bytedance/sa2va-26b-video 🖼️📝🔢 → ❓

▶️ 366 runs 📅 Feb 2025 ⚙️ Cog 0.13.8-dev+gdeaa413.d20250220 🔗 GitHub 📄 Paper ⚖️ License
text-guided-segmentation video-grounding video-object-tracking video-segmentation

About

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Example Output

Output

Performance Metrics

24.67s Prediction Time
24.68s Total Time
All Input Parameters
{
  "video": "https://replicate.delivery/pbxt/MXbmbHYHjCwOVD24dhKMSD7ttWW596GHhOLw8IoRFN2kCTR9/sora-otter-5.mp4",
  "instruction": "segment the otter",
  "frame_interval": 4
}
Input Parameters
video (required) Type: string
Input video for segmentation
instruction (required) Type: string
Text instruction for the model
frame_interval Type: integerDefault: 6Range: 1 - 30
Frame interval for processing
Output Schema
response Type: string
Response
masked_video Type: stringFormat: uri
Masked Video
Example Execution Logs
propagate in video:   0%|          | 0/45 [00:00<?, ?it/s]
propagate in video:  18%|█▊        | 8/45 [00:00<00:00, 63.62it/s]
propagate in video:  33%|███▎      | 15/45 [00:00<00:00, 31.85it/s]
propagate in video:  42%|████▏     | 19/45 [00:00<00:00, 28.18it/s]
propagate in video:  51%|█████     | 23/45 [00:00<00:00, 26.10it/s]
propagate in video:  58%|█████▊    | 26/45 [00:00<00:00, 25.08it/s]
propagate in video:  64%|██████▍   | 29/45 [00:01<00:00, 24.34it/s]
propagate in video:  71%|███████   | 32/45 [00:01<00:00, 23.81it/s]
propagate in video:  78%|███████▊  | 35/45 [00:01<00:00, 23.43it/s]
propagate in video:  84%|████████▍ | 38/45 [00:01<00:00, 23.14it/s]
propagate in video:  91%|█████████ | 41/45 [00:01<00:00, 22.93it/s]
propagate in video:  98%|█████████▊| 44/45 [00:01<00:00, 22.78it/s]
propagate in video: 100%|██████████| 45/45 [00:01<00:00, 25.42it/s]
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, avi, from '/tmp/output/temp_masked.avi':
Metadata:
software        : Lavf59.27.100
Duration: 00:00:06.01, start: 0.000000, bitrate: 1706 kb/s
Stream #0:0: Video: mjpeg (Baseline) (MJPG / 0x47504A4D), yuvj420p(pc, bt470bg/unknown/unknown), 1940x1096, 1731 kb/s, 7.48 fps, 7.48 tbr, 7.48 tbn, 7.48 tbc
Stream mapping:
Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264))
Press [q] to stop, [?] for help
[swscaler @ 0x64be41f58d40] deprecated pixel format used, make sure you did set range correctly
[libx264 @ 0x64be41f20f80] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512
[libx264 @ 0x64be41f20f80] profile High, level 4.2, 4:2:0, 8-bit
[libx264 @ 0x64be41f20f80] 264 - core 163 r3060 5db6aa6 - H.264/MPEG-4 AVC codec - Copyleft 2003-2021 - http://www.videolan.org/x264.html - options: cabac=1 ref=2 deblock=1:0:0 analyse=0x3:0x113 me=hex subme=6 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=1 keyint=250 keyint_min=7 scenecut=40 intra_refresh=0 rc_lookahead=30 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/output/masked_video.mp4':
Metadata:
software        : Lavf59.27.100
encoder         : Lavf58.76.100
Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, bt470bg/unknown/unknown, progressive), 1940x1096, q=2-31, 7.48 fps, 14964 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=   45 fps=0.0 q=0.0 size=       0kB time=00:00:00.00 bitrate=N/A speed=   0x
frame=   45 fps=0.0 q=-1.0 Lsize=     178kB time=00:00:05.61 bitrate= 260.2kbits/s speed=8.61x
video:177kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.739327%
[libx264 @ 0x64be41f20f80] frame I:1     Avg QP: 6.97  size:  5474
[libx264 @ 0x64be41f20f80] frame P:18    Avg QP:16.42  size:  4613
[libx264 @ 0x64be41f20f80] frame B:26    Avg QP:18.41  size:  3540
[libx264 @ 0x64be41f20f80] consecutive B-frames: 13.3% 13.3% 46.7% 26.7%
[libx264 @ 0x64be41f20f80] mb I  I16..4: 87.6% 10.4%  2.0%
[libx264 @ 0x64be41f20f80] mb P  I16..4:  0.4%  2.1%  1.4%  P16..4:  1.7%  0.5%  0.2%  0.0%  0.0%    skip:93.9%
[libx264 @ 0x64be41f20f80] mb B  I16..4:  0.4%  0.0%  0.2%  B16..8:  2.5%  1.3%  0.4%  direct: 0.1%  skip:95.1%  L0:52.1% L1:44.6% BI: 3.3%
[libx264 @ 0x64be41f20f80] 8x8 transform intra:26.0% inter:2.1%
[libx264 @ 0x64be41f20f80] coded y,uvDC,uvAC intra: 8.3% 0.0% 0.0% inter: 0.4% 0.0% 0.0%
[libx264 @ 0x64be41f20f80] i16 v,h,dc,p: 92%  6%  2%  0%
[libx264 @ 0x64be41f20f80] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 37% 14% 48%  0%  0%  0%  0%  0%  0%
[libx264 @ 0x64be41f20f80] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 21% 23% 40%  3%  2%  2%  4%  1%  4%
[libx264 @ 0x64be41f20f80] i8c dc,h,v,p: 100%  0%  0%  0%
[libx264 @ 0x64be41f20f80] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x64be41f20f80] ref P L0: 43.9% 56.1%
[libx264 @ 0x64be41f20f80] ref B L0: 87.9% 12.1%
[libx264 @ 0x64be41f20f80] ref B L1: 98.4%  1.6%
[libx264 @ 0x64be41f20f80] kb/s:240.16
Version Details
Version ID
b5f31abc431a2348551fb0f60845572ea61ff3d1d4d55cf2bd59209290680681
Version Created
February 22, 2025
Run on Replicate →