zedge/live-portrait β“πŸ”’πŸ–ΌοΈ β†’ πŸ–ΌοΈ

▢️ 261.1K runs πŸ“… May 2025 βš™οΈ Cog 0.16.0
image-to-video-with-audio lipsync

About

Example Output

Output

Performance Metrics

14.62s Prediction Time
14.63s Total Time
All Input Parameters
{
  "source_image": "https://replicate.delivery/pbxt/NPsSxK4VWdN8V2bXh1bjet8KcOo1FIlHoIBpGPGc5qBQA86h/Cat03.jpg",
  "driving_input": "https://replicate.delivery/pbxt/NPsSwcwbRVeoKH02wRWWjduFBR9upk7QJmYeU5pgkf7q0WSh/d11.mp4",
  "driving_multiplier": 0.7
}
Input Parameters
preset Default: none
Use a preset template and audio combination. Available: dragostea_din_tei
warm_delay Type: integer
Parameter for warming the model. If set, returns empty dict after specified seconds
source_image (required) Type: string
Source image (must be animal)
driving_audio Type: string
Driving audio to use with template (.pkl). When used with video, it will override original video audio. Not required if using a preset.
driving_input Type: string
Driving video (.mp4) or template (.pkl). Use .pkl for faster processing. Not required if using a preset.
driving_multiplier Type: numberDefault: 1.1
Multiplier for driving motion magnitude
Output Schema

