135 [00:41<00:10, 2.67it/s]
faceClone:: 79%|███████▉ | 107/135 [00:42<00:10, 2.69it/s]
faceClone:: 80%|████████ | 108/135 [00:42<00:10, 2.68it/s]
faceClone:: 81%|████████ | 109/135 [00:42<00:09, 2.70it/s]
faceClone:: 81%|████████▏ | 110/135 [00:43<00:09, 2.67it/s]
faceClone:: 82%|████████▏ | 111/135 [00:43<00:08, 2.69it/s]
faceClone:: 83%|████████▎ | 112/135 [00:44<00:08, 2.66it/s]
faceClone:: 84%|████████▎ | 113/135 [00:44<00:08, 2.66it/s]
faceClone:: 84%|████████▍ | 114/135 [00:44<00:07, 2.66it/s]
faceClone:: 85%|████████▌ | 115/135 [00:45<00:07, 2.68it/s]
faceClone:: 86%|████████▌ | 116/135 [00:45<00:07, 2.64it/s]
faceClone:: 87%|████████▋ | 117/135 [00:45<00:06, 2.64it/s]
faceClone:: 87%|████████▋ | 118/135 [00:46<00:06, 2.66it/s]
faceClone:: 88%|████████▊ | 119/135 [00:46<00:05, 2.69it/s]
faceClone:: 89%|████████▉ | 120/135 [00:47<00:05, 2.70it/s]
faceClone:: 90%|████████▉ | 121/135 [00:47<00:05, 2.71it/s]
faceClone:: 90%|█████████ | 122/135 [00:47<00:04, 2.71it/s]
faceClone:: 91%|█████████ | 123/135 [00:48<00:04, 2.69it/s]
faceClone:: 92%|█████████▏| 124/135 [00:48<00:04, 2.71it/s]
faceClone:: 93%|█████████▎| 125/135 [00:48<00:03, 2.69it/s]
faceClone:: 93%|█████████▎| 126/135 [00:49<00:03, 2.70it/s]
faceClone:: 94%|█████████▍| 127/135 [00:49<00:02, 2.71it/s]
faceClone:: 95%|█████████▍| 128/135 [00:50<00:02, 2.71it/s]
faceClone:: 96%|█████████▌| 129/135 [00:50<00:02, 2.69it/s]
faceClone:: 96%|█████████▋| 130/135 [00:50<00:01, 2.69it/s]
faceClone:: 97%|█████████▋| 131/135 [00:51<00:01, 2.70it/s]
faceClone:: 98%|█████████▊| 132/135 [00:51<00:01, 2.67it/s]
faceClone:: 99%|█████████▊| 133/135 [00:51<00:00, 2.68it/s]
faceClone:: 99%|█████████▉| 134/135 [00:52<00:00, 2.64it/s]
faceClone:: 100%|██████████| 135/135 [00:52<00:00, 2.64it/s]
faceClone:: 100%|██████████| 135/135 [00:52<00:00, 2.56it/s]
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil 56. 70.100 / 56. 70.100
libavcodec 58.134.100 / 58.134.100
libavformat 58. 76.100 / 58. 76.100
libavdevice 58. 13.100 / 58. 13.100
libavfilter 7.110.100 / 7.110.100
libswscale 5. 9.100 / 5. 9.100
libswresample 3. 9.100 / 3. 9.100
libpostproc 55. 9.100 / 55. 9.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from '4ce1cfac-74fa-4bbd-87f5-95ff48f17cfe.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2mp41
encoder : Lavf59.27.100
Duration: 00:00:05.40, start: 0.000000, bitrate: 600 kb/s
Stream #0:0(und): Video: mpeg4 (Simple Profile) (mp4v / 0x7634706D), yuv420p, 700x700 [SAR 1:1 DAR 1:1], 598 kb/s, 25 fps, 25 tbr, 12800 tbn, 25 tbc (default)
Metadata:
handler_name : VideoHandler
vendor_id : [0][0][0][0]
Guessed Channel Layout for Input Stream #1.0 : mono
Input #1, wav, from 'results/2024_01_09_11.01.46/tmpy824i3jtchinese_poem1.wav':
Duration: 00:00:05.40, bitrate: 256 kb/s
Stream #1:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (mpeg4 (native) -> h264 (libx264))
Stream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native))
Press [q] to stop, [?] for help
[libx264 @ 0x55c33629d900] using SAR=1/1
[libx264 @ 0x55c33629d900] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2
[libx264 @ 0x55c33629d900] profile High, level 3.1, 4:2:0, 8-bit
[libx264 @ 0x55c33629d900] 264 - core 163 r3060 5db6aa6 - H.264/MPEG-4 AVC codec - Copyleft 2003-2021 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=15 lookahead_threads=2 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00
