所以基本上，我正在插入视频然后对其进行放大，使用流帧进行插入（RIFE Cuda）并放大real_esrgan，但是在使用ffmpeg时遇到了问题，我使用它来提取帧：
ffmpeg -i input.mp4 -qscale:v 1 -qmin 1 -qmax 1 -vsync 0 tmp_frames/frame%08d.jpg
然后使用升级器 AI，然后
此命令将放大的帧放回到一个视频
ffmpeg -i out_frames/frame%08d.jpg -i input.mp4 -vsync cfr -map 0:v:0 -map 1:a:0? -c:a copy -c:v libx264 -r 40 -pix_fmt yuv420p output_w_audio.mp4
结果通常较慢且帧数较多。
（Anaconda 日志）提取帧：
built with gcc 10.2.1 (GCC) 20200726
configuration: --disable-static --enable-shared --enable-gpl --enable-version3 --enable-sdl2 --enable-fontconfig --enable-gnutls --enable-iconv --enable-libass --enable-libdav1d --enable-libbluray --enable-libfreetype --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopus --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libsrt --enable-libtheora --enable-libtwolame --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libzimg --enable-lzma --enable-zlib --enable-gmp --enable-libvidstab --enable-libvmaf --enable-libvorbis --enable-libvo-amrwbenc --enable-libmysofa --enable-libspeex --enable-libxvid --enable-libaom --enable-libgsm --enable-librav1e --disable-w32threads --enable-libmfx --enable-ffnvcodec --enable-cuda-llvm --enable-cuvid --enable-d3d11va --enable-nvenc --enable-nvdec --enable-dxva2 --enable-avisynth --enable-libopenmpt --enable-amf
libavutil 56. 51.100 / 56. 51.100
libavcodec 58. 91.100 / 58. 91.100
libavformat 58. 45.100 / 58. 45.100
libavdevice 58. 10.100 / 58. 10.100
libavfilter 7. 85.100 / 7. 85.100
libswscale 5. 7.100 / 5. 7.100
libswresample 3. 7.100 / 3. 7.100
libpostproc 55. 7.100 / 55. 7.100
Input #0, mov,mp4,m4a,3gp,3g2,mj2, from 'input.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf58.76.100
Duration: 00:00:01.73, start: 0.000000, bitrate: 846 kb/s
Stream #0:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 498x280, 838 kb/s, 40 fps, 40 tbr, 10240 tbn, 80 tbc (default)
Metadata:
handler_name : VideoHandler
Stream mapping:
Stream #0:0 -> #0:0 (h264 (native) -> mjpeg (native))
Press [q] to stop, [?] for help
[swscaler @ 0000019a185e9440] deprecated pixel format used, make sure you did set range correctly
Output #0, image2, to 'tmp_frames/frame%08d.jpg':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf58.45.100
Stream #0:0(und): Video: mjpeg, yuvj420p(pc), 498x280, q=1-1, 200 kb/s, 40 fps, 40 tbn, 40 tbc (default)
Metadata:
handler_name : VideoHandler
encoder : Lavc58.91.100 mjpeg
Side data:
cpb: bitrate max/min/avg: 0/0/200000 buffer size: 0 vbv_delay: N/A
frame= 69 fps=0.0 q=1.0 Lsize=N/A time=00:00:01.72 bitrate=N/A speed=6.82x
video:2684kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: unknown
将放大的帧放回原位：
built with gcc 10.2.1 (GCC) 20200726
configuration: --disable-static --enable-shared --enable-gpl --enable-version3 --enable-sdl2 --enable-fontconfig --enable-gnutls --enable-iconv --enable-libass --enable-libdav1d --enable-libbluray --enable-libfreetype --enable-libmp3lame --enable-libopencore-amrnb --enable-libopencore-amrwb --enable-libopenjpeg --enable-libopus --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libsrt --enable-libtheora --enable-libtwolame --enable-libvpx --enable-libwavpack --enable-libwebp --enable-libx264 --enable-libx265 --enable-libxml2 --enable-libzimg --enable-lzma --enable-zlib --enable-gmp --enable-libvidstab --enable-libvmaf --enable-libvorbis --enable-libvo-amrwbenc --enable-libmysofa --enable-libspeex --enable-libxvid --enable-libaom --enable-libgsm --enable-librav1e --disable-w32threads --enable-libmfx --enable-ffnvcodec --enable-cuda-llvm --enable-cuvid --enable-d3d11va --enable-nvenc --enable-nvdec --enable-dxva2 --enable-avisynth --enable-libopenmpt --enable-amf
