xiankgx/video-retalking 🖼️🔢 → 🖼️
About
VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing in the Wild
Example Output
Output
Performance Metrics
150.26s
Prediction Time
282.06s
Total Time
All Input Parameters
{
"face": "https://replicate.delivery/pbxt/Jxq7lLdhxoe9ykDMENIFXqWTccDl1yIW3SGrRsMRp1ScvU9I/example_instantavatar_0901_josh.mp4",
"input_audio": "https://replicate.delivery/pbxt/Jxq7l9EEhbeaveI7YJUj2ZhMgYm5EUdJ7vztTmUvNjr0dU21/PM%20Lee%20Hsien%20Loong%20on%20the%20principles%20behind%20Singapore%27s%20stance%20on%20Ukraine.mp4",
"audio_duration": 5
}
Input Parameters
- face (required)
- Input video file of someone talking.
- input_audio (required)
- Input audio file.
- audio_duration
- Limit the audio to this duration in seconds.
Output Schema
Output
Example Execution Logs
face: /tmp/tmpik0cc1w1example_instantavatar_0901_josh.mp4 input_audio: /tmp/tmplyeu9revPM Lee Hsien Loong on the principles behind Singapore's stance on Ukraine.mp4 audio_duration: 5.0 landmarks_file: /tmp/video-retalkingujnr4vqo/landmarks.txt [Step 1] Landmarks Extraction in Video. landmark Det:: 0%| | 0/472 [00:00<?, ?it/s] landmark Det:: 0%| | 1/472 [00:09<1:12:24, 9.22s/it] landmark Det:: 0%| | 2/472 [00:16<1:01:32, 7.86s/it] landmark Det:: 2%|▏ | 8/472 [00:16<10:09, 1.31s/it] landmark Det:: 3%|▎ | 15/472 [00:16<04:15, 1.79it/s] landmark Det:: 5%|▍ | 22/472 [00:16<02:20, 3.20it/s] landmark Det:: 6%|▌ | 29/472 [00:16<01:26, 5.10it/s] landmark Det:: 8%|▊ | 36/472 [00:16<00:57, 7.63it/s] landmark Det:: 9%|▉ | 43/472 [00:16<00:39, 10.88it/s] landmark Det:: 11%|█ | 50/472 [00:16<00:28, 14.93it/s] landmark Det:: 12%|█▏ | 57/472 [00:17<00:21, 19.70it/s] landmark Det:: 14%|█▎ | 64/472 [00:17<00:16, 25.06it/s] landmark Det:: 15%|█▌ | 71/472 [00:17<00:13, 30.74it/s] landmark Det:: 17%|█▋ | 78/472 [00:17<00:11, 35.35it/s] landmark Det:: 18%|█▊ | 85/472 [00:17<00:09, 40.71it/s] landmark Det:: 19%|█▉ | 92/472 [00:17<00:08, 45.53it/s] landmark Det:: 21%|██ | 99/472 [00:17<00:07, 50.21it/s] landmark Det:: 22%|██▏ | 106/472 [00:17<00:06, 54.03it/s] landmark Det:: 24%|██▍ | 113/472 [00:17<00:06, 56.79it/s] landmark Det:: 25%|██▌ | 120/472 [00:18<00:05, 59.07it/s] landmark Det:: 27%|██▋ | 127/472 [00:18<00:05, 60.66it/s] landmark Det:: 28%|██▊ | 134/472 [00:18<00:05, 60.43it/s] landmark Det:: 30%|██▉ | 141/472 [00:18<00:05, 59.42it/s] landmark Det:: 31%|███▏ | 148/472 [00:18<00:05, 59.13it/s] landmark Det:: 33%|███▎ | 155/472 [00:18<00:05, 60.02it/s] landmark Det:: 34%|███▍ | 162/472 [00:18<00:05, 60.54it/s] landmark Det:: 36%|███▌ | 169/472 [00:18<00:04, 61.28it/s] landmark Det:: 37%|███▋ | 176/472 [00:18<00:04, 61.45it/s] landmark Det:: 39%|███▉ | 183/472 [00:19<00:04, 62.04it/s] landmark Det:: 40%|████ | 190/472 [00:19<00:04, 62.94it/s] landmark Det:: 42%|████▏ | 197/472 [00:19<00:04, 62.88it/s] landmark Det:: 43%|████▎ | 204/472 [00:19<00:04, 61.31it/s] landmark Det:: 45%|████▍ | 211/472 [00:19<00:04, 62.31it/s] landmark Det:: 46%|████▌ | 218/472 [00:19<00:04, 62.19it/s] landmark Det:: 48%|████▊ | 225/472 [00:19<00:03, 62.93it/s] landmark Det:: 49%|████▉ | 232/472 [00:19<00:03, 62.95it/s] landmark Det:: 51%|█████ | 239/472 [00:19<00:03, 62.69it/s] landmark Det:: 52%|█████▏ | 246/472 [00:20<00:03, 63.17it/s] landmark Det:: 54%|█████▎ | 253/472 [00:20<00:03, 63.44it/s] landmark Det:: 55%|█████▌ | 260/472 [00:20<00:03, 63.52it/s] landmark Det:: 57%|█████▋ | 267/472 [00:20<00:03, 61.86it/s] landmark Det:: 58%|█████▊ | 274/472 [00:20<00:03, 62.73it/s] landmark Det:: 60%|█████▉ | 281/472 [00:20<00:03, 63.34it/s] landmark Det:: 61%|██████ | 288/472 [00:20<00:02, 63.70it/s] landmark Det:: 62%|██████▎ | 295/472 [00:20<00:02, 64.17it/s] landmark Det:: 64%|██████▍ | 302/472 [00:20<00:02, 64.45it/s] landmark Det:: 65%|██████▌ | 309/472 [00:21<00:02, 64.63it/s] landmark Det:: 67%|██████▋ | 316/472 [00:21<00:02, 63.77it/s] landmark Det:: 68%|██████▊ | 323/472 [00:21<00:02, 63.99it/s] landmark Det:: 70%|██████▉ | 330/472 [00:21<00:02, 61.26it/s] landmark Det:: 71%|███████▏ | 337/472 [00:21<00:02, 62.46it/s] landmark Det:: 73%|███████▎ | 344/472 [00:21<00:02, 62.69it/s] landmark Det:: 74%|███████▍ | 351/472 [00:21<00:01, 63.64it/s] landmark Det:: 76%|███████▌ | 358/472 [00:21<00:01, 64.10it/s] landmark Det:: 77%|███████▋ | 365/472 [00:21<00:01, 64.43it/s] landmark Det:: 79%|███████▉ | 372/472 [00:22<00:01, 63.47it/s] landmark Det:: 80%|████████ | 379/472 [00:22<00:01, 63.73it/s] landmark Det:: 82%|████████▏ | 386/472 [00:22<00:01, 64.19it/s] landmark Det:: 83%|████████▎ | 393/472 [00:22<00:01, 62.62it/s] landmark Det:: 85%|████████▍ | 400/472 [00:22<00:01, 63.04it/s] landmark Det:: 86%|████████▌ | 407/472 [00:22<00:01, 62.83it/s] landmark Det:: 88%|████████▊ | 414/472 [00:22<00:00, 62.05it/s] landmark Det:: 89%|████████▉ | 421/472 [00:22<00:00, 62.40it/s] landmark Det:: 91%|█████████ | 428/472 [00:22<00:00, 62.68it/s] landmark Det:: 92%|█████████▏| 435/472 [00:23<00:00, 62.85it/s] landmark Det:: 94%|█████████▎| 442/472 [00:23<00:00, 63.36it/s] landmark Det:: 95%|█████████▌| 449/472 [00:23<00:00, 62.76it/s] landmark Det:: 97%|█████████▋| 456/472 [00:23<00:00, 61.12it/s] landmark Det:: 98%|█████████▊| 463/472 [00:23<00:00, 61.87it/s] landmark Det:: 100%|█████████▉| 470/472 [00:23<00:00, 62.42it/s] landmark Det:: 100%|██████████| 472/472 [00:23<00:00, 19.98it/s] coeffs_file: /tmp/video-retalkingujnr4vqo/coeffs.npy [Step 2] 3DMM Extraction In