Output #0, mp4, to 'results/2024_01_09_11.01.46/tmpiuycqk491##tmpy824i3jtchinese_poem1_full.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2mp41
encoder : Lavf58.76.100
Stream #0:0(und): Video: h264 (avc1 / 0x31637661), yuv420p(progressive), 700x700 [SAR 1:1 DAR 1:1], q=2-31, 25 fps, 12800 tbn (default)
Metadata:
handler_name : VideoHandler
vendor_id : [0][0][0][0]
encoder : Lavc58.134.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A
Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 16000 Hz, mono, fltp, 69 kb/s
Metadata:
encoder : Lavc58.134.100 aac
frame= 1 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x
frame= 135 fps=0.0 q=-1.0 Lsize= 281kB time=00:00:05.37 bitrate= 428.6kbits/s speed=11.2x
video:233kB audio:44kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.691295%
[libx264 @ 0x55c33629d900] frame I:1 Avg QP:18.57 size: 11753
[libx264 @ 0x55c33629d900] frame P:58 Avg QP:20.29 size: 2937
[libx264 @ 0x55c33629d900] frame B:76 Avg QP:22.27 size: 728
[libx264 @ 0x55c33629d900] consecutive B-frames: 15.6% 26.7% 4.4% 53.3%
[libx264 @ 0x55c33629d900] mb I I16..4: 29.2% 70.1% 0.6%
[libx264 @ 0x55c33629d900] mb P I16..4: 1.3% 4.8% 0.1% P16..4: 27.3% 5.9% 2.8% 0.0% 0.0% skip:57.8%
[libx264 @ 0x55c33629d900] mb B I16..4: 0.3% 1.0% 0.0% B16..8: 25.6% 0.6% 0.0% direct: 0.3% skip:72.1% L0:48.8% L1:50.5% BI: 0.7%
[libx264 @ 0x55c33629d900] 8x8 transform intra:76.1% inter:89.4%
[libx264 @ 0x55c33629d900] coded y,uvDC,uvAC intra: 34.0% 37.2% 3.7% inter: 3.5% 4.8% 0.0%
[libx264 @ 0x55c33629d900] i16 v,h,dc,p: 40% 38% 15% 7%
[libx264 @ 0x55c33629d900] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 29% 24% 40% 1% 1% 1% 1% 1% 1%
[libx264 @ 0x55c33629d900] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 37% 29% 15% 2% 4% 3% 6% 2% 1%
[libx264 @ 0x55c33629d900] i8c dc,h,v,p: 52% 24% 22% 2%
[libx264 @ 0x55c33629d900] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x55c33629d900] ref P L0: 70.2% 6.3% 17.0% 6.5%
[libx264 @ 0x55c33629d900] ref B L0: 79.2% 17.1% 3.7%
[libx264 @ 0x55c33629d900] ref B L1: 96.0% 4.0%
[libx264 @ 0x55c33629d900] kb/s:351.74
[aac @ 0x55c33629f8c0] Qavg: 42759.586
The generated video is named results/2024_01_09_11.01.46/tmpiuycqk491##tmpy824i3jtchinese_poem1_full.mp4
This model costs approximately $0.27 to run on Replicate, or 3 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.
This model runs on Nvidia L40S GPU hardware. Predictions typically complete within 5 minutes. The predict time for this model varies significantly based on the inputs.
This model doesn't have a readme.
This model is cold. You'll get a fast response if the model is warm and already running, and a slower response if the model is cold and starting up.
Choose a file from your machine
Hint: you can also drag files onto the input
Choose a file from your machine
Hint: you can also drag files onto the input
Start Predictions...
3DMM Extraction for source image
landmark Det:: 0%| | 0/135 [00:00<?, ?it/s]
landmark Det:: 1%| | 1/135 [00:09<21:17, 9.53s/it]
landmark Det:: 1%|▏ | 2/135 [00:13<13:33, 6.11s/it]
landmark Det:: 6%|▌ | 8/135 [00:13<02:10, 1.03s/it]
landmark Det:: 10%|█ | 14/135 [00:13<00:58, 2.08it/s]
landmark Det:: 15%|█▍ | 20/135 [00:13<00:32, 3.59it/s]
landmark Det:: 19%|█▉ | 26/135 [00:13<00:19, 5.60it/s]
landmark Det:: 24%|██▎ | 32/135 [00:13<00:12, 8.20it/s]
