stefan-st/face-diffuser 🖼️❓🔢 → 🖼️

▶️ 205 runs 📅 Sep 2023 ⚙️ Cog 0.7.2 🔗 GitHub ⚖️ License
audio-to-video lipsync

About

A facial animation generator model based on diffusion

Example Output

Output

Performance Metrics

45.74s Prediction Time
211.35s Total Time
All Input Parameters
{
  "audio": "https://replicate.delivery/pbxt/JXs3LNjev75vVGuPjondvJUMErh5wrmxPRHScDsBMP79H5yD/test1.wav",
  "subject": "F1",
  "skip_timesteps": 450,
  "conditioning_subject": "F3"
}
Input Parameters
audio (required) Type: string
Speech audio file
subject Default: F1
Subject to animate
skip_timesteps Type: integerDefault: 450Range: 0 - 500
Number of diffussion timesteps to skip. 0 will give the best result but takes the longest to compute.
conditioning_subject Default: F3
Conditioning Subject
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
0%|          | 0/50 [00:00<?, ?it/s]
  2%|▏         | 1/50 [00:00<00:07,  6.20it/s]
  6%|▌         | 3/50 [00:00<00:04, 11.10it/s]
 10%|█         | 5/50 [00:00<00:03, 13.37it/s]
 14%|█▍        | 7/50 [00:00<00:02, 15.42it/s]
 18%|█▊        | 9/50 [00:00<00:02, 16.64it/s]
 22%|██▏       | 11/50 [00:00<00:02, 17.62it/s]
 26%|██▌       | 13/50 [00:00<00:02, 18.25it/s]
 30%|███       | 15/50 [00:00<00:01, 18.63it/s]
 34%|███▍      | 17/50 [00:01<00:01, 18.93it/s]
 38%|███▊      | 19/50 [00:01<00:01, 19.16it/s]
 42%|████▏     | 21/50 [00:01<00:01, 19.29it/s]
 46%|████▌     | 23/50 [00:01<00:01, 19.38it/s]
 50%|█████     | 25/50 [00:01<00:01, 19.25it/s]
 54%|█████▍    | 27/50 [00:01<00:01, 19.24it/s]
 58%|█████▊    | 29/50 [00:01<00:01, 19.31it/s]
 62%|██████▏   | 31/50 [00:01<00:00, 19.40it/s]
 66%|██████▌   | 33/50 [00:01<00:00, 19.42it/s]
 70%|███████   | 35/50 [00:01<00:00, 19.42it/s]
 74%|███████▍  | 37/50 [00:02<00:00, 19.39it/s]
 78%|███████▊  | 39/50 [00:02<00:00, 19.48it/s]
 82%|████████▏ | 41/50 [00:02<00:00, 19.46it/s]
 86%|████████▌ | 43/50 [00:02<00:00, 19.46it/s]
 90%|█████████ | 45/50 [00:02<00:00, 19.42it/s]
 94%|█████████▍| 47/50 [00:02<00:00, 19.18it/s]
 98%|█████████▊| 49/50 [00:02<00:00, 19.25it/s]
100%|██████████| 50/50 [00:02<00:00, 18.34it/s]
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'
ffmpeg version 4.2.7-0ubuntu0.1 Copyright (c) 2000-2022 the FFmpeg developers
built with gcc 9 (Ubuntu 9.4.0-1ubuntu1~20.04.1)
configuration: --prefix=/usr --extra-version=0ubuntu0.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-avresample --disable-filter=resample --enable-avisynth --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --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-librsvg --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-nvenc --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil      56. 31.100 / 56. 31.100
libavcodec     58. 54.100 / 58. 54.100
libavformat    58. 29.100 / 58. 29.100
libavdevice    58.  8.100 / 58.  8.100
libavfilter     7. 57.100 /  7. 57.100
libavresample   4.  0.  0 /  4.  0.  0
libswscale      5.  5.100 /  5.  5.100
libswresample   3.  5.100 /  3.  5.100
libpostproc    55.  5.100 / 55.  5.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'renders/tmp/tmp.mp4':
Metadata:
major_brand     : isom
minor_version   : 512
compatible_brands: isomiso2mp41
encoder         : Lavf58.45.100
Duration: 00:00:06.00, start: 0.000000, bitrate: 578 kb/s