Video:: 0%| | 0/472 [00:00<?, ?it/s] [Step 2] 3DMM Extraction In Video:: 0%| | 1/472 [00:00<01:24, 5.55it/s] [Step 2] 3DMM Extraction In Video:: 3%|▎ | 14/472 [00:00<00:07, 60.06it/s] [Step 2] 3DMM Extraction In Video:: 6%|▌ | 27/472 [00:00<00:05, 86.35it/s] [Step 2] 3DMM Extraction In Video:: 9%|▊ | 41/472 [00:00<00:04, 103.00it/s] [Step 2] 3DMM Extraction In Video:: 12%|█▏ | 55/472 [00:00<00:03, 112.87it/s] [Step 2] 3DMM Extraction In Video:: 14%|█▍ | 67/472 [00:00<00:03, 113.13it/s] [Step 2] 3DMM Extraction In Video:: 17%|█▋ | 80/472 [00:00<00:03, 117.85it/s] [Step 2] 3DMM Extraction In Video:: 20%|█▉ | 94/472 [00:00<00:03, 121.97it/s] [Step 2] 3DMM Extraction In Video:: 23%|██▎ | 108/472 [00:01<00:02, 125.03it/s] [Step 2] 3DMM Extraction In Video:: 26%|██▌ | 122/472 [00:01<00:02, 127.09it/s] [Step 2] 3DMM Extraction In Video:: 29%|██▉ | 136/472 [00:01<00:02, 128.55it/s] [Step 2] 3DMM Extraction In Video:: 32%|███▏ | 150/472 [00:01<00:02, 129.15it/s] [Step 2] 3DMM Extraction In Video:: 35%|███▍ | 164/472 [00:01<00:02, 129.75it/s] [Step 2] 3DMM Extraction In Video:: 38%|███▊ | 178/472 [00:01<00:02, 130.47it/s] [Step 2] 3DMM Extraction In Video:: 41%|████ | 192/472 [00:01<00:02, 126.67it/s] [Step 2] 3DMM Extraction In Video:: 44%|████▎ | 206/472 [00:01<00:02, 128.04it/s] [Step 2] 3DMM Extraction In Video:: 47%|████▋ | 220/472 [00:01<00:01, 128.74it/s] [Step 2] 3DMM Extraction In Video:: 50%|████▉ | 234/472 [00:01<00:01, 129.68it/s] [Step 2] 3DMM Extraction In Video:: 53%|█████▎ | 248/472 [00:02<00:01, 130.14it/s] [Step 2] 3DMM Extraction In Video:: 56%|█████▌ | 262/472 [00:02<00:01, 130.62it/s] [Step 2] 3DMM Extraction In Video:: 58%|█████▊ | 276/472 [00:02<00:01, 130.88it/s] [Step 2] 3DMM Extraction In Video:: 61%|██████▏ | 290/472 [00:02<00:01, 130.85it/s] [Step 2] 3DMM Extraction In Video:: 64%|██████▍ | 304/472 [00:02<00:01, 131.26it/s] [Step 2] 3DMM Extraction In Video:: 67%|██████▋ | 318/472 [00:02<00:01, 127.86it/s] [Step 2] 3DMM Extraction In Video:: 70%|███████ | 331/472 [00:02<00:01, 128.18it/s] [Step 2] 3DMM Extraction In Video:: 73%|███████▎ | 345/472 [00:02<00:00, 129.33it/s] [Step 2] 3DMM Extraction In Video:: 76%|███████▌ | 359/472 [00:02<00:00, 129.85it/s] [Step 2] 3DMM Extraction In Video:: 79%|███████▉ | 373/472 [00:03<00:00, 130.51it/s] [Step 2] 3DMM Extraction In Video:: 82%|████████▏ | 387/472 [00:03<00:00, 130.97it/s] [Step 2] 3DMM Extraction In Video:: 85%|████████▍ | 401/472 [00:03<00:00, 131.34it/s] [Step 2] 3DMM Extraction In Video:: 88%|████████▊ | 415/472 [00:03<00:00, 131.48it/s] [Step 2] 3DMM Extraction In Video:: 91%|█████████ | 429/472 [00:03<00:00, 131.03it/s] [Step 2] 3DMM Extraction In Video:: 94%|█████████▍| 443/472 [00:03<00:00, 131.19it/s] [Step 2] 3DMM Extraction In Video:: 97%|█████████▋| 457/472 [00:03<00:00, 125.88it/s] [Step 2] 3DMM Extraction In Video:: 100%|█████████▉| 470/472 [00:03<00:00, 126.98it/s] [Step 2] 3DMM Extraction In Video:: 100%|██████████| 472/472 [00:03<00:00, 123.40it/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%| | 0/472 [00:00<?, ?it/s] [Step 3] Stabilize the expression In Video:: 0%| | 1/472 [00:00<02:41, 2.91it/s] [Step 3] Stabilize the expression In Video:: 1%| | 3/472 [00:00<01:09, 6.72it/s] [Step 3] Stabilize the expression In Video:: 1%| | 5/472 [00:00<00:52, 8.92it/s] [Step 3] Stabilize the expression In Video:: 1%|▏ | 7/472 [00:00<00:45, 10.27it/s] [Step 3] Stabilize the expression In Video:: 2%|▏ | 9/472 [00:00<00:41, 11.14it/s] [Step 3] Stabilize the expression In Video:: 2%|▏ | 11/472 [00:01<00:39, 11.69it/s] [Step 3] Stabilize the expression In Video:: 3%|▎ | 13/472 [00:01<00:37, 12.08it/s] [Step 3] Stabilize the expression In Video:: 3%|▎ | 15/472 [00:01<00:36, 12.36it/s] [Step 3] Stabilize the expression In Video:: 4%|▎ | 17/472 [00:01<00:36, 12.54it/s] [Step 3] Stabilize the expression In Video:: 4%|▍ | 19/472 [00:01<00:35, 12.62it/s] [Step 3] Stabilize the expression In Video:: 4%|▍ | 21/472 [00:01<00:35, 12.72it/s] [Step 3] Stabilize the expression In Video:: 5%|▍ | 23/472 [00:02<00:35, 12.80it/s] [Step 3] Stabilize the expression In Video:: 5%|▌ | 25/472 [00:02<00:34, 12.84it/s] [Step 3] Stabilize the expression In Video:: 6%|▌ | 27/472 [00:02<00:34, 12.81it/s] [Step 3] Stabilize the expression In Video:: 6%|▌ | 29/472 [00:02<00:34, 12.76it/s] [Step 3] Stabilize the expression In Video:: 7%|▋ | 31/472 [00:02<00:34, 12.63it/s] [Step 3] Stabilize the expression In Video:: 7%|▋ | 33/472 [00:02<00:34, 12.73it/s] [Step 3] Stabilize the expression In Video:: 7%|▋ | 35/472 [00:02<00:34, 12.77it/s] [Step 3] Stabilize the expression In Video:: 8%|▊ | 37/472 [00:03<00:33, 12.82it/s] [Step 3] Stabilize the expression In Video:: 8%|▊ | 39/472 [00:03<00:34, 12.71it/s] [Step 3] Stabilize the expression In Video:: 9%|▊ | 41/472 [00:03<00:33, 12.77it/s] [Step 3] Stabilize the expression In Video:: 9%|▉ | 43/472 [00:03<00:34, 12.57it/s] [Step 3] Stabilize the expression In Video:: 10%|▉ | 45/472 [00:03<00:33, 12.65it/s] [Step 3] Stabilize the expression In Video:: 10%|▉ | 47/472 [00:03<00:33, 12.73it/s] [Step 3] Stabilize the expression In Video:: 10%|█ | 49/472 [00:04<00:33, 12.80it/s] [Step 3] Stabilize the expression In Video:: 11%|█ | 51/472 [00:04<00:32, 12.82it/s] [Step 3] Stabilize the expression In Video:: 11%|█ | 53/472 [00:04<00:32, 12.86it/s] [Step 3] Stabilize the expression In Video:: 12%|█▏ | 55/472 [00:04<00:32, 12.88it/s] [Step 3] Stabilize the expression In Video:: 12%|█▏ | 57/472 [00:04<00:32, 12.87it/s] [Step 3] Stabilize the expression In Video:: 12%|█▎ | 59/472 [00:04<00:32, 12.80it/s] [Step 3] Stabilize the expression In Video:: 13%|█▎ | 61/472 [00:05<00:32, 12.83it/s] [Step 3] Stabilize the expression In Video:: 13%|█▎ | 63/472 [00:05<00:31, 12.87it/s] [Step 3] Stabilize the expression In Video:: 14%|█▍ | 65/472 [00:05<00:31, 12.90it/s] [Step 3] Stabilize the expression In Video:: 14%|█▍ | 67/472 [00:05<00:31, 12.87it/s] [Step 3] Stabilize the expression In Video:: 15%|█▍ | 69/472 [00:05<00:31, 12.90it/s] [Step 3] Stabilize the expression In Video:: 15%|█▌ | 71/472 [00:05<00:31, 12.91it/s] [Step 3] Stabilize the expression In Video:: 15%|█▌ | 73/472 [00:05<00:30, 12.88it/s] [Step 3] Stabilize the expression In Video:: 16%|█▌ | 75/472 [00:06<00:30, 12.87it/s] [Step 3] Stabilize the expression In Video:: 16%|█▋ | 77/472 [00:06<00:30, 12.89it/s] [Step 3] Stabilize the expression In Video:: 17%|█▋ | 79/472 [00:06<00:30, 12.91it/s] [Step 3] Stabilize the expression In Video:: 17%|█▋ | 81/472 [00:06<00:30, 12.92it/s] [Step 3] Stabilize the expression In Video:: 18%|█▊ | 83/472 [00:06<00:30, 12.90it/s] [Step 3] Stabilize the expression In Video:: 18%|█▊ | 85/472 [00:06<00:29, 12.91it/s] [Step 3] Stabilize the expression In Video:: 18%|█▊ | 87/472 [00:07<00:29, 12.93it/s] [Step 3] Stabilize the expression In Video:: 19%|█▉ | 89/472 [00:07<00:29, 12.93it/s] [Step 3] Stabilize the expression In Video:: 19%|█▉ | 91/472 [00:07<00:29, 12.86it/s] [Step 3] Stabilize the expression In Video:: 20%|█▉ | 93/472 [00:07<00:29, 12.87it/s] [Step 3] Stabilize the expression In Video:: 20%|██ | 95/472 [00:07<00:29, 12.89it/s] [Step 3] Stabilize the expression In Video:: 21%|██ | 97/472 [00:07<00:29, 12.91it/s] [Step 3] Stabilize the expression In Video:: 21%|██ | 99/472 [00:07<00:28, 12.88it/s] [Step 3] Stabilize the expression In Video:: 21%|██▏ | 101/472 [00:08<00:28, 12.91it/s] [Step 3] Stabilize the expression In Video:: 22%|██▏ | 103/472 [00:08<00:28, 12.92it/s] [Step 3] Stabilize the expression In Video:: 22%|██▏ | 105/472 [00:08<00:28, 12.92it/s] [Step 3] Stabilize the expression In Video:: 23%|██▎ | 107/472 [00:08<00:28, 12.88it/s] [Step 3] Stabilize the expression In Video:: 23%|██▎ | 109/472 [00:08<00:28, 12.88it/s] [Step 3] Stabilize the expression In Video:: 24%|██▎ | 111/472 [00:08<00:27, 12.90it/s] [Step 3] Stabilize the expression In Video:: 24%|██▍ | 113/472 [00:09<00:27, 12.91it/s] [Step 3] Stabilize the expression In Video:: 24%|██▍ | 115/472 [00:09<00:27, 12.89it/s] [Step 3] Stabilize the expression In Video:: 25%|██▍ | 117/472 [00:09<00:27, 12.90it/s] [Step 3] Stabilize the expression In Video:: 25%|██▌ | 119/472 [00:09<00:27, 12.92it/s] [Step 3] Stabilize the expression In Video:: 26%|██▌ | 121/472 [00:09<00:27, 12.79it/s] [Step 3] Stabilize the expression In Video:: 26%|██▌ | 123/472 [00:09<00:27, 12.80it/s] [Step 3] Stabilize the expression In Video:: 26%|██▋ | 125/472 [00:09<00:27, 12.85it/s] [Step 3] Stabilize the expression In Video:: 27%|██▋ | 127/472 [00:10<00:26, 12.80it/s] [Step 3] Stabilize the expression In Video:: 27%|██▋ | 129/472 [00:10<00:26, 12.84it/s] [Step 3] Stabilize the expression In Video:: 28%|██▊ | 131/472 [00:10<00:26, 12.84it/s] [Step 3] Stabilize the expression In Video:: 28%|██▊ | 133/472 [00:10<00:26, 12.87it/s] [Step 3] Stabilize the expression In Video:: 29%|██▊ | 135/472 [00:10<00:26, 12.89it/s] [Step 3] Stabilize the expression In Video:: 29%|██▉ | 137/472 [00:10<00:26, 12.88it/s] [Step 3] Stabilize the expression In Video:: 29%|██▉ | 139/472 [00:11<00:25, 12.85it/s] [Step 3] Stabilize the expression In Video:: 30%|██▉ | 141/472 [00:11<00:25, 12.88it/s] [Step 3] Stabilize the expression In Video:: 30%|███ | 143/472 [00:11<00:25, 12.90it/s] [Step 3] Stabilize the expression In Video:: 31%|███ | 145/472 [00:11<00:25, 12.92it/s] [Step 3] Stabilize the expression In Video:: 31%|███ | 147/472 [00:11<00:25, 12.91it/s] [Step 3] Stabilize the expression In Video:: 32%|███▏ | 149/472 [00:11<00:24, 12.92it/s] [Step 3] Stabilize the expression In Video:: 32%|███▏ | 151/472 [00:12<00:24, 12.93it/s] [Step 3] Stabilize the expression In Video:: 32%|███▏ | 153/472 [00:12<00:24, 12.93it/s] [Step 3] Stabilize the expression In Video:: 33%|███▎ | 155/472 [00:12<00:24, 12.94it/s] [Step 3] Stabilize the expression In Video:: 33%|███▎ | 157/472 [00:12<00:24, 12.94it/s] [Step 3] Stabilize the expression In Video:: 34%|███▎ | 159/472 [00:12<00:24, 12.95it/s] [Step 3] Stabilize the expression In Video:: 34%|███▍ | 161/472 [00:12<00:24, 12.95it/s] [Step 3] Stabilize the expression In Video:: 35%|███▍ | 163/472 [00:12<00:23, 12.93it/s] [Step 3] Stabilize the expression In Video:: 35%|███▍ | 165/472 [00:13<00:23, 12.94it/s] [Step 3] Stabilize the expression In Video:: 35%|███▌ | 167/472 [00:13<00:23, 12.90it/s] [Step 3] Stabilize the expression In Video:: 36%|███▌ | 169/472 [00:13<00:23, 12.90it/s] [Step 3] Stabilize the expression In Video:: 36%|███▌ | 171/472 [00:13<00:23, 12.89it/s] [Step 3] Stabilize the expression In Video:: 37%|███▋ | 173/472 [00:13<00:23, 12.76it/s] [Step 3] Stabilize the expression In Video:: 37%|███▋ | 175/472 [00:13<00:23, 12.78it/s] [Step 3] Stabilize the expression In Video:: 38%|███▊ | 177/472 [00:14<00:22, 12.83it/s] [Step 3] Stabilize the expression In