landmark Det:: 28%|██▊ | 38/135 [00:13<00:08, 11.45it/s]
landmark Det:: 33%|███▎ | 44/135 [00:14<00:05, 15.38it/s]
landmark Det:: 37%|███▋ | 50/135 [00:14<00:04, 19.72it/s]
landmark Det:: 41%|████▏ | 56/135 [00:14<00:03, 24.29it/s]
landmark Det:: 46%|████▌ | 62/135 [00:14<00:02, 28.92it/s]
landmark Det:: 50%|█████ | 68/135 [00:14<00:02, 33.42it/s]
landmark Det:: 55%|█████▍ | 74/135 [00:14<00:01, 37.22it/s]
landmark Det:: 59%|█████▉ | 80/135 [00:14<00:01, 41.26it/s]
landmark Det:: 64%|██████▎ | 86/135 [00:14<00:01, 43.59it/s]
landmark Det:: 68%|██████▊ | 92/135 [00:15<00:00, 45.27it/s]
landmark Det:: 73%|███████▎ | 98/135 [00:15<00:00, 47.25it/s]
landmark Det:: 77%|███████▋ | 104/135 [00:15<00:00, 48.61it/s]
landmark Det:: 81%|████████▏ | 110/135 [00:15<00:00, 50.01it/s]
landmark Det:: 86%|████████▌ | 116/135 [00:15<00:00, 50.81it/s]
landmark Det:: 90%|█████████ | 122/135 [00:15<00:00, 50.96it/s]
landmark Det:: 95%|█████████▍| 128/135 [00:15<00:00, 50.16it/s]
landmark Det:: 99%|█████████▉| 134/135 [00:15<00:00, 49.98it/s]
landmark Det:: 100%|██████████| 135/135 [00:15<00:00, 8.52it/s]
3DMM Extraction In Video:: 0%| | 0/135 [00:00<?, ?it/s]
3DMM Extraction In Video:: 1%| | 1/135 [00:00<00:29, 4.59it/s]
3DMM Extraction In Video:: 9%|▉ | 12/135 [00:00<00:02, 45.03it/s]
3DMM Extraction In Video:: 17%|█▋ | 23/135 [00:00<00:01, 66.70it/s]
3DMM Extraction In Video:: 24%|██▍ | 33/135 [00:00<00:01, 76.58it/s]
3DMM Extraction In Video:: 33%|███▎ | 44/135 [00:00<00:01, 85.78it/s]
3DMM Extraction In Video:: 41%|████ | 55/135 [00:00<00:00, 91.91it/s]
3DMM Extraction In Video:: 50%|████▉ | 67/135 [00:00<00:00, 98.35it/s]
3DMM Extraction In Video:: 58%|█████▊ | 78/135 [00:00<00:00, 100.93it/s]
3DMM Extraction In Video:: 66%|██████▌ | 89/135 [00:01<00:00, 102.79it/s]
3DMM Extraction In Video:: 75%|███████▍ | 101/135 [00:01<00:00, 105.55it/s]
3DMM Extraction In Video:: 83%|████████▎ | 112/135 [00:01<00:00, 105.16it/s]
3DMM Extraction In Video:: 92%|█████████▏| 124/135 [00:01<00:00, 107.35it/s]
3DMM Extraction In Video:: 100%|██████████| 135/135 [00:01<00:00, 91.50it/s]
mel:: 0%| | 0/136 [00:00<?, ?it/s]
mel:: 100%|██████████| 136/136 [00:00<00:00, 39123.82it/s]
audio2exp:: 0%| | 0/14 [00:00<?, ?it/s]
audio2exp:: 57%|█████▋ | 8/14 [00:00<00:00, 78.85it/s]
audio2exp:: 100%|██████████| 14/14 [00:00<00:00, 81.42it/s]
Face Renderer:: 0%| | 0/136 [00:00<?, ?it/s]
Face Renderer:: 1%| | 1/136 [00:00<01:46, 1.27it/s]
Face Renderer:: 2%|▏ | 3/136 [00:00<00:32, 4.07it/s]
Face Renderer:: 4%|▎ | 5/136 [00:01<00:19, 6.58it/s]
Face Renderer:: 5%|▌ | 7/136 [00:01<00:14, 9.11it/s]
Face Renderer:: 7%|▋ | 9/136 [00:01<00:11, 11.30it/s]
Face Renderer:: 8%|▊ | 11/136 [00:01<00:09, 13.13it/s]
Face Renderer:: 10%|▉ | 13/136 [00:01<00:08, 14.55it/s]
Face Renderer:: 11%|█ | 15/136 [00:01<00:07, 15.70it/s]
Face Renderer:: 12%|█▎ | 17/136 [00:01<00:07, 16.53it/s]
Face Renderer:: 14%|█▍ | 19/136 [00:01<00:06, 17.15it/s]
Face Renderer:: 15%|█▌ | 21/136 [00:01<00:06, 17.59it/s]
Face Renderer:: 17%|█▋ | 23/136 [00:01<00:06, 17.89it/s]
Face Renderer:: 18%|█▊ | 25/136 [00:02<00:06, 18.06it/s]
Face Renderer:: 20%|█▉ | 27/136 [00:02<00:05, 18.31it/s]
Face Renderer:: 21%|██▏ | 29/136 [00:02<00:05, 18.44it/s]
Face Renderer:: 23%|██▎ | 31/136 [00:02<00:05, 18.53it/s]
Face Renderer:: 24%|██▍ | 33/136 [00:02<00:05, 18.61it/s]
Face Renderer:: 26%|██▌ | 35/136 [00:02<00:05, 18.59it/s]
