chenxwh/video-retalking 🖼️ → 🖼️

▶️ 31.2K runs 📅 Oct 2023 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License
lipsync video-editing

About

Audio-based Lip Synchronization for Talking Head Video

Example Output

Output

Performance Metrics

114.08s Prediction Time
266.42s Total Time
All Input Parameters
{
  "face": "https://replicate.delivery/pbxt/Jnm95KgYvAQIHlR0tg8rbWHweReTtCYp42Drl7dMNtHXaTNR/3.mp4",
  "input_audio": "https://replicate.delivery/pbxt/JnkUjVcUPLreS4x7ZXXQuCY7qVcLLDNxOeRAsHRi7qj79xBk/1.wav"
}
Input Parameters
face (required) Type: string
Input video file of a talking-head.
input_audio (required) Type: string
Input audio file. Avoid special symbol in the filename as it may cause ffmpeg erros.
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
[Step 1] Landmarks Extraction in Video.
landmark Det::   0%|          | 0/125 [00:00<?, ?it/s]
landmark Det::   1%|          | 1/125 [00:09<18:35,  9.00s/it]
landmark Det::   2%|▏         | 2/125 [00:15<15:31,  7.57s/it]
landmark Det::   7%|▋         | 9/125 [00:15<02:09,  1.11s/it]
landmark Det::  13%|█▎        | 16/125 [00:15<00:55,  1.96it/s]
landmark Det::  18%|█▊        | 23/125 [00:15<00:29,  3.41it/s]
landmark Det::  24%|██▍       | 30/125 [00:16<00:17,  5.36it/s]
landmark Det::  30%|██▉       | 37/125 [00:16<00:11,  7.93it/s]
landmark Det::  34%|███▍      | 43/125 [00:16<00:07, 10.76it/s]
landmark Det::  40%|████      | 50/125 [00:16<00:05, 14.93it/s]
landmark Det::  45%|████▍     | 56/125 [00:16<00:03, 18.96it/s]
landmark Det::  50%|█████     | 63/125 [00:16<00:02, 24.47it/s]
landmark Det::  56%|█████▌    | 70/125 [00:16<00:01, 30.41it/s]
landmark Det::  62%|██████▏   | 77/125 [00:16<00:01, 35.98it/s]
landmark Det::  67%|██████▋   | 84/125 [00:16<00:00, 41.04it/s]
landmark Det::  73%|███████▎  | 91/125 [00:17<00:00, 45.62it/s]
landmark Det::  78%|███████▊  | 98/125 [00:17<00:00, 48.72it/s]
landmark Det::  83%|████████▎ | 104/125 [00:17<00:00, 51.06it/s]
landmark Det::  89%|████████▉ | 111/125 [00:17<00:00, 53.91it/s]
landmark Det::  94%|█████████▎| 117/125 [00:17<00:00, 54.60it/s]
landmark Det::  99%|█████████▉| 124/125 [00:17<00:00, 56.96it/s]
landmark Det:: 100%|██████████| 125/125 [00:17<00:00,  7.10it/s]
[Step 2] 3DMM Extraction In Video::   0%|          | 0/125 [00:00<?, ?it/s]
[Step 2] 3DMM Extraction In Video::   1%|          | 1/125 [00:00<00:21,  5.64it/s]
[Step 2] 3DMM Extraction In Video::  12%|█▏        | 15/125 [00:00<00:01, 63.79it/s]
[Step 2] 3DMM Extraction In Video::  23%|██▎       | 29/125 [00:00<00:01, 91.19it/s]
[Step 2] 3DMM Extraction In Video::  34%|███▍      | 43/125 [00:00<00:00, 106.78it/s]
[Step 2] 3DMM Extraction In Video::  46%|████▌     | 57/125 [00:00<00:00, 115.69it/s]
[Step 2] 3DMM Extraction In Video::  57%|█████▋    | 71/125 [00:00<00:00, 121.07it/s]
[Step 2] 3DMM Extraction In Video::  67%|██████▋   | 84/125 [00:00<00:00, 120.56it/s]
[Step 2] 3DMM Extraction In Video::  78%|███████▊  | 98/125 [00:00<00:00, 124.50it/s]