Video:: 38%|███▊ | 179/472 [00:14<00:22, 12.84it/s] [Step 3] Stabilize the expression In Video:: 38%|███▊ | 181/472 [00:14<00:22, 12.87it/s] [Step 3] Stabilize the expression In Video:: 39%|███▉ | 183/472 [00:14<00:22, 12.89it/s] [Step 3] Stabilize the expression In Video:: 39%|███▉ | 185/472 [00:14<00:22, 12.90it/s] [Step 3] Stabilize the expression In Video:: 40%|███▉ | 187/472 [00:14<00:22, 12.92it/s] [Step 3] Stabilize the expression In Video:: 40%|████ | 189/472 [00:14<00:21, 12.93it/s] [Step 3] Stabilize the expression In Video:: 40%|████ | 191/472 [00:15<00:21, 12.93it/s] [Step 3] Stabilize the expression In Video:: 41%|████ | 193/472 [00:15<00:21, 12.94it/s] [Step 3] Stabilize the expression In Video:: 41%|████▏ | 195/472 [00:15<00:21, 12.91it/s] [Step 3] Stabilize the expression In Video:: 42%|████▏ | 197/472 [00:15<00:21, 12.93it/s] [Step 3] Stabilize the expression In Video:: 42%|████▏ | 199/472 [00:15<00:21, 12.91it/s] [Step 3] Stabilize the expression In Video:: 43%|████▎ | 201/472 [00:15<00:21, 12.90it/s] [Step 3] Stabilize the expression In Video:: 43%|████▎ | 203/472 [00:16<00:20, 12.88it/s] [Step 3] Stabilize the expression In Video:: 43%|████▎ | 205/472 [00:16<00:20, 12.90it/s] [Step 3] Stabilize the expression In Video:: 44%|████▍ | 207/472 [00:16<00:20, 12.92it/s] [Step 3] Stabilize the expression In Video:: 44%|████▍ | 209/472 [00:16<00:20, 12.93it/s] [Step 3] Stabilize the expression In Video:: 45%|████▍ | 211/472 [00:16<00:20, 12.91it/s] [Step 3] Stabilize the expression In Video:: 45%|████▌ | 213/472 [00:16<00:20, 12.92it/s] [Step 3] Stabilize the expression In Video:: 46%|████▌ | 215/472 [00:16<00:19, 12.92it/s] [Step 3] Stabilize the expression In Video:: 46%|████▌ | 217/472 [00:17<00:19, 12.92it/s] [Step 3] Stabilize the expression In Video:: 46%|████▋ | 219/472 [00:17<00:19, 12.90it/s] [Step 3] Stabilize the expression In Video:: 47%|████▋ | 221/472 [00:17<00:19, 12.86it/s] [Step 3] Stabilize the expression In Video:: 47%|████▋ | 223/472 [00:17<00:19, 12.87it/s] [Step 3] Stabilize the expression In Video:: 48%|████▊ | 225/472 [00:17<00:19, 12.87it/s] [Step 3] Stabilize the expression In Video:: 48%|████▊ | 227/472 [00:17<00:19, 12.86it/s] [Step 3] Stabilize the expression In Video:: 49%|████▊ | 229/472 [00:18<00:18, 12.89it/s] [Step 3] Stabilize the expression In Video:: 49%|████▉ | 231/472 [00:18<00:18, 12.91it/s] [Step 3] Stabilize the expression In Video:: 49%|████▉ | 233/472 [00:18<00:18, 12.93it/s] [Step 3] Stabilize the expression In Video:: 50%|████▉ | 235/472 [00:18<00:18, 12.90it/s] [Step 3] Stabilize the expression In Video:: 50%|█████ | 237/472 [00:18<00:18, 12.78it/s] [Step 3] Stabilize the expression In Video:: 51%|█████ | 239/472 [00:18<00:18, 12.80it/s] [Step 3] Stabilize the expression In Video:: 51%|█████ | 241/472 [00:18<00:17, 12.84it/s] [Step 3] Stabilize the expression In Video:: 51%|█████▏ | 243/472 [00:19<00:17, 12.85it/s] [Step 3] Stabilize the expression In Video:: 52%|█████▏ | 245/472 [00:19<00:17, 12.88it/s] [Step 3] Stabilize the expression In Video:: 52%|█████▏ | 247/472 [00:19<00:17, 12.90it/s] [Step 3] Stabilize the expression In Video:: 53%|█████▎ | 249/472 [00:19<00:17, 12.86it/s] [Step 3] Stabilize the expression In Video:: 53%|█████▎ | 251/472 [00:19<00:17, 12.84it/s] [Step 3] Stabilize the expression In Video:: 54%|█████▎ | 253/472 [00:19<00:17, 12.87it/s] [Step 3] Stabilize the expression In Video:: 54%|█████▍ | 255/472 [00:20<00:16, 12.89it/s] [Step 3] Stabilize the expression In Video:: 54%|█████▍ | 257/472 [00:20<00:16, 12.89it/s] [Step 3] Stabilize the expression In Video:: 55%|█████▍ | 259/472 [00:20<00:16, 12.88it/s] [Step 3] Stabilize the expression In Video:: 55%|█████▌ | 261/472 [00:20<00:16, 12.90it/s] [Step 3] Stabilize the expression In Video:: 56%|█████▌ | 263/472 [00:20<00:16, 12.91it/s] [Step 3] Stabilize the expression In Video:: 56%|█████▌ | 265/472 [00:20<00:16, 12.90it/s] [Step 3] Stabilize the expression In Video:: 57%|█████▋ | 267/472 [00:21<00:15, 12.86it/s] [Step 3] Stabilize the expression In Video:: 57%|█████▋ | 269/472 [00:21<00:15, 12.89it/s] [Step 3] Stabilize the expression In Video:: 57%|█████▋ | 271/472 [00:21<00:15, 12.90it/s] [Step 3] Stabilize the expression In Video:: 58%|█████▊ | 273/472 [00:21<00:15, 12.92it/s] [Step 3] Stabilize the expression In Video:: 58%|█████▊ | 275/472 [00:21<00:15, 12.91it/s] [Step 3] Stabilize the expression In Video:: 59%|█████▊ | 277/472 [00:21<00:15, 12.92it/s] [Step 3] Stabilize the expression In Video:: 59%|█████▉ | 279/472 [00:21<00:14, 12.93it/s] [Step 3] Stabilize the expression In Video:: 60%|█████▉ | 281/472 [00:22<00:14, 12.94it/s] [Step 3] Stabilize the expression In Video:: 60%|█████▉ | 283/472 [00:22<00:14, 12.91it/s] [Step 3] Stabilize the expression In Video:: 60%|██████ | 285/472 [00:22<00:14, 12.90it/s] [Step 3] Stabilize the expression In Video:: 61%|██████ | 287/472 [00:22<00:14, 12.83it/s] [Step 3] Stabilize the expression In Video:: 61%|██████ | 289/472 [00:22<00:14, 12.85it/s] [Step 3] Stabilize the expression In Video:: 62%|██████▏ | 291/472 [00:22<00:14, 12.84it/s] [Step 3] Stabilize the expression In Video:: 62%|██████▏ | 293/472 [00:23<00:14, 12.76it/s] [Step 3] Stabilize the expression In Video:: 62%|██████▎ | 295/472 [00:23<00:13, 12.82it/s] [Step 3] Stabilize the expression In Video:: 63%|██████▎ | 297/472 [00:23<00:13, 12.86it/s] [Step 