cudanexus/makeittalk 🖼️ → 🖼️

▶️ 8.1K runs 📅 Mar 2023 ⚙️ Cog 0.6.1
audio-to-video face-animation image-animation lip-sync

About

Make any Image Talk. The image must have a human face and should be of dimensions strictly 256x256.

Example Output

Output

Performance Metrics

16.74s Prediction Time
16.82s Total Time
All Input Parameters
{
  "audio": "https://replicate.delivery/pbxt/IX9TfC9r2AynlMcx83YA1skJ10yuozM6n8egzxCnKcaWqI1P/tmp.wav",
  "image": "https://replicate.delivery/pbxt/IX9TfcEGOZaZ5tIXgdg8uxdwDI9ywoX1IKCrruU7LSU24bIp/taylor.jpg"
}
Input Parameters
audio (required) Type: string
Audio input
image (required) Type: string
Grayscale input image
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
/tmp/tmprp0g9geptmp.wav
/tmp/tmpo7a2ujzdtaylor.jpg
Audio-----> tmprp0g9geptmp.wav
Parameters===== tmprp0g9geptmp.wav 16000 [95 75 80 ... 25 30 35]
Loaded the voice encoder model on cuda in 0.02 seconds.
Processing audio file tmprp0g9geptmp.wav
0 out of 0 are in this portion
Loaded the voice encoder model on cuda in 0.08 seconds.
source shape: torch.Size([1, 320, 80]) torch.Size([1, 256]) torch.Size([1, 256]) torch.Size([1, 320, 257])
converted shape: torch.Size([1, 320, 80])torch.Size([1, 640])
Run on device: cuda
Loading Data random_val
EVAL num videos: 1
G: Running on cuda, total num params = 3.00M
======== LOAD PRETRAINED FACE ID MODEL examples/ckpt/ckpt_speaker_branch.pth =========
======== LOAD PRETRAINED FACE ID MODEL examples/ckpt/ckpt_content_branch.pth =========
====================================
48uYS3bHIA8
YAZuSHvwVC0
0yaLdVk_UyQ
E_kmpT-EfOg
fQR31F7L3ww
JPMZAOGGHh8
W6uRNCJmdtI
2KL8PfQPmBg
p575B7k07a8
iUoAe2gXKE4
HH-iOC056aQ
S8fiWqrZEew
ROWN2ssXek8
irx71tYyI-Q
me6cdZCM2FY
OkqHtWOFliM
OfPKHc6w2vw
1lh57VnuaKE
_ldiVrXgZKc
H1Xnb_rtgqY
45hn7-LXDX8
bs7ZWVqAGCU
UElg0R7fmlk
bCs5SoifsiY
1Lx_ZqrK1bM
RrnL6Pcjjbw
sRbWv2R2hxE
wJmdE0G4sEg
hE-4e1vEiT8
XXbxe3fCQqg
02HOKnTjBlQ
wAAMEC1OsRc
7Sk--XzX8b0
I5Lm0Qce5kg
qLxfiUMYgQg
_VpqWkdcaqM
ljIkW4uVVQY
5m5iPZNJS6c
J-NPsvtQ8lE
gOrQyrbptGo
43BiUVlNy58
swLghyvhoqA
X3FCAoFnmdA
2NiCRAmwoc4
KVUf0J2LAaA
YtZS9hH1j24
5fZj9Fzi5K0
wbWKG26ebMw
QgNlXur0wrs
qek_5m1MRik
rmFsUV5ICKk
bEdGv1wixF4
ljh5PB6Utsc
izudwWTXuUk
B08yOvYMF7Y
UEmI4r5G-5Y
Scujgl9GbHA
sxCbrYjBsGA
qvQC0w3y_Fo
bXpavyiCu10
iWeklsXc0H8
H00oAfd_GsM
Z7WRt--g-h4
29k8RtSUjE0
E0zgrhQ0QDw
9KhvSxKE6Mc
qLNvRwMkhik
====================================
OpenCV: FFMPEG: tag 0x47504a4d/'MJPG' is not supported with codec id 7 and format 'mp4 / MP4 (MPEG-4 Part 14)'
OpenCV: FFMPEG: fallback to use tag 0x7634706d/'mp4v'
examples/tmprp0g9geptmp.wav
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 'examples/tmp.mp4':
Metadata:
major_brand     : isom
minor_version   : 512
compatible_brands: isomiso2mp41
encoder         : Lavf59.27.100
Duration: 00:00:04.59, start: 0.000000, bitrate: 5588 kb/s
Stream #0:0(und): Video: mjpeg (Baseline) (mp4v / 0x7634706D), yuvj420p(pc, bt470bg/unknown/unknown), 400x400, 5585 kb/s, 62.50 fps, 62.50 tbr, 10k tbn, 10k tbc (default)
Metadata:
handler_name    : VideoHandler
vendor_id       : [0][0][0][0]
Guessed Channel Layout for Input Stream #1.0 : mono
Input #1, wav, from 'examples/tmprp0g9geptmp.wav':
Duration: 00:00:04.88, bitrate: 256 kb/s
Stream #1:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s