[Step 2] 3DMM Extraction In Video::  90%|████████▉ | 112/125 [00:01<00:00, 127.22it/s]
[Step 2] 3DMM Extraction In Video:: 100%|██████████| 125/125 [00:01<00:00, 111.56it/s]
using expression center
Load checkpoint from: checkpoints/DNet.pt
Load checkpoint from: checkpoints/LNet.pth
Load checkpoint from: checkpoints/ENet.pth
[Step 3] Stabilize the expression In Video::   0%|          | 0/125 [00:00<?, ?it/s]
[Step 3] Stabilize the expression In Video::   1%|          | 1/125 [00:00<00:43,  2.84it/s]
[Step 3] Stabilize the expression In Video::   2%|▏         | 3/125 [00:00<00:18,  6.69it/s]
[Step 3] Stabilize the expression In Video::   4%|▍         | 5/125 [00:00<00:13,  8.90it/s]
[Step 3] Stabilize the expression In Video::   6%|▌         | 7/125 [00:00<00:11, 10.26it/s]
[Step 3] Stabilize the expression In Video::   7%|▋         | 9/125 [00:00<00:10, 11.13it/s]
[Step 3] Stabilize the expression In Video::   9%|▉         | 11/125 [00:01<00:09, 11.68it/s]
[Step 3] Stabilize the expression In Video::  10%|█         | 13/125 [00:01<00:09, 12.07it/s]
[Step 3] Stabilize the expression In Video::  12%|█▏        | 15/125 [00:01<00:08, 12.33it/s]
[Step 3] Stabilize the expression In Video::  14%|█▎        | 17/125 [00:01<00:08, 12.51it/s]
[Step 3] Stabilize the expression In Video::  15%|█▌        | 19/125 [00:01<00:08, 12.65it/s]
[Step 3] Stabilize the expression In Video::  17%|█▋        | 21/125 [00:01<00:08, 12.72it/s]
[Step 3] Stabilize the expression In Video::  18%|█▊        | 23/125 [00:02<00:07, 12.79it/s]
[Step 3] Stabilize the expression In Video::  20%|██        | 25/125 [00:02<00:07, 12.83it/s]
[Step 3] Stabilize the expression In Video::  22%|██▏       | 27/125 [00:02<00:07, 12.84it/s]
[Step 3] Stabilize the expression In Video::  23%|██▎       | 29/125 [00:02<00:07, 12.88it/s]
[Step 3] Stabilize the expression In Video::  25%|██▍       | 31/125 [00:02<00:07, 12.88it/s]
[Step 3] Stabilize the expression In Video::  26%|██▋       | 33/125 [00:02<00:07, 12.85it/s]
[Step 3] Stabilize the expression In Video::  28%|██▊       | 35/125 [00:02<00:06, 12.86it/s]
[Step 3] Stabilize the expression In Video::  30%|██▉       | 37/125 [00:03<00:06, 12.88it/s]
[Step 3] Stabilize the expression In Video::  31%|███       | 39/125 [00:03<00:06, 12.90it/s]
[Step 3] Stabilize the expression In Video::  33%|███▎      | 41/125 [00:03<00:06, 12.90it/s]
[Step 3] Stabilize the expression In Video::  34%|███▍      | 43/125 [00:03<00:06, 12.85it/s]
[Step 3] Stabilize the expression In Video::  36%|███▌      | 45/125 [00:03<00:06, 12.87it/s]
[Step 3] Stabilize the expression In Video::  38%|███▊      | 47/125 [00:03<00:06, 12.88it/s]
[Step 3] Stabilize the expression In Video::  39%|███▉      | 49/125 [00:04<00:05, 12.89it/s]
[Step 3] Stabilize the expression In Video::  41%|████      | 51/125 [00:04<00:05, 12.87it/s]
[Step 3] Stabilize the expression In Video::  42%|████▏     | 53/125 [00:04<00:05, 12.89it/s]
[Step 3] Stabilize the expression In Video::  44%|████▍     | 55/125 [00:04<00:05, 12.91it/s]