Output

Type: string β€’ Format: uri

Example Execution Logs
πŸš€ Starting inference...
[00:08:00] Load source image from            live_portrait_pipeline_animal.py:68
/tmp/tmpjvh0hikgCat03.jpg
Loading from template: False      live_portrait_pipeline_animal.py:76
Load driving video from:          live_portrait_pipeline_animal.py:84
/tmp/tmptsa0zwt4d11.mp4, FPS is
25
[00:08:01] Start making driving motion       live_portrait_pipeline_animal.py:89
template...
Making driving motion templates... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:01
[00:08:02] Dump motion template to          live_portrait_pipeline_animal.py:105
/tmp/tmptsa0zwt4d11.pkl
Prepared pasteback mask done.    live_portrait_pipeline_animal.py:112
πŸ”„ Processing source image...    live_portrait_pipeline_animal.py:114
πŸ”§ Crop config - scale: 2.3, vy_ratio: -0.2, dsize:    cropper.py:134
512
🎬 Starting animation for 225    live_portrait_pipeline_animal.py:138
frames...
πŸš€Animating... ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 100% 0:00:08
True
None
[00:08:13] Audio is selected from           live_portrait_pipeline_animal.py:190
/tmp/tmptsa0zwt4d11.mp4
Video with audio generated successfully:                 video.py:202
animations/tmpjvh0hikgCat03--tmptsa0zwt4d11_with_audio.m
p4
Replace                          live_portrait_pipeline_animal.py:193
animations/tmpjvh0hikgCat03--tmp
tsa0zwt4d11_with_audio.mp4 with
animations/tmpjvh0hikgCat03--tmp
tsa0zwt4d11.mp4
Animated template:               live_portrait_pipeline_animal.py:215
/tmp/tmptsa0zwt4d11.pkl, you can
specify `-d` argument with this
template path next time to avoid
cropping video, motion making
and protecting privacy.
Animated video:                  live_portrait_pipeline_animal.py:224
animations/tmpjvh0hikgCat03--tmp
tsa0zwt4d11.mp4
πŸŽ‰ Applying shake effect
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 'animations/tmpjvh0hikgCat03--tmptsa0zwt4d11.mp4':
Metadata:
major_brand     : isom
minor_version   : 512
compatible_brands: isomiso2avc1mp41
encoder         : Lavf58.76.100
Duration: 00:00:09.00, start: 0.000000, bitrate: 6429 kb/s
Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 1280x1278, 6294 kb/s, 25 fps, 25 tbr, 12800 tbn, 50 tbc (default)
Metadata:
handler_name    : VideoHandler
vendor_id       : [0][0][0][0]
Stream #0:1(und): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 128 kb/s (default)
Metadata:
handler_name    : Stereo
vendor_id       : [0][0][0][0]
Stream mapping:
Stream #0:0 (h264) -> crop (graph 0)
crop (graph 0) -> Stream #0:0 (libx264)
Stream #0:1 -> #0:1 (aac (native) -> aac (native))
Press [q] to stop, [?] for help
[libx264 @ 0x5e91bd1dc3c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512
[libx264 @ 0x5e91bd1dc3c0] profile High, level 4.0, 4:2:0, 8-bit
[libx264 @ 0x5e91bd1dc3c0] 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=19 lookahead_threads=3 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 '/tmp/outputs/final_animated_with_motion.mp4':
Metadata:
major_brand     : isom
minor_version   : 512
compatible_brands: isomiso2avc1mp41
encoder         : Lavf58.76.100
Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(progressive), 1260x1266, q=2-31, 25 fps, 12800 tbn (default)
Metadata:
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(und): Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 128 kb/s (default)
Metadata:
handler_name    : Stereo
vendor_id       : [0][0][0][0]
encoder         : Lavc58.134.100 aac
frame=    1 fps=0.0 q=0.0 size=       0kB time=00:00:00.53 bitrate=   0.7kbits/s speed=15.7x
frame=   98 fps=0.0 q=28.0 size=     256kB time=00:00:04.43 bitrate= 472.9kbits/s speed=8.28x
frame=  171 fps=165 q=28.0 size=    1280kB time=00:00:07.36 bitrate=1424.6kbits/s speed=7.09x
frame=  225 fps=129 q=-1.0 Lsize=    3246kB time=00:00:08.89 bitrate=2990.4kbits/s speed=5.12x
video:3096kB audio:141kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.269651%
[libx264 @ 0x5e91bd1dc3c0] frame I:1     Avg QP:19.01  size: 97220
[libx264 @ 0x5e91bd1dc3c0] frame P:56    Avg QP:20.90  size: 23166
[libx264 @ 0x5e91bd1dc3c0] frame B:168   Avg QP:25.74  size: 10567
[libx264 @ 0x5e91bd1dc3c0] consecutive B-frames:  0.4%  0.0%  0.0% 99.6%
[libx264 @ 0x5e91bd1dc3c0] mb I  I16..4:  7.1% 87.4%  5.5%
[libx264 @ 0x5e91bd1dc3c0] mb P  I16..4:  0.7%  7.9%  0.8%  P16..4: 28.8%  8.9%  3.4%  0.0%  0.0%    skip:49.5%
[libx264 @ 0x5e91bd1dc3c0] mb B  I16..4:  0.0%  0.7%  0.1%  B16..8: 24.3%  5.3%  1.0%  direct: 2.3%  skip:66.3%  L0:48.4% L1:44.9% BI: 6.7%
[libx264 @ 0x5e91bd1dc3c0] 8x8 transform intra:84.8% inter:79.8%
[libx264 @ 0x5e91bd1dc3c0] coded y,uvDC,uvAC intra: 79.9% 74.0% 17.3% inter: 13.3% 10.0% 0.0%
[libx264 @ 0x5e91bd1dc3c0] i16 v,h,dc,p: 10% 15%  5% 71%
[libx264 @ 0x5e91bd1dc3c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 12% 14% 12%  8% 11% 11% 12%  8% 11%
[libx264 @ 0x5e91bd1dc3c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 13% 13% 10%  6% 18% 15% 13%  6%  6%
[libx264 @ 0x5e91bd1dc3c0] i8c dc,h,v,p: 51% 21% 18% 11%
[libx264 @ 0x5e91bd1dc3c0] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x5e91bd1dc3c0] ref P L0: 43.4%  9.1% 24.5% 23.0%
[libx264 @ 0x5e91bd1dc3c0] ref B L0: 83.3% 12.1%  4.6%
[libx264 @ 0x5e91bd1dc3c0] ref B L1: 95.8%  4.2%
[libx264 @ 0x5e91bd1dc3c0] kb/s:2817.67
[aac @ 0x5e91bd1f9440] Qavg: 186.806
Inference took 14.4242 seconds
Version Details
Version ID
9f8f5880eb2db3778cc689fa00ee6e090fa3d8388ac278b608d4cc526a44c5df
Version Created
September 10, 2025
Run on Replicate β†’