cjwbw/dreamtalk ❓🖼️✓🔢 → 🖼️
About
RESEARCH/NON-COMMERCIAL USE ONLY: diffusion-based audio-driven expressive talking head generation
Example Output
Output
Performance Metrics
8.05s
Prediction Time
66.31s
Total Time
All Input Parameters
{
"pose": "data/pose/RichardShelby_front_neutral_level1_001.mat",
"audio": "https://replicate.delivery/pbxt/KBf8dw9d7uahoVoe0LXhzlV2X3hC6VVAza4HpXgiTK3NgOqy/example_reference.mp3",
"image": "https://replicate.delivery/pbxt/KBf8e4NvKBhVPly3fDK3vJoSdO8NDYUmukrtJAs3glm9mXaX/uncut_src_img.jpg",
"crop_image": true,
"style_clip": "data/style_clip/3DMM/M030_front_neutral_level1_001.mat",
"max_gen_len": 1000,
"num_inference_steps": 10
}
Input Parameters
- pose
- Input pose, specifies the head pose and should be a .mat file.
- audio (required)
- Input audio file. The input audio file extensions should be wav, mp3, m4a, and mp4 (video with sound) should all be compatible.
- image (required)
- Input image. This specifies the input portrait. The resolution should be larger than 256x256 and will be cropped to 256x256.
- crop_image
- Enable cropping the input image. If your portrait is already cropped to 256x256, set this to False.
- style_clip
- Input style_clip_mat, optional. This specifies the reference speaking style.
- max_gen_len
- The maximum length (seconds) limitation for generating videos.
- num_inference_steps
- Number of denoising steps
Output Schema
Output
Example Execution Logs
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, mp3, from '/tmp/tmp8b3ii7t7example_reference.mp3': Metadata: encoder : Lavf58.29.100 Duration: 00:00:14.59, start: 0.023021, bitrate: 64 kb/s Stream #0:0: Audio: mp3, 48000 Hz, mono, fltp, 64 kb/s Stream mapping: Stream #0:0 -> #0:0 (mp3 (mp3float) -> pcm_s16le (native)) Press [q] to stop, [?] for help -async is forwarded to lavfi similarly to -af aresample=async=1:min_hard_comp=0.100000:first_pts=0. Output #0, wav, to 'cog_temp/tmp_input_16K.wav': Metadata: ISFT : Lavf58.76.100 Stream #0:0: Audio: pcm_s16le ([1][0][0][0] / 0x0001), 16000 Hz, mono, s16, 256 kb/s Metadata: encoder : Lavc58.134.100 pcm_s16le size= 0kB time=00:00:00.00 bitrate=N/A speed=N/A size= 455kB time=00:00:14.56 bitrate= 256.1kbits/s speed=1.06e+03x video:0kB audio:455kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.016733% data/style_clip/3DMM/M030_front_neutral_level1_001.mat /root/.pyenv/versions/3.11.7/lib/python3.11/site-packages/torch/nn/functional.py:4236: UserWarning: Default grid_sample and affine_grid behavior has changed to align_corners=False since 1.3.0. Please specify align_corners=True if the old behavior is desired. See the documentation of grid_sample for details. warnings.warn( 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 'cog_temp/no_watermark.mp4': Metadata: major_brand : isom minor_version : 512 compatible_brands: isomiso2avc1mp41 encoder : Lavf58.76.100 Duration: 00:00:14.57, start: 0.000000, bitrate: 305 kb/s Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 256x256, 228 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), 16000 Hz, mono, fltp, 71 kb/s (default) Metadata: handler_name : SoundHandler vendor_id : [0][0][0][0] Stream mapping: Stream #0:0 -> #0:0 (h264 (native) -> h264 (libx264)) Stream #0:1 -> #0:1 (aac (native) -> aac (native)) Press [q] to stop, [?] for help [png @ 0x5623cc248280] Application has requested 97 threads. Using a thread count greater than 16 is not recommended. [libx264 @ 0x5623cbe047c0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 [libx264 @ 0x5623cbe047c0] profile High, level 1.3, 4:2:0, 8-bit [libx264 @ 0x5623cbe047c0] 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=8 lookahead_threads=1 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/out.mp4': Metadata: major_brand : isom minor_version : 512 compatible_brands: isomiso2avc1mp41 encoder : Lavf58.76.100 Stream #0:0(und): Video: h264 (avc1 / 0x31637661), yuv420p(progressive), 256x256, q=2-31, 25 fps, 12800 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(und): Audio: aac (LC) (mp4a / 0x6134706D), 16000 Hz, mono, fltp, 69 kb/s (default) Metadata: handler_name : SoundHandler vendor_id : [0][0][0][0] encoder : Lavc58.134.100 aac frame= 1 fps=0.0 q=0.0 size= 0kB time=00:00:00.44 bitrate= 0.9kbits/s speed=71.8x [Parsed_movie_0 @ 0x5623cbe45bc0] EOF timestamp not reliable frame= 364 fps=0.0 q=-1.0 Lsize= 498kB time=00:00:14.52 bitrate= 280.9kbits/s speed=42.7x video:358kB audio:130kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 2.144712% [libx264 @ 0x5623cbe047c0] frame I:2 Avg QP:21.47 size: 11592 [libx264 @ 0x5623cbe047c0] frame P:96 Avg QP:23.56 size: 2931 [libx264 @ 0x5623cbe047c0] frame B:266 Avg QP:27.96 size: 230 [libx264 @ 0x5623cbe047c0] consecutive B-frames: 0.8% 4.9% 0.8% 93.4% [libx264 @ 0x5623cbe047c0] mb I I16..4: 4.1% 61.3% 34.6% [libx264 @ 0x5623cbe047c0] mb P I16..4: 0.0% 0.2% 0.1% P16..4: 37.6% 29.6% 19.1% 0.0% 0.0% skip:13.4% [libx264 @ 0x5623cbe047c0] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 35.0% 3.2% 0.5% direct: 0.7% skip:60.6% L0:41.7% L1:49.2% BI: 9.1% [libx264 @ 0x5623cbe047c0] 8x8 transform intra:62.4% inter:60.9% [libx264 @ 0x5623cbe047c0] coded y,uvDC,uvAC intra: 92.6% 97.4% 79.8% inter: 13.7% 7.7% 0.1% [libx264 @ 0x5623cbe047c0] i16 v,h,dc,p: 33% 8% 8% 50% [libx264 @ 0x5623cbe047c0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 27% 15% 8% 5% 8% 14% 6% 9% 9% [libx264 @ 0x5623cbe047c0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 25% 14% 7% 6% 10% 15% 7% 9% 8% [libx264 @ 0x5623cbe047c0] i8c dc,h,v,p: 33% 21% 33% 14% [libx264 @ 0x5623cbe047c0] Weighted P-Frames: Y:4.2% UV:0.0% [libx264 @ 0x5623cbe047c0] ref P L0: 54.0% 19.8% 17.0% 8.6% 0.5% [libx264 @ 0x5623cbe047c0] ref B L0: 88.3% 8.9% 2.8% [libx264 @ 0x5623cbe047c0] ref B L1: 97.3% 2.7% [libx264 @ 0x5623cbe047c0] kb/s:200.88 [aac @ 0x5623cbe337c0] Qavg: 205.920
Version Details
- Version ID
c52a2bad8c0bdf9645609de071dddb1ddab0b396b8bf7096027819473a85b4ca- Version Created
- January 7, 2024