[Step 3] Stabilize the expression In Video::  46%|████▌     | 57/125 [00:04<00:05, 12.90it/s]
[Step 3] Stabilize the expression In Video::  47%|████▋     | 59/125 [00:04<00:05, 12.90it/s]
[Step 3] Stabilize the expression In Video::  49%|████▉     | 61/125 [00:05<00:04, 12.91it/s]
[Step 3] Stabilize the expression In Video::  50%|█████     | 63/125 [00:05<00:04, 12.92it/s]
[Step 3] Stabilize the expression In Video::  52%|█████▏    | 65/125 [00:05<00:04, 12.90it/s]
[Step 3] Stabilize the expression In Video::  54%|█████▎    | 67/125 [00:05<00:04, 12.87it/s]
[Step 3] Stabilize the expression In Video::  55%|█████▌    | 69/125 [00:05<00:04, 12.87it/s]
[Step 3] Stabilize the expression In Video::  57%|█████▋    | 71/125 [00:05<00:04, 12.88it/s]
[Step 3] Stabilize the expression In Video::  58%|█████▊    | 73/125 [00:05<00:04, 12.91it/s]
[Step 3] Stabilize the expression In Video::  60%|██████    | 75/125 [00:06<00:03, 12.90it/s]
[Step 3] Stabilize the expression In Video::  62%|██████▏   | 77/125 [00:06<00:03, 12.91it/s]
[Step 3] Stabilize the expression In Video::  63%|██████▎   | 79/125 [00:06<00:03, 12.74it/s]
[Step 3] Stabilize the expression In Video::  65%|██████▍   | 81/125 [00:06<00:03, 12.73it/s]
[Step 3] Stabilize the expression In Video::  66%|██████▋   | 83/125 [00:06<00:03, 12.78it/s]
[Step 3] Stabilize the expression In Video::  68%|██████▊   | 85/125 [00:06<00:03, 12.84it/s]
[Step 3] Stabilize the expression In Video::  70%|██████▉   | 87/125 [00:07<00:02, 12.88it/s]
[Step 3] Stabilize the expression In Video::  71%|███████   | 89/125 [00:07<00:02, 12.91it/s]
[Step 3] Stabilize the expression In Video::  73%|███████▎  | 91/125 [00:07<00:02, 12.90it/s]
[Step 3] Stabilize the expression In Video::  74%|███████▍  | 93/125 [00:07<00:02, 12.92it/s]
[Step 3] Stabilize the expression In Video::  76%|███████▌  | 95/125 [00:07<00:02, 12.92it/s]
[Step 3] Stabilize the expression In Video::  78%|███████▊  | 97/125 [00:07<00:02, 12.94it/s]
[Step 3] Stabilize the expression In Video::  79%|███████▉  | 99/125 [00:07<00:02, 12.92it/s]
[Step 3] Stabilize the expression In Video::  81%|████████  | 101/125 [00:08<00:01, 12.93it/s]
[Step 3] Stabilize the expression In Video::  82%|████████▏ | 103/125 [00:08<00:01, 12.94it/s]
[Step 3] Stabilize the expression In Video::  84%|████████▍ | 105/125 [00:08<00:01, 12.94it/s]
[Step 3] Stabilize the expression In Video::  86%|████████▌ | 107/125 [00:08<00:01, 12.89it/s]
[Step 3] Stabilize the expression In Video::  87%|████████▋ | 109/125 [00:08<00:01, 12.89it/s]
[Step 3] Stabilize the expression In Video::  89%|████████▉ | 111/125 [00:08<00:01, 12.89it/s]
[Step 3] Stabilize the expression In Video::  90%|█████████ | 113/125 [00:09<00:00, 12.90it/s]
[Step 3] Stabilize the expression In Video::  92%|█████████▏| 115/125 [00:09<00:00, 12.87it/s]
[Step 3] Stabilize the expression In Video::  94%|█████████▎| 117/125 [00:09<00:00, 12.87it/s]
[Step 3] Stabilize the expression In Video::  95%|█████████▌| 119/125 [00:09<00:00, 12.90it/s]