3] Stabilize the expression In Video:: 63%|██████▎ | 299/472 [00:23<00:13, 12.86it/s] [Step 3] Stabilize the expression In Video:: 64%|██████▍ | 301/472 [00:23<00:13, 12.89it/s] [Step 3] Stabilize the expression In Video:: 64%|██████▍ | 303/472 [00:23<00:13, 12.91it/s] [Step 3] Stabilize the expression In Video:: 65%|██████▍ | 305/472 [00:23<00:12, 12.92it/s] [Step 3] Stabilize the expression In Video:: 65%|██████▌ | 307/472 [00:24<00:12, 12.90it/s] [Step 3] Stabilize the expression In Video:: 65%|██████▌ | 309/472 [00:24<00:12, 12.92it/s] [Step 3] Stabilize the expression In Video:: 66%|██████▌ | 311/472 [00:24<00:12, 12.93it/s] [Step 3] Stabilize the expression In Video:: 66%|██████▋ | 313/472 [00:24<00:12, 12.94it/s] [Step 3] Stabilize the expression In Video:: 67%|██████▋ | 315/472 [00:24<00:12, 12.91it/s] [Step 3] Stabilize the expression In Video:: 67%|██████▋ | 317/472 [00:24<00:12, 12.86it/s] [Step 3] Stabilize the expression In Video:: 68%|██████▊ | 319/472 [00:25<00:11, 12.87it/s] [Step 3] Stabilize the expression In Video:: 68%|██████▊ | 321/472 [00:25<00:11, 12.88it/s] [Step 3] Stabilize the expression In Video:: 68%|██████▊ | 323/472 [00:25<00:11, 12.87it/s] [Step 3] Stabilize the expression In Video:: 69%|██████▉ | 325/472 [00:25<00:11, 12.90it/s] [Step 3] Stabilize the expression In Video:: 69%|██████▉ | 327/472 [00:25<00:11, 12.78it/s] [Step 3] Stabilize the expression In Video:: 70%|██████▉ | 329/472 [00:25<00:11, 12.77it/s] [Step 3] Stabilize the expression In Video:: 70%|███████ | 331/472 [00:25<00:11, 12.80it/s] [Step 3] Stabilize the expression In Video:: 71%|███████ | 333/472 [00:26<00:10, 12.83it/s] [Step 3] Stabilize the expression In Video:: 71%|███████ | 335/472 [00:26<00:10, 12.83it/s] [Step 3] Stabilize the expression In Video:: 71%|███████▏ | 337/472 [00:26<00:10, 12.82it/s] [Step 3] Stabilize the expression In Video:: 72%|███████▏ | 339/472 [00:26<00:10, 12.59it/s] [Step 3] Stabilize the expression In Video:: 72%|███████▏ | 341/472 [00:26<00:10, 12.61it/s] [Step 3] Stabilize the expression In Video:: 73%|███████▎ | 343/472 [00:26<00:10, 12.71it/s] [Step 3] Stabilize the expression In Video:: 73%|███████▎ | 345/472 [00:27<00:09, 12.79it/s] [Step 3] Stabilize the expression In Video:: 74%|███████▎ | 347/472 [00:27<00:09, 12.81it/s] [Step 3] Stabilize the expression In Video:: 74%|███████▍ | 349/472 [00:27<00:09, 12.85it/s] [Step 3] Stabilize the expression In Video:: 74%|███████▍ | 351/472 [00:27<00:09, 12.87it/s] [Step 3] Stabilize the expression In Video:: 75%|███████▍ | 353/472 [00:27<00:09, 12.89it/s] [Step 3] Stabilize the expression In Video:: 75%|███████▌ | 355/472 [00:27<00:09, 12.86it/s] [Step 3] Stabilize the expression In Video:: 76%|███████▌ | 357/472 [00:28<00:08, 12.89it/s] [Step 3] Stabilize the expression In Video:: 76%|███████▌ | 359/472 [00:28<00:08, 12.91it/s] [Step 3] Stabilize the expression In Video:: 76%|███████▋ | 361/472 [00:28<00:08, 12.91it/s] [Step 3] Stabilize the expression In Video:: 77%|███████▋ | 363/472 [00:28<00:08, 12.90it/s] [Step 3] Stabilize the expression In Video:: 77%|███████▋ | 365/472 [00:28<00:08, 12.91it/s] [Step 3] Stabilize the expression In Video:: 78%|███████▊ | 367/472 [00:28<00:08, 12.93it/s] [Step 3] Stabilize the expression In Video:: 78%|███████▊ | 369/472 [00:28<00:07, 12.90it/s] [Step 3] Stabilize the expression In Video:: 79%|███████▊ | 371/472 [00:29<00:07, 12.87it/s] [Step 3] Stabilize the expression In Video:: 79%|███████▉ | 373/472 [00:29<00:07, 12.89it/s] [Step 3] Stabilize the expression In Video:: 79%|███████▉ | 375/472 [00:29<00:07, 12.91it/s] [Step 3] Stabilize the expression In Video:: 80%|███████▉ | 377/472 [00:29<00:07, 12.93it/s] [Step 3] Stabilize the expression In Video:: 80%|████████ | 379/472 [00:29<00:07, 12.91it/s] [Step 3] Stabilize the expression In Video:: 81%|████████ | 381/472 [00:29<00:07, 12.90it/s] [Step 3] Stabilize the expression In Video:: 81%|████████ | 383/472 [00:30<00:06, 12.91it/s] [Step 3] Stabilize the expression In Video:: 82%|████████▏ | 385/472 [00:30<00:06, 12.93it/s] [Step 3] Stabilize the expression In Video:: 82%|████████▏ | 387/472 [00:30<00:06, 12.91it/s] [Step 3] Stabilize the expression In Video:: 82%|████████▏ | 389/472 [00:30<00:06, 12.92it/s] [Step 3] Stabilize the expression In Video:: 83%|████████▎ | 391/472 [00:30<00:06, 12.93it/s] [Step 3] Stabilize the expression In Video:: 83%|████████▎ | 393/472 [00:30<00:06, 12.94it/s] [Step 3] Stabilize the expression In Video:: 84%|████████▎ | 395/472 [00:30<00:05, 12.91it/s] [Step 3] Stabilize the expression In Video:: 84%|████████▍ | 397/472 [00:31<00:05, 12.87it/s] [Step 3] Stabilize the expression In Video:: 85%|████████▍ | 399/472 [00:31<00:05, 12.87it/s] [Step 3] Stabilize the expression In Video:: 85%|████████▍ | 401/472 [00:31<00:05, 12.89it/s] [Step 3] Stabilize the expression In Video:: 85%|████████▌ | 403/472 [00:31<00:05, 12.88it/s] [Step 3] Stabilize the expression In Video:: 86%|████████▌ | 405/472 [00:31<00:05, 12.90it/s] [Step 3] Stabilize the expression In Video:: 86%|████████▌ | 407/472 [00:31<00:05, 12.91it/s] [Step 3] Stabilize the expression In Video:: 87%|████████▋ | 409/472 [00:32<00:04, 12.92it/s] [Step 3] Stabilize the expression In Video:: 87%|████████▋ | 411/472 [00:32<00:04, 12.91it/s] [Step 3] Stabilize the expression In Video:: 88%|████████▊ | 413/472 [00:32<00:04, 12.92it/s] [Step 