sebi75/video-inference 🔢📝🖼️❓ → 🖼️
About
Implementation of the latest Stable Video Diffusion model in Cog for inference on Replicate
Example Output
Output
Performance Metrics
109.93s
Prediction Time
109.97s
Total Time
All Input Parameters
{
"seed": 23,
"fps_id": 6,
"version": "svd_xt",
"cond_aug": 0.02,
"decoding_t": 7,
"num_frames": 25,
"input_image": "https://replicate.delivery/pbxt/JwbPVJ24A2Igxw2g0NJ1b3LM4XTXj4GvEYpuUOU958IMlt4o/test_image.png",
"sizing_strategy": "crop_to_16_9",
"motion_bucket_id": 127
}
Input Parameters
- seed
- Seed for random number generation
- fps_id
- Frames per second
- version
- Version of the model
- cond_aug
- Condition augmentation factor
- decoding_t
- Number of frames decoded at a time, affects VRAM usage
- num_frames
- Number of frames to process
- input_image (required)
- Path to the input image file or folder with image files
- sizing_strategy
- Decide how to resize the input image
- motion_bucket_id
- Motion bucket ID for video processing
Output Schema
Output
Example Execution Logs
Resizing and cropping to 16:9 Scale factor w: 1.0, Scale factor h: 1.0 New width: 1024, New height: 576 Left: 0.0, Top: 0.0, Right: 1024.0, Bottom: 576.0 Resized and cropped dimensions: 1024x576 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, image2, from 'tmp//frame_%06d.png': Duration: 00:00:01.00, start: 0.000000, bitrate: N/A Stream #0:0: Video: png, rgb24(pc), 1024x576, 25 fps, 25 tbr, 25 tbn, 25 tbc Stream mapping: Stream #0:0 -> #0:0 (png (native) -> h264 (libx264)) Press [q] to stop, [?] for help [libx264 @ 0x5567ab734840] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 [libx264 @ 0x5567ab734840] profile High, level 3.1, 4:2:0, 8-bit [libx264 @ 0x5567ab734840] 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=18 lookahead_threads=3 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=7 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/000009.mp4': Metadata: encoder : Lavf58.76.100 Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 1024x576, q=2-31, 7 fps, 14336 tbn Metadata: encoder : Lavc58.134.100 libx264 Side data: cpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A frame= 1 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x frame= 25 fps=0.0 q=-1.0 Lsize= 299kB time=00:00:03.14 bitrate= 779.5kbits/s speed=13.7x video:298kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.380226% [libx264 @ 0x5567ab734840] frame I:1 Avg QP:18.60 size: 31563 [libx264 @ 0x5567ab734840] frame P:6 Avg QP:18.87 size: 18696 [libx264 @ 0x5567ab734840] frame B:18 Avg QP:19.83 size: 8925 [libx264 @ 0x5567ab734840] consecutive B-frames: 4.0% 0.0% 0.0% 96.0% [libx264 @ 0x5567ab734840] mb I I16..4: 28.3% 48.5% 23.2% [libx264 @ 0x5567ab734840] mb P I16..4: 12.8% 9.4% 3.0% P16..4: 40.8% 19.3% 10.0% 0.0% 0.0% skip: 4.6% [libx264 @ 0x5567ab734840] mb B I16..4: 1.2% 0.3% 0.1% B16..8: 41.2% 9.4% 1.7% direct:11.8% skip:34.3% L0:47.9% L1:38.9% BI:13.1% [libx264 @ 0x5567ab734840] 8x8 transform intra:39.4% inter:76.6% [libx264 @ 0x5567ab734840] coded y,uvDC,uvAC intra: 36.8% 80.7% 61.7% inter: 23.2% 41.8% 18.4% [libx264 @ 0x5567ab734840] i16 v,h,dc,p: 3% 25% 2% 71% [libx264 @ 0x5567ab734840] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 8% 47% 19% 1% 5% 3% 9% 1% 5% [libx264 @ 0x5567ab734840] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 12% 57% 12% 2% 3% 2% 6% 2% 4% [libx264 @ 0x5567ab734840] i8c dc,h,v,p: 44% 35% 14% 7% [libx264 @ 0x5567ab734840] Weighted P-Frames: Y:0.0% UV:0.0% [libx264 @ 0x5567ab734840] ref P L0: 73.8% 4.3% 16.1% 5.8% [libx264 @ 0x5567ab734840] ref B L0: 92.6% 6.4% 1.0% [libx264 @ 0x5567ab734840] ref B L1: 97.1% 2.9% [libx264 @ 0x5567ab734840] kb/s:681.84
Version Details
- Version ID
2ea1dd84082842e2035fbc36be290e7df2c1227a487e9c9076be3e6fe0b02e91- Version Created
- November 26, 2023