[Step 3] Stabilize the expression In Video::  97%|█████████▋| 121/125 [00:09<00:00, 12.91it/s]
[Step 3] Stabilize the expression In Video::  98%|█████████▊| 123/125 [00:09<00:00, 12.90it/s]
[Step 3] Stabilize the expression In Video:: 100%|██████████| 125/125 [00:09<00:00, 12.91it/s]
[Step 3] Stabilize the expression In Video:: 100%|██████████| 125/125 [00:09<00:00, 12.54it/s]
[Step 4] Load audio; Length of mel chunks: 122
[Step 5] Reference Enhancement:   0%|          | 0/122 [00:00<?, ?it/s]
[Step 5] Reference Enhancement:   1%|          | 1/122 [00:01<02:14,  1.11s/it]
[Step 5] Reference Enhancement:   2%|▏         | 2/122 [00:01<01:05,  1.84it/s]
[Step 5] Reference Enhancement:   2%|▏         | 3/122 [00:01<00:42,  2.79it/s]
[Step 5] Reference Enhancement:   3%|▎         | 4/122 [00:01<00:32,  3.67it/s]
[Step 5] Reference Enhancement:   4%|▍         | 5/122 [00:01<00:26,  4.44it/s]
[Step 5] Reference Enhancement:   5%|▍         | 6/122 [00:01<00:22,  5.09it/s]
[Step 5] Reference Enhancement:   6%|▌         | 7/122 [00:01<00:20,  5.56it/s]
[Step 5] Reference Enhancement:   7%|▋         | 8/122 [00:02<00:19,  5.98it/s]
[Step 5] Reference Enhancement:   7%|▋         | 9/122 [00:02<00:17,  6.29it/s]
[Step 5] Reference Enhancement:   8%|▊         | 10/122 [00:02<00:17,  6.54it/s]
[Step 5] Reference Enhancement:   9%|▉         | 11/122 [00:02<00:16,  6.70it/s]
[Step 5] Reference Enhancement:  10%|▉         | 12/122 [00:02<00:16,  6.83it/s]
[Step 5] Reference Enhancement:  11%|█         | 13/122 [00:02<00:15,  6.92it/s]
[Step 5] Reference Enhancement:  11%|█▏        | 14/122 [00:02<00:15,  7.02it/s]
[Step 5] Reference Enhancement:  12%|█▏        | 15/122 [00:03<00:15,  7.07it/s]
[Step 5] Reference Enhancement:  13%|█▎        | 16/122 [00:03<00:14,  7.07it/s]
[Step 5] Reference Enhancement:  14%|█▍        | 17/122 [00:03<00:14,  7.09it/s]
[Step 5] Reference Enhancement:  15%|█▍        | 18/122 [00:03<00:14,  7.05it/s]
[Step 5] Reference Enhancement:  16%|█▌        | 19/122 [00:03<00:14,  7.03it/s]
[Step 5] Reference Enhancement:  16%|█▋        | 20/122 [00:03<00:14,  7.05it/s]
[Step 5] Reference Enhancement:  17%|█▋        | 21/122 [00:03<00:14,  7.09it/s]
[Step 5] Reference Enhancement:  18%|█▊        | 22/122 [00:04<00:14,  7.12it/s]
[Step 5] Reference Enhancement:  19%|█▉        | 23/122 [00:04<00:13,  7.08it/s]
[Step 5] Reference Enhancement:  20%|█▉        | 24/122 [00:04<00:13,  7.05it/s]
[Step 5] Reference Enhancement:  20%|██        | 25/122 [00:04<00:13,  7.07it/s]
[Step 5] Reference Enhancement:  21%|██▏       | 26/122 [00:04<00:13,  7.06it/s]
[Step 5] Reference Enhancement:  22%|██▏       | 27/122 [00:04<00:13,  7.07it/s]
[Step 5] Reference Enhancement:  23%|██▎       | 28/122 [00:04<00:13,  7.05it/s]
[Step 5] Reference Enhancement:  24%|██▍       | 29/122 [00:05<00:13,  7.10it/s]
[Step 5] Reference Enhancement:  25%|██▍       | 30/122 [00:05<00:12,  7.09it/s]
[Step 5] Reference Enhancement:  25%|██▌       | 31/122 [00:05<00:12,  7.10it/s]
