translated prompts ['Star and light, space and stardust.by android jones, psychedelic, alien geometry, digital art, neon', 'Star and light, space and stardust.by android jones, psychedelic, alien geometry, digital art, neon'] using audio file /tmp/tmpvqj8t_u0Capo-In-The-Fields.wav hop length 1378 audio length 666709 audio sr22050 length of audio intensities 484 num frames per prompt 484 Seed set to 13 embedding prompts prompt 0 shape torch.Size([1, 77, 768]) len smoothed_audio_intensities 484 len interpolated_prompts 484 interp prompts 0 shape torch.Size([1, 77, 768]) start_codes 0 shape torch.Size([1, 4, 64, 48]) data_batch torch.Size([24, 77, 768]) start_code_batchtorch.Size([24, 4, 64, 48]) sigmas tensor([14.6090, 10.7477, 8.0787, 6.2059, 4.8573, 3.8654, 3.1229, 2.5581, 2.1152, 1.7641, 1.4802, 1.2456, 1.0481, 0.8783, 0.7297, 0.5962, 0.4736, 0.3552, 0.2322, 0.0313, 0.0000], device='cuda:0') 0%| | 0/20 [00:00 #0:0 (png (native) -> h264 (libx264)) Stream #1:0 -> #0:1 (pcm_s16le (native) -> aac (native)) Press [q] to stop, [?] for help [image2 @ 0x626975839a00] Thread message queue blocking; consider raising the thread_queue_size option (current value: 8) [libx264 @ 0x62697588ac40] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512 [libx264 @ 0x62697588ac40] profile High, level 2.1, 4:2:0, 8-bit [libx264 @ 0x62697588ac40] 264 - core 163 r3060 5db6aa6 - H.264/MPEG-4 AVC codec - Copyleft 2003-2021 - http://www.videolan.org/x264.html - options: cabac=1 ref=5 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=8 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=2 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=16 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=3 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=16 scenecut=40 intra_refresh=0 rc_lookahead=50 rc=crf mbtree=1 crf=20.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00 Output #0, mp4, to '/tmp/z_interpollation.mp4': Metadata: encoder : Lavf58.76.100 Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 384x512, q=2-31, 16 fps, 16384 tbn 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: 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= 121 fps=0.0 q=24.0 size= 2048kB time=00:00:03.00 bitrate=5592.4kbits/s speed=5.66x frame= 197 fps=190 q=24.0 size= 5376kB time=00:00:07.75 bitrate=5682.6kbits/s speed=7.46x frame= 271 fps=175 q=24.0 size= 8448kB time=00:00:12.37 bitrate=5592.4kbits/s speed=7.98x frame= 348 fps=169 q=24.0 size= 11776kB time=00:00:17.18 bitrate=5612.7kbits/s speed=8.37x frame= 434 fps=170 q=24.0 size= 15360kB time=00:00:22.56 bitrate=5576.9kbits/s speed=8.82x [mp4 @ 0x626975889d40] Starting second pass: moving the moov atom to the beginning of the file frame= 484 fps=146 q=-1.0 Lsize= 20600kB time=00:00:30.23 bitrate=5582.1kbits/s speed=9.14x video:20105kB audio:476kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.093760% [libx264 @ 0x62697588ac40] frame I:24 Avg QP:22.34 size: 80897 [libx264 @ 0x62697588ac40] frame P:129 Avg QP:25.42 size: 46296 [libx264 @ 0x62697588ac40] frame B:331 Avg QP:26.57 size: 38287 [libx264 @ 0x62697588ac40] consecutive B-frames: 6.0% 4.1% 13.0% 76.9% [libx264 @ 0x62697588ac40] mb I I16..4: 0.0% 48.1% 51.9% [libx264 @ 0x62697588ac40] mb P I16..4: 0.1% 13.8% 9.2% P16..4: 22.3% 30.7% 23.9% 0.0% 0.0% skip: 0.1% [libx264 @ 0x62697588ac40] mb B I16..4: 0.0% 8.0% 6.1% B16..8: 21.5% 30.4% 18.8% direct:13.9% skip: 1.2% L0:48.9% L1:26.0% BI:25.1% [libx264 @ 0x62697588ac40] 8x8 transform intra:55.5% inter:44.3% [libx264 @ 0x62697588ac40] direct mvs spatial:96.7% temporal:3.3% [libx264 @ 0x62697588ac40] coded y,uvDC,uvAC intra: 99.3% 100.0% 100.0% inter: 88.5% 96.9% 81.9% [libx264 @ 0x62697588ac40] i16 v,h,dc,p: 2% 61% 2% 35% [libx264 @ 0x62697588ac40] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 7% 16% 10% 9% 9% 8% 12% 10% 17% [libx264 @ 0x62697588ac40] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 7% 10% 8% 10% 14% 11% 14% 10% 14% [libx264 @ 0x62697588ac40] i8c dc,h,v,p: 54% 18% 7% 21% [libx264 @ 0x62697588ac40] Weighted P-Frames: Y:40.3% UV:34.9% [libx264 @ 0x62697588ac40] ref P L0: 24.9% 7.4% 11.1% 26.0% 23.2% 