libavutil 56. 51.100 / 56. 51.100
libavcodec 58. 91.100 / 58. 91.100
libavformat 58. 45.100 / 58. 45.100
libavdevice 58. 10.100 / 58. 10.100
libavfilter 7. 85.100 / 7. 85.100
libswscale 5. 7.100 / 5. 7.100
libswresample 3. 7.100 / 3. 7.100
libpostproc 55. 7.100 / 55. 7.100
Input #0, image2, from 'out_frames/frame%08d.jpg':
Duration: 00:00:02.76, start: 0.000000, bitrate: N/A
Stream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 1992x1120, 25 fps, 25 tbr, 25 tbn, 25 tbc
Input #1, mov,mp4,m4a,3gp,3g2,mj2, from 'input.mp4':
Metadata:
major_brand : isom
minor_version : 512
compatible_brands: isomiso2avc1mp41
encoder : Lavf58.76.100
Duration: 00:00:01.73, start: 0.000000, bitrate: 846 kb/s
Stream #1:0(und): Video: h264 (High) (avc1 / 0x31637661), yuv420p, 498x280, 838 kb/s, 40 fps, 40 tbr, 10240 tbn, 80 tbc (default)
Metadata:
handler_name : VideoHandler
Stream mapping:
Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264))
Press [q] to stop, [?] for help
[swscaler @ 000001899df68740] deprecated pixel format used, make sure you did set range correctly
[libx264 @ 000001899df60b80] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX XOP FMA3 BMI1
[libx264 @ 000001899df60b80] profile High, level 5.0, 4:2:0, 8-bit
[libx264 @ 000001899df60b80] 264 - core 161 - H.264/MPEG-4 AVC codec - Copyleft 2003-2020 - 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=6 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 'output_w_audio.mp4':
Metadata:
encoder : Lavf58.45.100
Stream #0:0: Video: h264 (libx264) (avc1 / 0x31637661), yuv420p, 1992x1120, q=-1--1, 40 fps, 10240 tbn, 40 tbc
Metadata:
encoder : Lavc58.91.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A
[image2 @ 000001899d4055c0] Thread message queue blocking; consider raising the thread_queue_size option (current value: 8)
frame= 111 fps= 14 q=-1.0 Lsize= 1255kB time=00:00:02.70 bitrate=3806.5kbits/s dup=42 drop=0 speed=0.351x
video:1253kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.170050%
[libx264 @ 000001899df60b80] frame I:1 Avg QP:21.58 size: 79333
[libx264 @ 000001899df60b80] frame P:32 Avg QP:22.57 size: 29435
[libx264 @ 000001899df60b80] frame B:78 Avg QP:21.28 size: 3342
[libx264 @ 000001899df60b80] consecutive B-frames: 1.8% 12.6% 2.7% 82.9%
[libx264 @ 000001899df60b80] mb I I16..4: 19.7% 59.1% 21.2%
[libx264 @ 000001899df60b80] mb P I16..4: 7.7% 25.3% 4.3% P16..4: 20.0% 4.3% 2.8% 0.0% 0.0% skip:35.6%
[libx264 @ 000001899df60b80] mb B I16..4: 0.6% 0.7% 0.1% B16..8: 15.2% 0.4% 0.1% direct: 3.2% skip:79.7% L0:43.0% L1:55.8% BI: 1.3%
[libx264 @ 000001899df60b80] 8x8 transform intra:66.1% inter:74.1%
[libx264 @ 000001899df60b80] coded y,uvDC,uvAC intra: 19.4% 30.1% 6.6% inter: 3.0% 8.9% 0.3%
[libx264 @ 000001899df60b80] i16 v,h,dc,p: 30% 37% 7% 26%
[libx264 @ 000001899df60b80] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 28% 19% 40% 2% 2% 2% 3% 1% 2%
[libx264 @ 000001899df60b80] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 25% 24% 20% 7% 5% 4% 5% 5% 4%
[libx264 @ 000001899df60b80] i8c dc,h,v,p: 65% 19% 14% 3%
[libx264 @ 000001899df60b80] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 000001899df60b80] ref P L0: 62.1% 9.5% 19.3% 9.1%
[libx264 @ 000001899df60b80] ref B L0: 77.9% 18.3% 3.8%
[libx264 @ 000001899df60b80] ref B L1: 95.1% 4.9%
[libx264 @ 000001899df60b80] kb/s:3695.54
任何帮助都将不胜感激！！！（图片是 anaconda 日志）提取帧][1[在此处输入图片描述
![提取帧][1[在此处输入图片描述](https://i.stack.imgur.com/VfI2o.png){kind=link}