[Step 5] Reference Enhancement:  26%|██▌       | 32/122 [00:05<00:12,  7.04it/s]
[Step 5] Reference Enhancement:  27%|██▋       | 33/122 [00:05<00:12,  7.05it/s]
[Step 5] Reference Enhancement:  28%|██▊       | 34/122 [00:05<00:12,  7.09it/s]
[Step 5] Reference Enhancement:  29%|██▊       | 35/122 [00:05<00:12,  7.06it/s]
[Step 5] Reference Enhancement:  30%|██▉       | 36/122 [00:06<00:12,  7.10it/s]
[Step 5] Reference Enhancement:  30%|███       | 37/122 [00:06<00:12,  7.05it/s]
[Step 5] Reference Enhancement:  31%|███       | 38/122 [00:06<00:11,  7.12it/s]
[Step 5] Reference Enhancement:  32%|███▏      | 39/122 [00:06<00:11,  7.08it/s]
[Step 5] Reference Enhancement:  33%|███▎      | 40/122 [00:06<00:11,  7.04it/s]
[Step 5] Reference Enhancement:  34%|███▎      | 41/122 [00:06<00:11,  7.12it/s]
[Step 5] Reference Enhancement:  34%|███▍      | 42/122 [00:06<00:11,  7.12it/s]
[Step 5] Reference Enhancement:  35%|███▌      | 43/122 [00:07<00:11,  7.14it/s]
[Step 5] Reference Enhancement:  36%|███▌      | 44/122 [00:07<00:10,  7.16it/s]
[Step 5] Reference Enhancement:  37%|███▋      | 45/122 [00:07<00:10,  7.14it/s]
[Step 5] Reference Enhancement:  38%|███▊      | 46/122 [00:07<00:10,  7.13it/s]
[Step 5] Reference Enhancement:  39%|███▊      | 47/122 [00:07<00:10,  7.10it/s]
[Step 5] Reference Enhancement:  39%|███▉      | 48/122 [00:07<00:10,  7.10it/s]
[Step 5] Reference Enhancement:  40%|████      | 49/122 [00:07<00:10,  7.00it/s]
[Step 5] Reference Enhancement:  41%|████      | 50/122 [00:08<00:10,  7.02it/s]
[Step 5] Reference Enhancement:  42%|████▏     | 51/122 [00:08<00:10,  7.09it/s]
[Step 5] Reference Enhancement:  43%|████▎     | 52/122 [00:08<00:09,  7.12it/s]
[Step 5] Reference Enhancement:  43%|████▎     | 53/122 [00:08<00:09,  7.09it/s]
[Step 5] Reference Enhancement:  44%|████▍     | 54/122 [00:08<00:09,  7.06it/s]
[Step 5] Reference Enhancement:  45%|████▌     | 55/122 [00:08<00:09,  7.08it/s]
[Step 5] Reference Enhancement:  46%|████▌     | 56/122 [00:08<00:09,  7.08it/s]
[Step 5] Reference Enhancement:  47%|████▋     | 57/122 [00:09<00:09,  7.10it/s]
[Step 5] Reference Enhancement:  48%|████▊     | 58/122 [00:09<00:09,  7.10it/s]
[Step 5] Reference Enhancement:  48%|████▊     | 59/122 [00:09<00:08,  7.06it/s]
[Step 5] Reference Enhancement:  49%|████▉     | 60/122 [00:09<00:08,  7.05it/s]
[Step 5] Reference Enhancement:  50%|█████     | 61/122 [00:09<00:08,  7.03it/s]
[Step 5] Reference Enhancement:  51%|█████     | 62/122 [00:09<00:08,  7.07it/s]
[Step 5] Reference Enhancement:  52%|█████▏    | 63/122 [00:09<00:08,  7.09it/s]
[Step 5] Reference Enhancement:  52%|█████▏    | 64/122 [00:10<00:08,  7.11it/s]
[Step 5] Reference Enhancement:  53%|█████▎    | 65/122 [00:10<00:08,  7.10it/s]
[Step 5] Reference Enhancement:  54%|█████▍    | 66/122 [00:10<00:07,  7.05it/s]
[Step 5] Reference Enhancement:  55%|█████▍    | 67/122 [00:10<00:07,  7.06it/s]
[Step 5] Reference Enhancement:  56%|█████▌    | 68/122 [00:10<00:07,  7.05it/s]