7.0% 0.3% [libx264 @ 0x62697588ac40] ref B L0: 52.4% 23.8% 15.1% 8.7% [libx264 @ 0x62697588ac40] ref B L1: 90.3% 9.7% [libx264 @ 0x62697588ac40] kb/s:5444.41 [aac @ 0x62697588e0c0] Qavg: 214.235 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 '/tmp/z_interpollation.mp4': Metadata: major_brand : isom minor_version : 512 compatible_brands: isomiso2avc1mp41 encoder : Lavf58.76.100 Duration: 00:00:30.25, start: 0.000000, bitrate: 5578 kb/s Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 384x512, 5444 kb/s, 16 fps, 16 tbr, 16384 tbn, 32 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, 129 kb/s (default) Metadata: handler_name : SoundHandler vendor_id : [0][0][0][0] Multiple -filter, -af or -vf options specified for stream 0, only the last option '-filter:v format=yuv420p' will be used. 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 [libx264 @ 0x615716b52380] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512 [libx264 @ 0x615716b52380] profile High, level 2.1, 4:2:0, 8-bit [libx264 @ 0x615716b52380] 264 - core 163 r3060 5db6aa6 - H.264/MPEG-4 AVC codec - Copyleft 2003-2021 - http://www.videolan.org/x264.html - options: cabac=1 ref=5 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=8 psy=1 psy_rd=1.00:0.00 mixed_ref=1 me_range=16 chroma_me=1 trellis=2 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=1 chroma_qp_offset=-2 threads=16 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=3 weightb=1 open_gop=0 weightp=2 keyint=250 keyint_min=16 scenecut=40 intra_refresh=0 rc_lookahead=50 rc=crf mbtree=1 crf=20.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00 Output #0, mp4, to '/tmp/z_interpollation_60fps.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), 384x512, q=2-31, 16 fps, 16384 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), 44100 Hz, stereo, fltp, 128 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=00:00:00.88 bitrate= 0.4kbits/s speed=53.3x frame= 122 fps=0.0 q=24.0 size= 2048kB time=00:00:08.47 bitrate=1979.6kbits/s speed=16.4x frame= 209 fps=205 q=24.0 size= 5632kB time=00:00:13.90 bitrate=3317.2kbits/s speed=13.6x frame= 299 fps=195 q=21.0 size= 9472kB time=00:00:19.52 bitrate=3973.5kbits/s speed=12.8x frame= 388 fps=191 q=24.0 size= 13056kB time=00:00:25.10 bitrate=4261.0kbits/s speed=12.4x frame= 484 fps=190 q=24.0 size= 16896kB time=00:00:30.18 bitrate=4585.3kbits/s speed=11.9x [mp4 @ 0x615716b65d40] Starting second pass: moving the moov atom to the beginning of the file frame= 484 fps=168 q=-1.0 Lsize= 19899kB time=00:00:30.23 bitrate=5391.9kbits/s speed=10.5x video:19403kB audio:476kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.097030% [libx264 @ 0x615716b52380] frame I:24 Avg QP:22.27 size: 80313 [libx264 @ 0x615716b52380] frame P:129 Avg QP:25.34 size: 44795 [libx264 @ 0x615716b52380] frame B:331 Avg QP:26.52 size: 36743 [libx264 @ 0x615716b52380] consecutive B-frames: 6.0% 4.1% 13.0% 76.9% [libx264 @ 0x615716b52380] mb I I16..4: 0.0% 48.1% 51.8% [libx264 @ 0x615716b52380] mb P I16..4: 0.1% 14.1% 9.3% P16..4: 23.4% 29.2% 23.8% 0.0% 0.0% skip: 0.1% [libx264 @ 0x615716b52380] mb B I16..4: 0.1% 7.7% 6.5% B16..8: 22.5% 29.8% 19.3% direct:12.8% skip: 1.5% L0:49.5% L1:27.2% BI:23.3% [libx264 @ 0x615716b52380] 8x8 transform intra:54.4% inter:44.5% [libx264 @ 0x615716b52380] direct mvs spatial:97.9% temporal:2.1% [libx264 @ 0x615716b52380] coded y,uvDC,uvAC intra: 98.9% 100.0% 99.9% inter: 85.9% 96.0% 79.7% [libx264 @ 0x615716b52380] i16 v,h,dc,p: 1% 60% 4% 35% [libx264 @ 0x615716b52380] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 7% 17% 11% 9% 9% 8% 12% 10% 18% [libx264 @ 0x615716b52380] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 8% 11% 9% 10% 13% 11% 13% 10% 15% [libx264 @ 0x615716b52380] i8c dc,h,v,p: 54% 18% 7% 21% [libx264 @ 0x615716b52380] Weighted P-Frames: Y:40.3% UV:36.4% [libx264 @ 0x615716b52380] ref P L0: 24.8% 7.4% 11.0% 26.7% 22.6% 7.1% 0.3% [libx264 @ 0x615716b52380] ref B L0: 52.9% 23.5% 15.0% 8.6% [libx264 @ 0x615716b52380] ref B L1: 90.7% 9.3% [libx264 @ 0x615716b52380] kb/s:5254.37 [aac @ 0x615716b5df00] Qavg: 162.253

Examples

Run time and cost

Readme