Stream #0:0(und): Video: mpeg4 (Simple Profile) (mp4v / 0x7634706D), yuv420p, 480x480 [SAR 1:1 DAR 1:1], 576 kb/s, 25 fps, 25 tbr, 12800 tbn, 25 tbc (default)
Metadata:
handler_name    : VideoHandler
Guessed Channel Layout for Input Stream #1.0 : mono
Input #1, wav, from '/tmp/tmp4ghql28otest1.wav':
Metadata:
encoder         : Lavf59.16.100
Duration: 00:00:06.06, bitrate: 705 kb/s
Stream #1:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 44100 Hz, mono, s16, 705 kb/s
Stream mapping:
Stream #0:0 (mpeg4) -> concat:in0:v0
Stream #1:0 (pcm_s16le) -> concat:in0:a0
concat:out:a0 -> Stream #0:0 (aac)
concat:out:v0 -> Stream #0:1 (libx264)
Press [q] to stop, [?] for help
[libx264 @ 0x5c9b06f35380] using SAR=1/1
[libx264 @ 0x5c9b06f35380] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2
[libx264 @ 0x5c9b06f35380] profile High, level 3.0
[libx264 @ 0x5c9b06f35380] 264 - core 155 r2917 0a84d98 - H.264/MPEG-4 AVC codec - Copyleft 2003-2018 - 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=12 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 'renders/result.mp4':
Metadata:
major_brand     : isom
minor_version   : 512
compatible_brands: isomiso2mp41
encoder         : Lavf58.29.100
Stream #0:0: Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, mono, fltp, 69 kb/s (default)
Metadata:
encoder         : Lavc58.54.100 aac
Stream #0:1: Video: h264 (libx264) (avc1 / 0x31637661), yuv420p, 480x480 [SAR 1:1 DAR 1:1], q=-1--1, 25 fps, 12800 tbn, 25 tbc (default)
Metadata:
encoder         : Lavc58.54.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: -1
frame=  150 fps=0.0 q=-1.0 Lsize=     170kB time=00:00:06.06 bitrate= 230.3kbits/s speed=10.2x
video:112kB audio:52kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 3.784237%
[aac @ 0x5c9b06f37180] Qavg: 538.646
[libx264 @ 0x5c9b06f35380] frame I:1     Avg QP:18.12  size:  4304
[libx264 @ 0x5c9b06f35380] frame P:52    Avg QP:23.18  size:  1410
[libx264 @ 0x5c9b06f35380] frame B:97    Avg QP:23.82  size:   375
[libx264 @ 0x5c9b06f35380] consecutive B-frames:  9.3% 10.7%  8.0% 72.0%
[libx264 @ 0x5c9b06f35380] mb I  I16..4: 10.2% 82.0%  7.8%
[libx264 @ 0x5c9b06f35380] mb P  I16..4:  0.9%  3.1%  0.2%  P16..4: 22.8%  7.1%  2.2%  0.0%  0.0%    skip:63.7%
[libx264 @ 0x5c9b06f35380] mb B  I16..4:  0.3%  0.6%  0.0%  B16..8: 20.1%  1.7%  0.1%  direct: 0.1%  skip:77.1%  L0:50.3% L1:46.9% BI: 2.8%
[libx264 @ 0x5c9b06f35380] 8x8 transform intra:75.1% inter:69.7%
[libx264 @ 0x5c9b06f35380] coded y,uvDC,uvAC intra: 30.9% 3.8% 0.4% inter: 2.6% 0.4% 0.0%
[libx264 @ 0x5c9b06f35380] i16 v,h,dc,p: 40% 22% 18% 20%
[libx264 @ 0x5c9b06f35380] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 24% 20% 44%  2%  2%  2%  2%  2%  1%
[libx264 @ 0x5c9b06f35380] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 29% 25% 27%  3%  3%  3%  5%  2%  3%
[libx264 @ 0x5c9b06f35380] i8c dc,h,v,p: 82%  9%  8%  0%
[libx264 @ 0x5c9b06f35380] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x5c9b06f35380] ref P L0: 63.0%  7.2% 20.4%  9.4%
[libx264 @ 0x5c9b06f35380] ref B L0: 81.2% 14.5%  4.4%
[libx264 @ 0x5c9b06f35380] ref B L1: 93.4%  6.6%
[libx264 @ 0x5c9b06f35380] kb/s:151.96
Version Details
Version ID
fc7610e0e9baa1050ea47a08d55c2be9ab990c9a887c7597b3d0d71ebe0f6058
Version Created
September 17, 2023
Run on Replicate →