Stream mapping:
Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264))
Stream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native))
Press [q] to stop, [?] for help
[libx264 @ 0x563dd5b04040] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2
[libx264 @ 0x563dd5b04040] profile High, level 3.0, 4:2:0, 8-bit
[libx264 @ 0x563dd5b04040] 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=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 'examples/tmprp0g9geptmp_av.mp4':
Metadata:
major_brand     : isom
minor_version   : 512
compatible_brands: isomiso2mp41
encoder         : Lavf58.76.100
Stream #0:0(und): Video: h264 (avc1 / 0x31637661), yuvj420p(pc, bt470bg/unknown/unknown, progressive), 400x400, q=2-31, 62.50 fps, 16k tbn (default)
Metadata:
handler_name    : VideoHandler
vendor_id       : [0][0][0][0]
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: Audio: aac (LC) (mp4a / 0x6134706D), 16000 Hz, mono, fltp, 69 kb/s
Metadata:
encoder         : Lavc58.134.100 aac
frame=    1 fps=0.0 q=0.0 size=       0kB time=00:00:00.00 bitrate=N/A speed=   0x
frame=  256 fps=0.0 q=32.0 size=       0kB time=00:00:03.15 bitrate=   0.1kbits/s speed= 6.2x
frame=  287 fps=0.0 q=-1.0 Lsize=     236kB time=00:00:04.54 bitrate= 426.4kbits/s speed=6.84x
video:192kB audio:39kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 2.409990%
[libx264 @ 0x563dd5b04040] frame I:2     Avg QP:10.18  size:  4790
[libx264 @ 0x563dd5b04040] frame P:80    Avg QP:24.58  size:  1299
[libx264 @ 0x563dd5b04040] frame B:205   Avg QP:30.72  size:   401
[libx264 @ 0x563dd5b04040] consecutive B-frames:  3.1%  4.2%  2.1% 90.6%
[libx264 @ 0x563dd5b04040] mb I  I16..4: 87.4%  0.5% 12.1%
[libx264 @ 0x563dd5b04040] mb P  I16..4:  0.8%  1.5%  0.1%  P16..4:  6.3%  4.2%  2.3%  0.0%  0.0%    skip:84.8%
[libx264 @ 0x563dd5b04040] mb B  I16..4:  0.2%  0.2%  0.0%  B16..8:  9.2%  2.1%  0.9%  direct: 0.3%  skip:87.2%  L0:51.4% L1:46.9% BI: 1.7%
[libx264 @ 0x563dd5b04040] 8x8 transform intra:34.6% inter:6.5%
[libx264 @ 0x563dd5b04040] coded y,uvDC,uvAC intra: 3.5% 17.4% 11.5% inter: 1.4% 3.7% 3.4%
[libx264 @ 0x563dd5b04040] i16 v,h,dc,p: 81% 15%  4%  0%
[libx264 @ 0x563dd5b04040] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu:  6%  9% 84%  1%  0%  0%  0%  0%  0%
[libx264 @ 0x563dd5b04040] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 20% 25% 31%  4%  2%  4%  5%  3%  5%
[libx264 @ 0x563dd5b04040] i8c dc,h,v,p: 55% 23% 22%  0%
[libx264 @ 0x563dd5b04040] Weighted P-Frames: Y:7.5% UV:0.0%
[libx264 @ 0x563dd5b04040] ref P L0: 45.0% 16.4% 18.5% 18.4%  1.6%
[libx264 @ 0x563dd5b04040] ref B L0: 77.2% 17.2%  5.6%
[libx264 @ 0x563dd5b04040] ref B L1: 91.5%  8.5%
[libx264 @ 0x563dd5b04040] kb/s:340.95
[aac @ 0x563dd5b05680] Qavg: 135.552
Run on device cuda
OpenCV: FFMPEG: tag 0x67706a6d/'mjpg' is not supported with codec id 7 and format 'mp4 / MP4 (MPEG-4 Part 14)'
OpenCV: FFMPEG: fallback to use tag 0x7634706d/'mp4v'
Time - only video: 8.78536581993103
Time - ffmpeg add audio: 10.202400922775269
finish image2image gen
examples/test_pred_fls_tmprp0g9geptmp_audio_embed.mp4
Version Details
Version ID
e63aa3e0830945d12340aba53c63e27288b5705eec0c8ea0db5b144c5d64dbf6
Version Created
March 25, 2023
Run on Replicate →