[Step 5] Reference Enhancement:  57%|█████▋    | 69/122 [00:10<00:07,  7.06it/s]
[Step 5] Reference Enhancement:  57%|█████▋    | 70/122 [00:10<00:07,  6.97it/s]
[Step 5] Reference Enhancement:  58%|█████▊    | 71/122 [00:11<00:07,  6.98it/s]
[Step 5] Reference Enhancement:  59%|█████▉    | 72/122 [00:11<00:07,  7.01it/s]
[Step 5] Reference Enhancement:  60%|█████▉    | 73/122 [00:11<00:06,  7.01it/s]
[Step 5] Reference Enhancement:  61%|██████    | 74/122 [00:11<00:06,  7.01it/s]
[Step 5] Reference Enhancement:  61%|██████▏   | 75/122 [00:11<00:06,  7.01it/s]
[Step 5] Reference Enhancement:  62%|██████▏   | 76/122 [00:11<00:06,  7.03it/s]
[Step 5] Reference Enhancement:  63%|██████▎   | 77/122 [00:11<00:06,  7.02it/s]
[Step 5] Reference Enhancement:  64%|██████▍   | 78/122 [00:11<00:06,  7.04it/s]
[Step 5] Reference Enhancement:  65%|██████▍   | 79/122 [00:12<00:06,  7.00it/s]
[Step 5] Reference Enhancement:  66%|██████▌   | 80/122 [00:12<00:05,  7.04it/s]
[Step 5] Reference Enhancement:  66%|██████▋   | 81/122 [00:12<00:05,  7.00it/s]
[Step 5] Reference Enhancement:  67%|██████▋   | 82/122 [00:12<00:05,  6.98it/s]
[Step 5] Reference Enhancement:  68%|██████▊   | 83/122 [00:12<00:05,  7.01it/s]
[Step 5] Reference Enhancement:  69%|██████▉   | 84/122 [00:12<00:05,  7.02it/s]
[Step 5] Reference Enhancement:  70%|██████▉   | 85/122 [00:12<00:05,  7.01it/s]
[Step 5] Reference Enhancement:  70%|███████   | 86/122 [00:13<00:05,  7.04it/s]
[Step 5] Reference Enhancement:  71%|███████▏  | 87/122 [00:13<00:04,  7.05it/s]
[Step 5] Reference Enhancement:  72%|███████▏  | 88/122 [00:13<00:04,  7.07it/s]
[Step 5] Reference Enhancement:  73%|███████▎  | 89/122 [00:13<00:04,  7.11it/s]
[Step 5] Reference Enhancement:  74%|███████▍  | 90/122 [00:13<00:04,  7.10it/s]
[Step 5] Reference Enhancement:  75%|███████▍  | 91/122 [00:13<00:04,  7.06it/s]
[Step 5] Reference Enhancement:  75%|███████▌  | 92/122 [00:13<00:04,  7.03it/s]
[Step 5] Reference Enhancement:  76%|███████▌  | 93/122 [00:14<00:04,  7.03it/s]
[Step 5] Reference Enhancement:  77%|███████▋  | 94/122 [00:14<00:04,  6.99it/s]
[Step 5] Reference Enhancement:  78%|███████▊  | 95/122 [00:14<00:03,  7.01it/s]
[Step 5] Reference Enhancement:  79%|███████▊  | 96/122 [00:14<00:03,  7.03it/s]
[Step 5] Reference Enhancement:  80%|███████▉  | 97/122 [00:14<00:03,  7.05it/s]
[Step 5] Reference Enhancement:  80%|████████  | 98/122 [00:14<00:03,  7.02it/s]
[Step 5] Reference Enhancement:  81%|████████  | 99/122 [00:14<00:03,  7.05it/s]
[Step 5] Reference Enhancement:  82%|████████▏ | 100/122 [00:15<00:03,  7.04it/s]
[Step 5] Reference Enhancement:  83%|████████▎ | 101/122 [00:15<00:02,  7.01it/s]
[Step 5] Reference Enhancement:  84%|████████▎ | 102/122 [00:15<00:02,  7.02it/s]
[Step 5] Reference Enhancement:  84%|████████▍ | 103/122 [00:15<00:02,  7.05it/s]
[Step 5] Reference Enhancement:  85%|████████▌ | 104/122 [00:15<00:02,  7.01it/s]
[Step 5] Reference Enhancement:  86%|████████▌ | 105/122 [00:15<00:02,  7.02it/s]