3] Stabilize the expression In Video:: 88%|████████▊ | 415/472 [00:32<00:04, 12.89it/s] [Step 3] Stabilize the expression In Video:: 88%|████████▊ | 417/472 [00:32<00:04, 12.89it/s] [Step 3] Stabilize the expression In Video:: 89%|████████▉ | 419/472 [00:32<00:04, 12.90it/s] [Step 3] Stabilize the expression In Video:: 89%|████████▉ | 421/472 [00:32<00:03, 12.91it/s] [Step 3] Stabilize the expression In Video:: 90%|████████▉ | 423/472 [00:33<00:03, 12.93it/s] [Step 3] Stabilize the expression In Video:: 90%|█████████ | 425/472 [00:33<00:03, 12.93it/s] [Step 3] Stabilize the expression In Video:: 90%|█████████ | 427/472 [00:33<00:03, 12.91it/s] [Step 3] Stabilize the expression In Video:: 91%|█████████ | 429/472 [00:33<00:03, 12.92it/s] [Step 3] Stabilize the expression In Video:: 91%|█████████▏| 431/472 [00:33<00:03, 12.93it/s] [Step 3] Stabilize the expression In Video:: 92%|█████████▏| 433/472 [00:33<00:03, 12.94it/s] [Step 3] Stabilize the expression In Video:: 92%|█████████▏| 435/472 [00:34<00:02, 12.91it/s] [Step 3] Stabilize the expression In Video:: 93%|█████████▎| 437/472 [00:34<00:02, 12.92it/s] [Step 3] Stabilize the expression In Video:: 93%|█████████▎| 439/472 [00:34<00:02, 12.93it/s] [Step 3] Stabilize the expression In Video:: 93%|█████████▎| 441/472 [00:34<00:02, 12.88it/s] [Step 3] Stabilize the expression In Video:: 94%|█████████▍| 443/472 [00:34<00:02, 12.84it/s] [Step 3] Stabilize the expression In Video:: 94%|█████████▍| 445/472 [00:34<00:02, 12.87it/s] [Step 3] Stabilize the expression In Video:: 95%|█████████▍| 447/472 [00:34<00:01, 12.90it/s] [Step 3] Stabilize the expression In Video:: 95%|█████████▌| 449/472 [00:35<00:01, 12.91it/s] [Step 3] Stabilize the expression In Video:: 96%|█████████▌| 451/472 [00:35<00:01, 12.89it/s] [Step 3] Stabilize the expression In Video:: 96%|█████████▌| 453/472 [00:35<00:01, 12.91it/s] [Step 3] Stabilize the expression In Video:: 96%|█████████▋| 455/472 [00:35<00:01, 12.91it/s] [Step 3] Stabilize the expression In Video:: 97%|█████████▋| 457/472 [00:35<00:01, 12.91it/s] [Step 3] Stabilize the expression In Video:: 97%|█████████▋| 459/472 [00:35<00:01, 12.90it/s] [Step 3] Stabilize the expression In Video:: 98%|█████████▊| 461/472 [00:36<00:00, 12.92it/s] [Step 3] Stabilize the expression In Video:: 98%|█████████▊| 463/472 [00:36<00:00, 12.88it/s] [Step 3] Stabilize the expression In Video:: 99%|█████████▊| 465/472 [00:36<00:00, 12.82it/s] [Step 3] Stabilize the expression In Video:: 99%|█████████▉| 467/472 [00:36<00:00, 12.79it/s] [Step 3] Stabilize the expression In Video:: 99%|█████████▉| 469/472 [00:36<00:00, 12.74it/s] [Step 3] Stabilize the expression In Video:: 100%|█████████▉| 471/472 [00:36<00:00, 12.78it/s] [Step 3] Stabilize the expression In Video:: 100%|██████████| 472/472 [00:36<00:00, 12.78it/s] temp_audio_file: /tmp/video-retalkingujnr4vqo/audio.wav Limiting audio duration to: 5.0 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<02:16, 1.13s/it] [Step 5] Reference Enhancement: 2%|▏ | 2/122 [00:01<01:05, 1.82it/s] [Step 5] Reference Enhancement: 2%|▏ | 3/122 [00:01<00:42, 2.78it/s] [Step 5] Reference Enhancement: 3%|▎ | 4/122 [00:01<00:32, 3.69it/s] [Step 5] Reference Enhancement: 4%|▍ | 5/122 [00:01<00:26, 4.48it/s] [Step 5] Reference Enhancement: 5%|▍ | 6/122 [00:01<00:22, 5.17it/s] [Step 5] Reference Enhancement: 6%|▌ | 7/122 [00:01<00:20, 5.74it/s] [Step 5] Reference Enhancement: 7%|▋ | 8/122 [00:02<00:18, 6.16it/s] [Step 5] Reference Enhancement: 7%|▋ | 9/122 [00:02<00:17, 6.48it/s] [Step 5] Reference Enhancement: 8%|▊ | 10/122 [00:02<00:16, 6.65it/s] [Step 5] Reference Enhancement: 9%|▉ | 11/122 [00:02<00:16, 6.82it/s] [Step 5] Reference Enhancement: 10%|▉ | 12/122 [00:02<00:15, 6.96it/s] [Step 5] Reference Enhancement: 11%|█ | 13/122 [00:02<00:15, 7.06it/s] [Step 5] Reference Enhancement: 11%|█▏ | 14/122 [00:02<00:15, 7.13it/s] [Step 5] Reference Enhancement: 12%|█▏ | 15/122 [00:03<00:14, 7.16it/s] [Step 5] Reference Enhancement: 13%|█▎ | 16/122 [00:03<00:14, 7.22it/s] [Step 5] Reference Enhancement: 14%|█▍ | 17/122 [00:03<00:14, 7.25it/s] [Step 5] Reference Enhancement: 15%|█▍ | 18/122 [00:03<00:14, 7.29it/s] [Step 5] Reference Enhancement: 16%|█▌ | 19/122 [00:03<00:14, 7.31it/s] [Step 5] Reference Enhancement: 16%|█▋ | 20/122 [00:03<00:13, 7.34it/s] [Step 5] Reference Enhancement: 17%|█▋ | 21/122 [00:03<00:13, 7.34it/s] [Step 5] Reference Enhancement: 18%|█▊ | 22/122 [00:04<00:13, 7.27it/s] [Step 5] Reference Enhancement: 19%|█▉ | 23/122 [00:04<00:13, 7.29it/s] [Step 5] Reference Enhancement: 20%|█▉ | 24/122 [00:04<00:13, 7.28it/s] [Step 5] Reference Enhancement: 20%|██ | 25/122 [00:04<00:13, 7.29it/s] [Step 5] Reference Enhancement: 21%|██▏ | 26/122 [00:04<00:13, 7.28it/s] [Step 5] Reference Enhancement: 22%|██▏ | 27/122 [00:04<00:13, 7.26it/s] [Step 5] Reference Enhancement: 23%|██▎ | 28/122 [00:04<00:13, 7.23it/s] [Step 5] Reference Enhancement: 24%|██▍ | 29/122 [00:04<00:12, 7.26it/s] [Step 5] Reference Enhancement: 25%|██▍ | 30/122 [00:05<00:12, 7.23it/s] [Step 5] Reference Enhancement: 25%|██▌ | 31/122 [00:05<00:12, 7.26it/s] [Step 5] Reference Enhancement: 26%|██▌ | 32/122 [00:05<00:12, 7.28it/s] [Step 5] Reference Enhancement: 27%|██▋ | 33/122 [00:05<00:12, 7.27it/s] [Step 5] Reference Enhancement: 28%|██▊ | 34/122 [00:05<00:12, 7.25it/s] [Step 5] Reference Enhancement: 29%|██▊ | 35/122 [00:05<00:11, 