Face Renderer:: 27%|██▋ | 37/136 [00:02<00:05, 18.63it/s]
Face Renderer:: 29%|██▊ | 39/136 [00:02<00:05, 18.51it/s]
Face Renderer:: 30%|███ | 41/136 [00:02<00:05, 18.59it/s]
Face Renderer:: 32%|███▏ | 43/136 [00:03<00:04, 18.64it/s]
Face Renderer:: 33%|███▎ | 45/136 [00:03<00:04, 18.68it/s]
Face Renderer:: 35%|███▍ | 47/136 [00:03<00:04, 18.70it/s]
Face Renderer:: 36%|███▌ | 49/136 [00:03<00:04, 18.70it/s]
Face Renderer:: 38%|███▊ | 51/136 [00:03<00:04, 18.69it/s]
Face Renderer:: 39%|███▉ | 53/136 [00:03<00:04, 18.72it/s]
Face Renderer:: 40%|████ | 55/136 [00:03<00:04, 18.51it/s]
Face Renderer:: 42%|████▏ | 57/136 [00:03<00:04, 18.68it/s]
Face Renderer:: 43%|████▎ | 59/136 [00:03<00:04, 18.66it/s]
Face Renderer:: 45%|████▍ | 61/136 [00:04<00:04, 18.59it/s]
Face Renderer:: 46%|████▋ | 63/136 [00:04<00:03, 18.57it/s]
Face Renderer:: 48%|████▊ | 65/136 [00:04<00:03, 18.64it/s]
Face Renderer:: 49%|████▉ | 67/136 [00:04<00:03, 18.65it/s]
Face Renderer:: 51%|█████ | 69/136 [00:04<00:03, 18.69it/s]
Face Renderer:: 52%|█████▏ | 71/136 [00:04<00:03, 18.68it/s]
Face Renderer:: 54%|█████▎ | 73/136 [00:04<00:03, 18.71it/s]
Face Renderer:: 55%|█████▌ | 75/136 [00:04<00:03, 18.73it/s]
Face Renderer:: 57%|█████▋ | 77/136 [00:04<00:03, 18.68it/s]
Face Renderer:: 58%|█████▊ | 79/136 [00:04<00:03, 18.69it/s]
Face Renderer:: 60%|█████▉ | 81/136 [00:05<00:02, 18.72it/s]
Face Renderer:: 61%|██████ | 83/136 [00:05<00:02, 18.76it/s]
Face Renderer:: 62%|██████▎ | 85/136 [00:05<00:02, 18.73it/s]
Face Renderer:: 64%|██████▍ | 87/136 [00:05<00:02, 18.49it/s]
Face Renderer:: 65%|██████▌ | 89/136 [00:05<00:02, 18.53it/s]
Face Renderer:: 67%|██████▋ | 91/136 [00:05<00:02, 18.55it/s]
Face Renderer:: 68%|██████▊ | 93/136 [00:05<00:02, 18.63it/s]
Face Renderer:: 70%|██████▉ | 95/136 [00:05<00:02, 18.68it/s]
Face Renderer:: 71%|███████▏ | 97/136 [00:05<00:02, 18.70it/s]
Face Renderer:: 73%|███████▎ | 99/136 [00:06<00:01, 18.72it/s]
Face Renderer:: 74%|███████▍ | 101/136 [00:06<00:01, 18.71it/s]
Face Renderer:: 76%|███████▌ | 103/136 [00:06<00:01, 18.77it/s]
Face Renderer:: 77%|███████▋ | 105/136 [00:06<00:01, 18.74it/s]
Face Renderer:: 79%|███████▊ | 107/136 [00:06<00:01, 18.74it/s]
Face Renderer:: 80%|████████ | 109/136 [00:06<00:01, 18.62it/s]
Face Renderer:: 82%|████████▏ | 111/136 [00:06<00:01, 18.65it/s]
Face Renderer:: 83%|████████▎ | 113/136 [00:06<00:01, 18.44it/s]
Face Renderer:: 85%|████████▍ | 115/136 [00:06<00:01, 18.46it/s]
Face Renderer:: 86%|████████▌ | 117/136 [00:07<00:01, 18.53it/s]
Face Renderer:: 88%|████████▊ | 119/136 [00:07<00:00, 18.59it/s]
Face Renderer:: 89%|████████▉ | 121/136 [00:07<00:00, 18.65it/s]
Face Renderer:: 90%|█████████ | 123/136 [00:07<00:00, 18.64it/s]
Face Renderer:: 92%|█████████▏| 125/136 [00:07<00:00, 18.63it/s]
Face Renderer:: 93%|█████████▎| 127/136 [00:07<00:00, 18.58it/s]
Face Renderer:: 95%|█████████▍| 129/136 [00:07<00:00, 18.53it/s]
Face Renderer:: 96%|█████████▋| 131/136 [00:07<00:00, 18.54it/s]
Face Renderer:: 98%|█████████▊| 133/136 [00:07<00:00, 18.63it/s]
Face Renderer:: 99%|█████████▉| 135/136 [00:07<00:00, 18.68it/s]
Face Renderer:: 99%|█████████▉| 135/136 [00:07<00:00, 16.89it/s]
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil 56. 70.100 / 56. 70.100
libavcodec 58.134.100 / 58.134.100
libavformat 58. 76.100 / 58. 76.100
libavdevice 58. 13.100 / 58. 13.100
libavfilter 7.110.100 / 7.110.100