[Step 5] Reference Enhancement:  87%|████████▋ | 106/122 [00:15<00:02,  6.97it/s]
[Step 5] Reference Enhancement:  88%|████████▊ | 107/122 [00:16<00:02,  6.97it/s]
[Step 5] Reference Enhancement:  89%|████████▊ | 108/122 [00:16<00:02,  6.99it/s]
[Step 5] Reference Enhancement:  89%|████████▉ | 109/122 [00:16<00:01,  7.00it/s]
[Step 5] Reference Enhancement:  90%|█████████ | 110/122 [00:16<00:01,  6.97it/s]
[Step 5] Reference Enhancement:  91%|█████████ | 111/122 [00:16<00:01,  7.00it/s]
[Step 5] Reference Enhancement:  92%|█████████▏| 112/122 [00:16<00:01,  7.00it/s]
[Step 5] Reference Enhancement:  93%|█████████▎| 113/122 [00:16<00:01,  7.00it/s]
[Step 5] Reference Enhancement:  93%|█████████▎| 114/122 [00:17<00:01,  6.96it/s]
[Step 5] Reference Enhancement:  94%|█████████▍| 115/122 [00:17<00:01,  6.94it/s]
[Step 5] Reference Enhancement:  95%|█████████▌| 116/122 [00:17<00:00,  6.99it/s]
[Step 5] Reference Enhancement:  96%|█████████▌| 117/122 [00:17<00:00,  7.01it/s]
[Step 5] Reference Enhancement:  97%|█████████▋| 118/122 [00:17<00:00,  7.03it/s]
[Step 5] Reference Enhancement:  98%|█████████▊| 119/122 [00:17<00:00,  7.05it/s]
[Step 5] Reference Enhancement:  98%|█████████▊| 120/122 [00:17<00:00,  7.04it/s]
[Step 5] Reference Enhancement:  99%|█████████▉| 121/122 [00:18<00:00,  7.06it/s]
[Step 5] Reference Enhancement: 100%|██████████| 122/122 [00:18<00:00,  7.04it/s]
[Step 5] Reference Enhancement: 100%|██████████| 122/122 [00:18<00:00,  6.68it/s]
[Step 6] Lip Synthesis::   0%|          | 0/8 [00:00<?, ?it/s]
landmark Det::   0%|          | 0/122 [00:00<?, ?it/s]
landmark Det::   1%|          | 1/122 [00:00<00:22,  5.45it/s]
landmark Det::   2%|▏         | 2/122 [00:00<00:40,  2.99it/s]
landmark Det::   7%|▋         | 8/122 [00:00<00:08, 14.09it/s]
landmark Det::  11%|█▏        | 14/122 [00:00<00:04, 23.70it/s]
landmark Det::  16%|█▋        | 20/122 [00:00<00:03, 31.61it/s]
landmark Det::  21%|██▏       | 26/122 [00:01<00:02, 37.89it/s]
landmark Det::  26%|██▌       | 32/122 [00:01<00:02, 42.45it/s]
landmark Det::  31%|███       | 38/122 [00:01<00:01, 44.87it/s]
landmark Det::  36%|███▌      | 44/122 [00:01<00:01, 47.18it/s]
landmark Det::  41%|████      | 50/122 [00:01<00:01, 49.21it/s]
landmark Det::  46%|████▌     | 56/122 [00:01<00:01, 51.04it/s]
landmark Det::  51%|█████     | 62/122 [00:01<00:01, 52.43it/s]
landmark Det::  56%|█████▌    | 68/122 [00:01<00:01, 52.97it/s]
landmark Det::  61%|██████    | 74/122 [00:01<00:00, 53.58it/s]
landmark Det::  66%|██████▌   | 80/122 [00:02<00:00, 54.19it/s]
landmark Det::  70%|███████   | 86/122 [00:02<00:00, 54.44it/s]
landmark Det::  75%|███████▌  | 92/122 [00:02<00:00, 53.38it/s]
landmark Det::  80%|████████  | 98/122 [00:02<00:00, 53.31it/s]
landmark Det::  85%|████████▌ | 104/122 [00:02<00:00, 53.55it/s]
landmark Det::  90%|█████████ | 110/122 [00:02<00:00, 53.73it/s]
landmark Det::  95%|█████████▌| 116/122 [00:02<00:00, 54.48it/s]
landmark Det:: 100%|██████████| 122/122 [00:02<00:00, 54.89it/s]
