Starting prediction... Saved input image to: /src/tmp_path/input_image.png Converted and saved audio to: /src/tmp_path/input_audio.wav Preprocessing image... /root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/functional.py:507: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3549.) return _VF.meshgrid(tensors, **kwargs) # type: ignore[attr-defined] Face detection result: 1 face(s) found Using cropped face image for processing Generating talking face animation... 0%| | 0/125 [00:00 #0:0 (h264 (native) -> h264 (libx264)) Stream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native)) Press [q] to stop, [?] for help [libx264 @ 0x5eb8574eb080] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512 [libx264 @ 0x5eb8574eb080] profile High, level 3.0, 4:2:0, 8-bit [libx264 @ 0x5eb8574eb080] 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=15 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=18.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00 Output #0, mp4, to '/src/res_path/output.mp4': Metadata: major_brand : isom minor_version : 512 compatible_brands: isomiso2avc1mp41 encoder : Lavf58.76.100 Stream #0:0(und): Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 502x504, 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: Audio: aac (LC) (mp4a / 0x6134706D), 44100 Hz, stereo, fltp, 128 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= 221 fps=0.0 q=23.0 size= 512kB time=00:00:06.36 bitrate= 659.3kbits/s speed=12.3x frame= 249 fps=0.0 q=-1.0 Lsize= 1093kB time=00:00:09.93 bitrate= 900.6kbits/s speed=13.5x video:924kB audio:159kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.878750% [libx264 @ 0x5eb8574eb080] frame I:1 Avg QP:15.64 size: 38446 [libx264 @ 0x5eb8574eb080] frame P:66 Avg QP:16.76 size: 10130 [libx264 @ 0x5eb8574eb080] frame B:182 Avg QP:23.10 size: 1310 [libx264 @ 0x5eb8574eb080] consecutive B-frames: 0.4% 5.6% 2.4% 91.6% [libx264 @ 0x5eb8574eb080] mb I I16..4: 5.1% 43.4% 51.6% [libx264 @ 0x5eb8574eb080] mb P I16..4: 0.4% 1.6% 0.7% P16..4: 29.3% 30.3% 20.1% 0.0% 0.0% skip:17.6% [libx264 @ 0x5eb8574eb080] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 31.8% 7.8% 1.4% direct: 1.7% skip:57.3% L0:38.4% L1:41.1% BI:20.4% [libx264 @ 0x5eb8574eb080] 8x8 transform intra:54.4% inter:59.3% [libx264 @ 0x5eb8574eb080] coded y,uvDC,uvAC intra: 75.5% 93.2% 82.1% inter: 15.3% 18.6% 2.6% [libx264 @ 0x5eb8574eb080] i16 v,h,dc,p: 12% 20% 11% 57% [libx264 @ 0x5eb8574eb080] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 17% 21% 20% 5% 8% 7% 9% 5% 7% [libx264 @ 0x5eb8574eb080] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 17% 21% 11% 5% 14% 8% 13% 4% 6% [libx264 @ 0x5eb8574eb080] i8c dc,h,v,p: 44% 28% 15% 12% [libx264 @ 0x5eb8574eb080] Weighted P-Frames: Y:15.2% UV:7.6% [libx264 @ 0x5eb8574eb080] ref P L0: 59.7% 16.4% 17.5% 5.5% 0.9% [libx264 @ 0x5eb8574eb080] ref B L0: 92.7% 5.9% 1.4% [libx264 @ 0x5eb8574eb080] ref B L1: 97.7% 2.3% [libx264 @ 0x5eb8574eb080] kb/s:759.43 [aac @ 0x5eb8574eca00] Qavg: 1651.281 Video generation complete Total prediction time: 151.81 seconds