libswscale 5. 9.100 / 5. 9.100
libswresample 3. 9.100 / 3. 9.100
libpostproc 55. 9.100 / 55. 9.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'results/2024_01_09_11.01.46/temp_tmpiuycqk491##tmpy824i3jtchinese_poem1.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf58.29.100
Duration: 00:00:05.40, start: 0.000000, bitrate: 69 kb/s
Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 256x256, 66 kb/s, 25 fps, 25 tbr, 12800 tbn, 50 tbc (default)
Metadata:
handler_name : VideoHandler
vendor_id : [0][0][0][0]
Guessed Channel Layout for Input Stream #1.0 : mono
Input #1, wav, from 'results/2024_01_09_11.01.46/tmpy824i3jtchinese_poem1.wav':
Duration: 00:00:05.40, bitrate: 256 kb/s
Stream #1:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (copy)
Stream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native))
Press [q] to stop, [?] for help
Output #0, mp4, to 'bab057ca-1797-4081-af8f-efd4d5d799ca.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf58.76.100
Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 256x256, q=2-31, 66 kb/s, 25 fps, 25 tbr, 12800 tbn, 12800 tbc (default)
Metadata:
handler_name : VideoHandler
vendor_id : [0][0][0][0]
Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 16000 Hz, mono, fltp, 69 kb/s
Metadata:
encoder : Lavc58.134.100 aac
frame= 0 fps=0.0 q=-1.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x
frame= 135 fps=0.0 q=-1.0 Lsize= 92kB time=00:00:05.37 bitrate= 140.8kbits/s speed= 308x
video:44kB audio:44kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 5.446096%
[aac @ 0x5563e2ed36c0] Qavg: 42759.586
The generated video is named tmpiuycqk491##tmpy824i3jtchinese_poem1.mp4 in results/2024_01_09_11.01.46
OpenCV: FFMPEG: tag 0x5634504d/'MP4V' is not supported with codec id 12 and format 'mp4 / MP4 (MPEG-4 Part 14)'
OpenCV: FFMPEG: fallback to use tag 0x7634706d/'mp4v'
faceClone:: 0%| | 0/135 [00:00<?, ?it/s]
faceClone:: 1%| | 1/135 [00:01<03:09, 1.41s/it]
faceClone:: 1%|▏ | 2/135 [00:01<01:45, 1.27it/s]
faceClone:: 2%|▏ | 3/135 [00:02<01:18, 1.68it/s]
faceClone:: 3%|▎ | 4/135 [00:02<01:05, 2.00it/s]
faceClone:: 4%|▎ | 5/135 [00:02<00:59, 2.20it/s]
faceClone:: 4%|▍ | 6/135 [00:03<00:55, 2.34it/s]
faceClone:: 5%|▌ | 7/135 [00:03<00:52, 2.44it/s]
faceClone:: 6%|▌ | 8/135 [00:03<00:50, 2.53it/s]
faceClone:: 7%|▋ | 9/135 [00:04<00:48, 2.59it/s]
faceClone:: 7%|▋ | 10/135 [00:04<00:47, 2.61it/s]
faceClone:: 8%|▊ | 11/135 [00:05<00:46, 2.66it/s]
faceClone:: 9%|▉ | 12/135 [00:05<00:45, 2.69it/s]
faceClone:: 10%|▉ | 13/135 [00:05<00:44, 2.71it/s]
faceClone:: 10%|█ | 14/135 [00:06<00:44, 2.74it/s]
faceClone:: 11%|█ | 15/135 [00:06<00:44, 2.71it/s]
faceClone:: 12%|█▏ | 16/135 [00:06<00:44, 2.70it/s]
faceClone:: 13%|█▎ | 17/135 [00:07<00:43, 2.69it/s]
faceClone:: 13%|█▎ | 18/135 [00:07<00:43, 2.71it/s]
faceClone:: 14%|█▍ | 19/135 [00:08<00:42, 2.73it/s]
faceClone:: 15%|█▍ | 20/135 [00:08<00:42, 2.73it/s]
faceClone:: 16%|█▌ | 21/135 [00:08<00:43, 2.61it/s]
faceClone:: 16%|█▋ | 22/135 [00:09<00:44, 2.51it/s]
faceClone:: 17%|█▋ | 23/135 [00:09<00:44, 2.53it/s]
faceClone:: 18%|█▊ | 24/135 [00:09<00:42, 2.62it/s]
faceClone:: 19%|█▊ | 25/135 [00:10<00:41, 2.63it/s]
faceClone:: 19%|█▉ | 26/135 [00:10<00:41, 2.63it/s]
faceClone:: 20%|██ | 27/135 [00:11<00:40, 2.65it/s]
faceClone:: 21%|██ | 28/135 [00:11<00:40, 2.65it/s]
faceClone:: 21%|██▏ | 29/135 [00:11<00:40, 2.65it/s]