landmark Det:: 100%|██████████| 122/122 [00:02<00:00, 43.08it/s]
  0%|          | 0/122 [00:00<?, ?it/s]
100%|██████████| 122/122 [00:00<00:00, 20623.29it/s]
  0%|          | 0/122 [00:00<?, ?it/s]
 54%|█████▍    | 66/122 [00:00<00:00, 656.23it/s]
100%|██████████| 122/122 [00:00<00:00, 671.87it/s]
FaceDet::   0%|          | 0/31 [00:00<?, ?it/s]
FaceDet::   3%|▎         | 1/31 [00:00<00:22,  1.34it/s]
FaceDet::   6%|▋         | 2/31 [00:00<00:12,  2.38it/s]
FaceDet::  10%|▉         | 3/31 [00:01<00:08,  3.26it/s]
FaceDet::  13%|█▎        | 4/31 [00:01<00:07,  3.83it/s]
FaceDet::  16%|█▌        | 5/31 [00:01<00:06,  4.26it/s]
FaceDet::  19%|█▉        | 6/31 [00:01<00:05,  4.53it/s]
FaceDet::  23%|██▎       | 7/31 [00:01<00:05,  4.77it/s]
FaceDet::  26%|██▌       | 8/31 [00:02<00:04,  4.95it/s]
FaceDet::  29%|██▉       | 9/31 [00:02<00:04,  5.04it/s]
FaceDet::  32%|███▏      | 10/31 [00:02<00:03,  5.37it/s]
FaceDet::  35%|███▌      | 11/31 [00:02<00:03,  5.40it/s]
FaceDet::  39%|███▊      | 12/31 [00:02<00:03,  5.39it/s]
FaceDet::  42%|████▏     | 13/31 [00:02<00:03,  5.47it/s]
FaceDet::  45%|████▌     | 14/31 [00:03<00:03,  5.56it/s]
FaceDet::  48%|████▊     | 15/31 [00:03<00:02,  5.53it/s]
FaceDet::  52%|█████▏    | 16/31 [00:03<00:02,  5.49it/s]
FaceDet::  55%|█████▍    | 17/31 [00:03<00:02,  5.46it/s]
FaceDet::  58%|█████▊    | 18/31 [00:03<00:02,  5.43it/s]
FaceDet::  61%|██████▏   | 19/31 [00:04<00:02,  5.43it/s]
FaceDet::  65%|██████▍   | 20/31 [00:04<00:02,  5.35it/s]
FaceDet::  68%|██████▊   | 21/31 [00:04<00:01,  5.36it/s]
FaceDet::  71%|███████   | 22/31 [00:04<00:01,  5.27it/s]
FaceDet::  74%|███████▍  | 23/31 [00:04<00:01,  5.24it/s]
FaceDet::  77%|███████▋  | 24/31 [00:04<00:01,  5.32it/s]
FaceDet::  81%|████████  | 25/31 [00:05<00:01,  5.33it/s]
FaceDet::  84%|████████▍ | 26/31 [00:05<00:00,  5.36it/s]
FaceDet::  87%|████████▋ | 27/31 [00:05<00:00,  5.36it/s]
FaceDet::  90%|█████████ | 28/31 [00:05<00:00,  5.36it/s]
FaceDet::  94%|█████████▎| 29/31 [00:05<00:00,  5.39it/s]
FaceDet::  97%|█████████▋| 30/31 [00:06<00:00,  5.48it/s]
FaceDet:: 100%|██████████| 31/31 [00:06<00:00,  3.83it/s]
FaceDet:: 100%|██████████| 31/31 [00:06<00:00,  4.74it/s]
[Step 6] Lip Synthesis::  12%|█▎        | 1/8 [00:23<02:43, 23.33s/it]
[Step 6] Lip Synthesis::  25%|██▌       | 2/8 [00:28<01:16, 12.74s/it]
[Step 6] Lip Synthesis::  38%|███▊      | 3/8 [00:33<00:46,  9.35s/it]
[Step 6] Lip Synthesis::  50%|█████     | 4/8 [00:39<00:31,  7.77s/it]
[Step 6] Lip Synthesis::  62%|██████▎   | 5/8 [00:44<00:20,  6.89s/it]
[Step 6] Lip Synthesis::  75%|███████▌  | 6/8 [00:49<00:12,  6.36s/it]
[Step 6] Lip Synthesis::  88%|████████▊ | 7/8 [00:55<00:06,  6.05s/it]
[Step 6] Lip Synthesis:: 100%|██████████| 8/8 [01:01<00:00,  6.03s/it]
[Step 6] Lip Synthesis:: 100%|██████████| 8/8 [01:01<00:00,  7.67s/it]
Version Details
Version ID
db5a650c807b007dc5f9e5abe27c53e1b62880d1f94d218d27ce7fa802711d67
Version Created
January 15, 2024
Run on Replicate →