7.28it/s] [Step 5] Reference Enhancement: 30%|██▉ | 36/122 [00:05<00:11, 7.28it/s] [Step 5] Reference Enhancement: 30%|███ | 37/122 [00:06<00:11, 7.28it/s] [Step 5] Reference Enhancement: 31%|███ | 38/122 [00:06<00:11, 7.29it/s] [Step 5] Reference Enhancement: 32%|███▏ | 39/122 [00:06<00:11, 7.28it/s] [Step 5] Reference Enhancement: 33%|███▎ | 40/122 [00:06<00:11, 7.31it/s] [Step 5] Reference Enhancement: 34%|███▎ | 41/122 [00:06<00:11, 7.30it/s] [Step 5] Reference Enhancement: 34%|███▍ | 42/122 [00:06<00:10, 7.30it/s] [Step 5] Reference Enhancement: 35%|███▌ | 43/122 [00:06<00:10, 7.31it/s] [Step 5] Reference Enhancement: 36%|███▌ | 44/122 [00:07<00:10, 7.22it/s] [Step 5] Reference Enhancement: 37%|███▋ | 45/122 [00:07<00:10, 7.26it/s] [Step 5] Reference Enhancement: 38%|███▊ | 46/122 [00:07<00:10, 7.29it/s] [Step 5] Reference Enhancement: 39%|███▊ | 47/122 [00:07<00:10, 7.32it/s] [Step 5] Reference Enhancement: 39%|███▉ | 48/122 [00:07<00:10, 7.31it/s] [Step 5] Reference Enhancement: 40%|████ | 49/122 [00:07<00:10, 7.27it/s] [Step 5] Reference Enhancement: 41%|████ | 50/122 [00:07<00:09, 7.30it/s] [Step 5] Reference Enhancement: 42%|████▏ | 51/122 [00:07<00:09, 7.27it/s] [Step 5] Reference Enhancement: 43%|████▎ | 52/122 [00:08<00:09, 7.29it/s] [Step 5] Reference Enhancement: 43%|████▎ | 53/122 [00:08<00:09, 7.32it/s] [Step 5] Reference Enhancement: 44%|████▍ | 54/122 [00:08<00:09, 7.33it/s] [Step 5] Reference Enhancement: 45%|████▌ | 55/122 [00:08<00:09, 7.34it/s] [Step 5] Reference Enhancement: 46%|████▌ | 56/122 [00:08<00:09, 7.31it/s] [Step 5] Reference Enhancement: 47%|████▋ | 57/122 [00:08<00:08, 7.33it/s] [Step 5] Reference Enhancement: 48%|████▊ | 58/122 [00:08<00:08, 7.28it/s] [Step 5] Reference Enhancement: 48%|████▊ | 59/122 [00:09<00:08, 7.29it/s] [Step 5] Reference Enhancement: 49%|████▉ | 60/122 [00:09<00:08, 7.32it/s] [Step 5] Reference Enhancement: 50%|█████ | 61/122 [00:09<00:08, 7.34it/s] [Step 5] Reference Enhancement: 51%|█████ | 62/122 [00:09<00:08, 7.30it/s] [Step 5] Reference Enhancement: 52%|█████▏ | 63/122 [00:09<00:08, 7.28it/s] [Step 5] Reference Enhancement: 52%|█████▏ | 64/122 [00:09<00:07, 7.25it/s] [Step 5] Reference Enhancement: 53%|█████▎ | 65/122 [00:09<00:07, 7.26it/s] [Step 5] Reference Enhancement: 54%|█████▍ | 66/122 [00:10<00:07, 7.25it/s] [Step 5] Reference Enhancement: 55%|█████▍ | 67/122 [00:10<00:07, 7.24it/s] [Step 5] Reference Enhancement: 56%|█████▌ | 68/122 [00:10<00:07, 7.29it/s] [Step 5] Reference Enhancement: 57%|█████▋ | 69/122 [00:10<00:07, 7.30it/s] [Step 5] Reference Enhancement: 57%|█████▋ | 70/122 [00:10<00:07, 7.32it/s] [Step 5] Reference Enhancement: 58%|█████▊ | 71/122 [00:10<00:06, 7.35it/s] [Step 5] Reference Enhancement: 59%|█████▉ | 72/122 [00:10<00:06, 7.36it/s] [Step 5] Reference Enhancement: 60%|█████▉ | 73/122 [00:11<00:06, 7.31it/s] [Step 5] Reference Enhancement: 61%|██████ | 74/122 [00:11<00:06, 7.34it/s] [Step 5] Reference Enhancement: 61%|██████▏ | 75/122 [00:11<00:06, 7.35it/s] [Step 5] Reference Enhancement: 62%|██████▏ | 76/122 [00:11<00:06, 7.33it/s] [Step 5] Reference Enhancement: 63%|██████▎ | 77/122 [00:11<00:06, 7.35it/s] [Step 5] Reference Enhancement: 64%|██████▍ | 78/122 [00:11<00:05, 7.35it/s] [Step 5] Reference Enhancement: 65%|██████▍ | 79/122 [00:11<00:05, 7.35it/s] [Step 5] Reference Enhancement: 66%|██████▌ | 80/122 [00:11<00:05, 7.36it/s] [Step 5] Reference Enhancement: 66%|██████▋ | 81/122 [00:12<00:05, 7.34it/s] [Step 5] Reference Enhancement: 67%|██████▋ | 82/122 [00:12<00:05, 7.33it/s] [Step 5] Reference Enhancement: 68%|██████▊ | 83/122 [00:12<00:05, 7.35it/s] [Step 5] Reference Enhancement: 69%|██████▉ | 84/122 [00:12<00:05, 7.32it/s] [Step 5] Reference Enhancement: 70%|██████▉ | 85/122 [00:12<00:05, 7.34it/s] [Step 5] Reference Enhancement: 70%|███████ | 86/122 [00:12<00:04, 7.35it/s] [Step 5] Reference Enhancement: 71%|███████▏ | 87/122 [00:12<00:04, 7.33it/s] [Step 5] Reference Enhancement: 72%|███████▏ | 88/122 [00:13<00:04, 7.29it/s] [Step 5] Reference Enhancement: 73%|███████▎ | 89/122 [00:13<00:04, 7.27it/s] [Step 5] Reference Enhancement: 74%|███████▍ | 90/122 [00:13<00:04, 7.30it/s] [Step 5] Reference Enhancement: 75%|███████▍ | 91/122 [00:13<00:04, 7.33it/s] [Step 5] Reference Enhancement: 75%|███████▌ | 92/122 [00:13<00:04, 7.33it/s] [Step 5] Reference Enhancement: 76%|███████▌ | 93/122 [00:13<00:03, 7.30it/s] [Step 5] Reference Enhancement: 77%|███████▋ | 94/122 [00:13<00:03, 7.28it/s] [Step 5] Reference Enhancement: 78%|███████▊ | 95/122 [00:14<00:03, 7.28it/s] [Step 5] Reference Enhancement: 79%|███████▊ | 96/122 [00:14<00:03, 7.31it/s] [Step 5] Reference Enhancement: 80%|███████▉ | 97/122 [00:14<00:03, 7.30it/s] [Step 5] Reference Enhancement: 80%|████████ | 98/122 [00:14<00:03, 7.31it/s] [Step 5] Reference Enhancement: 81%|████████ | 99/122 [00:14<00:03, 7.35it/s] [Step 5] Reference Enhancement: 82%|████████▏ | 100/122 [00:14<00:02, 7.36it/s] [Step 5] Reference Enhancement: 83%|████████▎ | 101/122 [00:14<00:02, 7.36it/s] [Step 5] Reference Enhancement: 84%|████████▎ | 102/122 [00:14<00:02, 7.34it/s] [Step 5] Reference Enhancement: 84%|████████▍ | 103/122 [00:15<00:02, 7.32it/s] [Step 5] Reference Enhancement: 85%|████████▌ | 104/122 [00:15<00:02, 7.35it/s] [Step 5] Reference Enhancement: 86%|████████▌ | 105/122 [00:15<00:02, 7.34it/s] [Step 5] Reference Enhancement: 87%|████████▋ | 106/122 [00:15<00:02, 7.34it/s] [Step 5] Reference Enhancement: 88%|████████▊ | 107/122 [00:15<00:02, 7.34it/s] [Step 5] Reference Enhancement: 89%|████████▊ | 108/122 [00:15<00:01, 7.35it/s] [Step 5] Reference Enhancement: 89%|████████▉ | 109/122 [00:15<00:01, 7.36it/s] [Step 5] Reference Enhancement: 90%|█████████ | 110/122 [00:16<00:01, 7.33it/s] [Step 5] Reference Enhancement: 91%|█████████ | 111/122 [00:16<00:01, 7.32it/s] [Step 5] Reference Enhancement: 92%|█████████▏| 112/122 [00:16<00:01, 7.32it/s] [Step 5] Reference Enhancement: 93%|█████████▎| 113/122 [00:16<00:01, 7.30it/s] [Step 5] Reference Enhancement: 93%|█████████▎| 114/122 [00:16<00:01, 7.32it/s] [Step 5] Reference Enhancement: 94%|█████████▍| 115/122 [00:16<00:00, 7.34it/s] [Step 5] Reference Enhancement: 95%|█████████▌| 116/122 [00:16<00:00, 7.35it/s] [Step 5] Reference Enhancement: 96%|█████████▌| 117/122 [00:17<00:00, 7.33it/s] [Step 5] Reference Enhancement: 97%|█████████▋| 118/122 [00:17<00:00, 7.32it/s] [Step 5] Reference Enhancement: 98%|█████████▊| 119/122 [00:17<00:00, 7.32it/s] [Step 5] Reference Enhancement: 98%|█████████▊| 120/122 [00:17<00:00, 7.35it/s] [Step 5] Reference Enhancement: 99%|█████████▉| 121/122 [00:17<00:00, 7.37it/s] [Step 5] Reference Enhancement: 100%|██████████| 122/122 [00:17<00:00, 7.37it/s] [Step 5] Reference Enhancement: 100%|██████████| 122/122 [00:17<00:00, 6.90it/s] result_file: /tmp/video-retalkingujnr4vqo/result.mp4 [Step 6] Lip Synthesis:: 0%| | 0/8 [00:00<?, ?it/s] landmark Det:: 0%| | 0/122 [00:00<?, ?it/s][A landmark Det:: 1%| | 1/122 [00:00<00:22, 5.31it/s][A landmark Det:: 2%|▏ | 2/122 [00:00<00:40, 2.95it/s][A landmark Det:: 7%|▋ | 8/122 [00:00<00:08, 14.24it/s][A landmark Det:: 11%|█▏ | 14/122 [00:00<00:04, 23.87it/s][A landmark Det:: 17%|█▋ | 21/122 [00:00<00:02, 34.02it/s][A landmark Det:: 23%|██▎ | 28/122 [00:01<00:02, 42.10it/s][A landmark Det:: 29%|██▊ | 35/122 [00:01<00:01, 48.42it/s][A landmark Det:: 34%|███▍ | 42/122 [00:01<00:01, 52.97it/s][A landmark Det:: 40%|████ | 49/122 [00:01<00:01, 56.53it/s][A landmark Det:: 46%|████▌ | 56/122 [00:01<00:01, 58.91it/s][A landmark Det:: 52%|█████▏ | 63/122 [00:01<00:00, 60.57it/s][A landmark Det:: 57%|█████▋ | 70/122 [00:01<00:00, 61.33it/s][A landmark Det:: 63%|██████▎ | 77/122 [00:01<00:00, 60.40it/s][A landmark Det:: 69%|██████▉ | 84/122 [00:01<00:00, 61.36it/s][A landmark Det:: 75%|███████▍ | 91/122 [00:02<00:00, 62.10it/s][A landmark Det:: 80%|████████ | 98/122 [00:02<00:00, 63.06it/s][A landmark Det:: 86%|████████▌ | 105/122 [00:02<00:00, 63.92it/s][A landmark Det:: 92%|█████████▏| 112/122 [00:02<00:00, 64.31it/s][A landmark Det:: 98%|█████████▊| 119/122 [00:02<00:00, 64.76it/s][A landmark Det:: 100%|██████████| 122/122 [00:02<00:00, 48.36it/s] 0%| | 0/122 [00:00<?, ?it/s][A 100%|██████████| 122/122 [00:00<00:00, 18786.44it/s] 0%| | 0/122 [00:00<?, ?it/s][A 52%|█████▏ | 64/122 [00:00<00:00, 636.69it/s][A 100%|██████████| 122/122 [00:00<00:00, 633.06it/s] FaceDet:: 0%| | 0/31 [00:00<?, ?it/s][A FaceDet:: 3%|▎ | 1/31 [00:00<00:18, 1.60it/s][A FaceDet:: 6%|▋ | 2/31 [00:00<00:09, 3.03it/s][A FaceDet:: 10%|▉ | 3/31 [00:00<00:06, 4.24it/s][A FaceDet:: 13%|█▎ | 4/31 [00:00<00:05, 5.30it/s][A FaceDet:: 16%|█▌ | 5/31 [00:01<00:04, 6.08it/s][A FaceDet:: 19%|█▉ | 6/31 [00:01<00:03, 6.73it/s][A FaceDet:: 23%|██▎ | 7/31 [00:01<00:03, 7.29it/s][A FaceDet:: 26%|██▌ | 8/31 [00:01<00:02, 7.69it/s][A FaceDet:: 32%|███▏ | 10/31 [00:01<00:02, 8.34it/s][A FaceDet:: 35%|███▌ | 11/31 [00:01<00:02, 8.33it/s][A FaceDet:: 39%|███▊ | 12/31 [00:01<00:02, 8.20it/s][A FaceDet:: 42%|████▏ | 13/31 [00:02<00:02, 8.20it/s][A FaceDet:: 45%|████▌ | 14/31 [00:02<00:02, 8.12it/s][A FaceDet:: 48%|████▊ | 15/31 [00:02<00:01, 8.27it/s][A FaceDet:: 52%|█████▏ | 16/31 [00:02<00:01, 8.11it/s][A FaceDet:: 55%|█████▍ | 17/31 [00:02<00:01, 8.17it/s][A FaceDet:: 58%|█████▊ | 18/31 [00:02<00:01, 8.49it/s][A FaceDet:: 61%|██████▏ | 19/31 [00:02<00:01, 8.45it/s][A FaceDet:: 65%|██████▍ | 20/31 [00:02<00:01, 8.43it/s][A FaceDet:: 68%|██████▊ | 21/31 [00:02<00:01, 8.67it/s][A FaceDet:: 71%|███████ | 22/31 [00:03<00:01, 8.74it/s][A FaceDet:: 74%|███████▍ | 23/31 [00:03<00:00, 8.82it/s][A FaceDet:: 77%|███████▋ | 24/31 [00:03<00:00, 8.90it/s][A FaceDet:: 81%|████████ | 25/31 [00:03<00:00, 8.92it/s][A FaceDet:: 87%|████████▋ | 27/31 [00:03<00:00, 9.49it/s][A FaceDet:: 90%|█████████ | 28/31 [00:03<00:00, 9.55it/s][A FaceDet:: 94%|█████████▎| 29/31 [00:03<00:00, 9.42it/s][A FaceDet:: 97%|█████████▋| 30/31 [00:03<00:00, 9.28it/s][A FaceDet:: 100%|██████████| 31/31 [00:04<00:00, 2.89it/s][A FaceDet:: 100%|██████████| 31/31 [00:04<00:00, 6.31it/s] [Step 6] Lip Synthesis:: 12%|█▎ | 1/8 [00:21<02:30, 21.51s/it] [Step 6] Lip Synthesis:: 25%|██▌ | 2/8 [00:26<01:12, 12.08s/it] [Step 6] Lip Synthesis:: 38%|███▊ | 3/8 [00:32<00:45, 9.03s/it] [Step 6] Lip Synthesis:: 50%|█████ | 4/8 [00:38<00:31, 7.78s/it] [Step 6] Lip Synthesis:: 62%|██████▎ | 5/8 [00:43<00:21, 7.01s/it] [Step 6] Lip Synthesis:: 75%|███████▌ | 6/8 [00:49<00:12, 6.49s/it] [Step 6] Lip Synthesis:: 88%|████████▊ | 7/8 [00:54<00:06, 6.13s/it] [Step 6] Lip Synthesis:: 100%|██████████| 8/8 [01:00<00:00, 6.10s/it] [Step 6] Lip Synthesis:: 100%|██████████| 8/8 [01:00<00:00, 7.60s/it] output_file: /tmp/output.mp4
Version Details
- Version ID
1e959997f54af5daa345d6c063f9abeef361029e730d4f57e876e2d5b31b5e9b- Version Created
- December 1, 2023