faceClone:: 22%|██▏ | 30/135 [00:12<00:39, 2.66it/s]
faceClone:: 23%|██▎ | 31/135 [00:12<00:38, 2.67it/s]
faceClone:: 24%|██▎ | 32/135 [00:12<00:38, 2.70it/s]
faceClone:: 24%|██▍ | 33/135 [00:13<00:37, 2.72it/s]
faceClone:: 25%|██▌ | 34/135 [00:13<00:36, 2.74it/s]
faceClone:: 26%|██▌ | 35/135 [00:14<00:36, 2.75it/s]
faceClone:: 27%|██▋ | 36/135 [00:14<00:36, 2.74it/s]
faceClone:: 27%|██▋ | 37/135 [00:14<00:35, 2.72it/s]
faceClone:: 28%|██▊ | 38/135 [00:15<00:35, 2.70it/s]
faceClone:: 29%|██▉ | 39/135 [00:15<00:35, 2.68it/s]
faceClone:: 30%|██▉ | 40/135 [00:15<00:35, 2.66it/s]
faceClone:: 30%|███ | 41/135 [00:16<00:35, 2.67it/s]
faceClone:: 31%|███ | 42/135 [00:16<00:35, 2.66it/s]
faceClone:: 32%|███▏ | 43/135 [00:17<00:34, 2.68it/s]
faceClone:: 33%|███▎ | 44/135 [00:17<00:33, 2.70it/s]
faceClone:: 33%|███▎ | 45/135 [00:17<00:33, 2.70it/s]
faceClone:: 34%|███▍ | 46/135 [00:18<00:32, 2.70it/s]
faceClone:: 35%|███▍ | 47/135 [00:18<00:33, 2.63it/s]
faceClone:: 36%|███▌ | 48/135 [00:18<00:34, 2.53it/s]
faceClone:: 36%|███▋ | 49/135 [00:19<00:33, 2.54it/s]
faceClone:: 37%|███▋ | 50/135 [00:19<00:32, 2.59it/s]
faceClone:: 38%|███▊ | 51/135 [00:20<00:32, 2.61it/s]
faceClone:: 39%|███▊ | 52/135 [00:20<00:31, 2.62it/s]
faceClone:: 39%|███▉ | 53/135 [00:20<00:31, 2.61it/s]
faceClone:: 40%|████ | 54/135 [00:21<00:30, 2.64it/s]
faceClone:: 41%|████ | 55/135 [00:21<00:30, 2.66it/s]
faceClone:: 41%|████▏ | 56/135 [00:21<00:29, 2.63it/s]
faceClone:: 42%|████▏ | 57/135 [00:22<00:29, 2.64it/s]
faceClone:: 43%|████▎ | 58/135 [00:22<00:29, 2.64it/s]
faceClone:: 44%|████▎ | 59/135 [00:23<00:28, 2.63it/s]
faceClone:: 44%|████▍ | 60/135 [00:23<00:29, 2.58it/s]
faceClone:: 45%|████▌ | 61/135 [00:23<00:29, 2.54it/s]
faceClone:: 46%|████▌ | 62/135 [00:24<00:28, 2.55it/s]
faceClone:: 47%|████▋ | 63/135 [00:24<00:28, 2.52it/s]
faceClone:: 47%|████▋ | 64/135 [00:25<00:28, 2.49it/s]
faceClone:: 48%|████▊ | 65/135 [00:25<00:29, 2.41it/s]
faceClone:: 49%|████▉ | 66/135 [00:26<00:28, 2.38it/s]
faceClone:: 50%|████▉ | 67/135 [00:26<00:28, 2.38it/s]
faceClone:: 50%|█████ | 68/135 [00:26<00:27, 2.39it/s]
faceClone:: 51%|█████ | 69/135 [00:27<00:27, 2.41it/s]
faceClone:: 52%|█████▏ | 70/135 [00:27<00:27, 2.40it/s]
faceClone:: 53%|█████▎ | 71/135 [00:28<00:25, 2.47it/s]
faceClone:: 53%|█████▎ | 72/135 [00:28<00:24, 2.52it/s]
faceClone:: 54%|█████▍ | 73/135 [00:28<00:24, 2.55it/s]
faceClone:: 55%|█████▍ | 74/135 [00:29<00:23, 2.57it/s]
faceClone:: 56%|█████▌ | 75/135 [00:29<00:23, 2.60it/s]
faceClone:: 56%|█████▋ | 76/135 [00:29<00:22, 2.62it/s]
faceClone:: 57%|█████▋ | 77/135 [00:30<00:23, 2.51it/s]
faceClone:: 58%|█████▊ | 78/135 [00:30<00:23, 2.47it/s]
faceClone:: 59%|█████▊ | 79/135 [00:31<00:22, 2.47it/s]
faceClone:: 59%|█████▉ | 80/135 [00:31<00:21, 2.53it/s]
faceClone:: 60%|██████ | 81/135 [00:31<00:21, 2.54it/s]
faceClone:: 61%|██████ | 82/135 [00:32<00:20, 2.58it/s]
faceClone:: 61%|██████▏ | 83/135 [00:32<00:20, 2.51it/s]
faceClone:: 62%|██████▏ | 84/135 [00:33<00:20, 2.43it/s]
faceClone:: 63%|██████▎ | 85/135 [00:33<00:20, 2.43it/s]
faceClone:: 64%|██████▎ | 86/135 [00:34<00:20, 2.40it/s]
faceClone:: 64%|██████▍ | 87/135 [00:34<00:20, 2.38it/s]
faceClone:: 65%|██████▌ | 88/135 [00:34<00:19, 2.37it/s]
faceClone:: 66%|██████▌ | 89/135 [00:35<00:19, 2.35it/s]
faceClone:: 67%|██████▋ | 90/135 [00:35<00:19, 2.35it/s]
faceClone:: 67%|██████▋ | 91/135 [00:36<00:18, 2.44it/s]
