charlesmccarthy/liveportrait 🖼️✓ → 🖼️

▶️ 115 runs 📅 Jul 2024 ⚙️ Cog 0.9.12 🔗 GitHub ⚖️ License
face-reenactment image-to-video talking-head

About

Example Output

Output

Performance Metrics

78.02s Prediction Time
148.65s Total Time
All Input Parameters
{
  "image": "https://replicate.delivery/pbxt/LECJXqGPZTRxGRMIVch48jG9anWqAKhtSB4uLQaPkpoQdGdK/genimage555824704_1.png",
  "video": "https://replicate.delivery/pbxt/LECJYHhKXvgg4bnRi9AMUWlm5fW54Cvuqoe1uh5GPOm52RLm/d6.mp4"
}
Input Parameters
image (required) Type: string
Portrait image
video (required) Type: string
Driving Video
flag_do_crop Type: booleanDefault: true
Whether to crop the source portrait to the face-cropping space
flag_pasteback Type: booleanDefault: true
Whether to paste-back/stitch the animated face cropping from the face-cropping space to the original image space
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
[18:18:04] Load source image from                   live_portrait_pipeline.py:46
/tmp/tmplhezve4mgenimage555824704_1.png
/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/nn/modules/conv.py:456: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
return F.conv2d(input, weight, bias, self.stride,
[18:18:07] Load from video file (mp4 mov avi        live_portrait_pipeline.py:72
etc...): /tmp/tmpkpj8_5uhd6.mp4
/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/nn/modules/conv.py:605: UserWarning: Plan failed with a cudnnException: CUDNN_BACKEND_EXECUTION_PLAN_DESCRIPTOR: cudnnFinalize Descriptor Failed cudnn_status: CUDNN_STATUS_NOT_SUPPORTED (Triggered internally at ../aten/src/ATen/native/cudnn/Conv_v8.cpp:919.)
return F.conv3d(
Animating... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:52
Concatenating result... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:02
Dump to /tmp/tmplhezve4mgenimage555824704_1--tmpkpj8_5uhd6_concat.mp4
Dump to /tmp/tmplhezve4mgenimage555824704_1--tmpkpj8_5uhd6.mp4
Version Details
Version ID
4d56e26a1ce02936e7c047b6ce9dc1a60fb7d97cc5a6a1f116a6a73af474cebf
Version Created
July 7, 2024
Run on Replicate →