faceClone:: 68%|██████▊ | 92/135 [00:36<00:17, 2.50it/s]
faceClone:: 69%|██████▉ | 93/135 [00:36<00:16, 2.53it/s]
faceClone:: 70%|██████▉ | 94/135 [00:37<00:15, 2.57it/s]
faceClone:: 70%|███████ | 95/135 [00:37<00:15, 2.58it/s]
faceClone:: 71%|███████ | 96/135 [00:38<00:15, 2.58it/s]
faceClone:: 72%|███████▏ | 97/135 [00:38<00:14, 2.60it/s]
faceClone:: 73%|███████▎ | 98/135 [00:38<00:14, 2.62it/s]
faceClone:: 73%|███████▎ | 99/135 [00:39<00:13, 2.63it/s]
faceClone:: 74%|███████▍ | 100/135 [00:39<00:13, 2.61it/s]
faceClone:: 75%|███████▍ | 101/135 [00:39<00:12, 2.63it/s]
faceClone:: 76%|███████▌ | 102/135 [00:40<00:12, 2.64it/s]
faceClone:: 76%|███████▋ | 103/135 [00:40<00:12, 2.64it/s]
faceClone:: 77%|███████▋ | 104/135 [00:41<00:11, 2.66it/s]
faceClone:: 78%|███████▊ | 105/135 [00:41<00:11, 2.69it/s]
faceClone:: 79%|███████▊ | 106/135 [00:41<00:10, 2.67it/s]
faceClone:: 79%|███████▉ | 107/135 [00:42<00:10, 2.69it/s]
faceClone:: 80%|████████ | 108/135 [00:42<00:10, 2.68it/s]
faceClone:: 81%|████████ | 109/135 [00:42<00:09, 2.70it/s]
faceClone:: 81%|████████▏ | 110/135 [00:43<00:09, 2.67it/s]
faceClone:: 82%|████████▏ | 111/135 [00:43<00:08, 2.69it/s]
faceClone:: 83%|████████▎ | 112/135 [00:44<00:08, 2.66it/s]
faceClone:: 84%|████████▎ | 113/135 [00:44<00:08, 2.66it/s]
faceClone:: 84%|████████▍ | 114/135 [00:44<00:07, 2.66it/s]
faceClone:: 85%|████████▌ | 115/135 [00:45<00:07, 2.68it/s]
faceClone:: 86%|████████▌ | 116/135 [00:45<00:07, 2.64it/s]
faceClone:: 87%|████████▋ | 117/135 [00:45<00:06, 2.64it/s]
faceClone:: 87%|████████▋ | 118/135 [00:46<00:06, 2.66it/s]
faceClone:: 88%|████████▊ | 119/135 [00:46<00:05, 2.69it/s]
faceClone:: 89%|████████▉ | 120/135 [00:47<00:05, 2.70it/s]
faceClone:: 90%|████████▉ | 121/135 [00:47<00:05, 2.71it/s]
faceClone:: 90%|█████████ | 122/135 [00:47<00:04, 2.71it/s]
faceClone:: 91%|█████████ | 123/135 [00:48<00:04, 2.69it/s]
faceClone:: 92%|█████████▏| 124/135 [00:48<00:04, 2.71it/s]
faceClone:: 93%|█████████▎| 125/135 [00:48<00:03, 2.69it/s]
faceClone:: 93%|█████████▎| 126/135 [00:49<00:03, 2.70it/s]
faceClone:: 94%|█████████▍| 127/135 [00:49<00:02, 2.71it/s]
faceClone:: 95%|█████████▍| 128/135 [00:50<00:02, 2.71it/s]
faceClone:: 96%|█████████▌| 129/135 [00:50<00:02, 2.69it/s]
faceClone:: 96%|█████████▋| 130/135 [00:50<00:01, 2.69it/s]
faceClone:: 97%|█████████▋| 131/135 [00:51<00:01, 2.70it/s]
faceClone:: 98%|█████████▊| 132/135 [00:51<00:01, 2.67it/s]
faceClone:: 99%|█████████▊| 133/135 [00:51<00:00, 2.68it/s]
faceClone:: 99%|█████████▉| 134/135 [00:52<00:00, 2.64it/s]
faceClone:: 100%|██████████| 135/135 [00:52<00:00, 2.64it/s]
faceClone:: 100%|██████████| 135/135 [00:52<00:00, 2.56it/s]
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil 56. 70.100 / 56. 70.100
libavcodec 58.134.100 / 58.134.100
libavformat 58. 76.100 / 58. 76.100
libavdevice 58. 13.100 / 58. 13.100
libavfilter 7.110.100 / 7.110.100
libswscale 5. 9.100 / 5. 9.100
libswresample 3. 9.100 / 3. 9.100
libpostproc 55. 9.100 / 55. 9.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from '4ce1cfac-74fa-4bbd-87f5-95ff48f17cfe.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2mp41
encoder : Lavf59.27.100
Duration: 00:00:05.40, start: 0.000000, bitrate: 600 kb/s
Stream #0:0(und): Video: mpeg4 (Simple Profile) (mp4v / 0x7634706D), yuv420p, 700x700 [SAR 1:1 DAR 1:1], 598 kb/s, 25 fps, 25 tbr, 12800 tbn, 25 tbc (default)
Metadata:
handler_name : VideoHandler
vendor_id : [0][0][0][0]
Guessed Channel Layout for Input Stream #1.0 : mono
Input #1, wav, from 'results/2024_01_09_11.01.46/tmpy824i3jtchinese_poem1.wav':
Duration: 00:00:05.40, bitrate: 256 kb/s
Stream #1:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (mpeg4 (native) -> h264 (libx264))
Stream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native))
Press [q] to stop, [?] for help
[libx264 @ 0x55c33629d900] using SAR=1/1
[libx264 @ 0x55c33629d900] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2
[libx264 @ 0x55c33629d900] profile High, level 3.1, 4:2:0, 8-bit
[libx264 @ 0x55c33629d900] 264 - core 163 r3060 5db6aa6 - H.264/MPEG-4 AVC codec - Copyleft 2003-2021 - http://www.videolan.org/x264.html - options: cabac=1 ref=3 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=7 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=1 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=15 lookahead_threads=2 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=3 b_pyramid=2 b_adapt=1 b_bias=0 direct=1 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00
Output #0, mp4, to 'results/2024_01_09_11.01.46/tmpiuycqk491##tmpy824i3jtchinese_poem1_full.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2mp41
encoder : Lavf58.76.100
Stream #0:0(und): Video: h264 (avc1 / 0x31637661), yuv420p(progressive), 700x700 [SAR 1:1 DAR 1:1], q=2-31, 25 fps, 12800 tbn (default)
Metadata:
handler_name : VideoHandler
vendor_id : [0][0][0][0]
encoder : Lavc58.134.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A
Stream #0:1: Audio: aac (LC) (mp4a / 0x6134706D), 16000 Hz, mono, fltp, 69 kb/s
Metadata:
encoder : Lavc58.134.100 aac
frame= 1 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x
frame= 135 fps=0.0 q=-1.0 Lsize= 281kB time=00:00:05.37 bitrate= 428.6kbits/s speed=11.2x
video:233kB audio:44kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.691295%
[libx264 @ 0x55c33629d900] frame I:1 Avg QP:18.57 size: 11753
[libx264 @ 0x55c33629d900] frame P:58 Avg QP:20.29 size: 2937
[libx264 @ 0x55c33629d900] frame B:76 Avg QP:22.27 size: 728
[libx264 @ 0x55c33629d900] consecutive B-frames: 15.6% 26.7% 4.4% 53.3%
[libx264 @ 0x55c33629d900] mb I I16..4: 29.2% 70.1% 0.6%
[libx264 @ 0x55c33629d900] mb P I16..4: 1.3% 4.8% 0.1% P16..4: 27.3% 5.9% 2.8% 0.0% 0.0% skip:57.8%
[libx264 @ 0x55c33629d900] mb B I16..4: 0.3% 1.0% 0.0% B16..8: 25.6% 0.6% 0.0% direct: 0.3% skip:72.1% L0:48.8% L1:50.5% BI: 0.7%
[libx264 @ 0x55c33629d900] 8x8 transform intra:76.1% inter:89.4%
[libx264 @ 0x55c33629d900] coded y,uvDC,uvAC intra: 34.0% 37.2% 3.7% inter: 3.5% 4.8% 0.0%
[libx264 @ 0x55c33629d900] i16 v,h,dc,p: 40% 38% 15% 7%
[libx264 @ 0x55c33629d900] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 29% 24% 40% 1% 1% 1% 1% 1% 1%
[libx264 @ 0x55c33629d900] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 37% 29% 15% 2% 4% 3% 6% 2% 1%
[libx264 @ 0x55c33629d900] i8c dc,h,v,p: 52% 24% 22% 2%
[libx264 @ 0x55c33629d900] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x55c33629d900] ref P L0: 70.2% 6.3% 17.0% 6.5%
[libx264 @ 0x55c33629d900] ref B L0: 79.2% 17.1% 3.7%
[libx264 @ 0x55c33629d900] ref B L1: 96.0% 4.0%
[libx264 @ 0x55c33629d900] kb/s:351.74
[aac @ 0x55c33629f8c0] Qavg: 42759.586
The generated video is named results/2024_01_09_11.01.46/tmpiuycqk491##tmpy824i3jtchinese_poem1_full.mp4