bytedance/sa2va-8b-video 🖼️📝🔢 → ❓
About
Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos

Example Output
Output
{"response":"Sure, [SEG] .<|im_end|>","masked_video":"https://replicate.delivery/xezq/lMZ2O5szFPqoEtMN4BvRXgzbr3WVWA5v6DgFy82uf7u0F2IKA/masked_video.mp4"}
Performance Metrics
8.31s
Prediction Time
8.31s
Total Time
All Input Parameters
{ "video": "https://replicate.delivery/pbxt/MXZ3bC24tLog8jym5fQSydwGEbUKZPyvOZyxADdJFpRlYcLa/sora-woman.mp4", "instruction": "Segment the person wearing sunglasses", "frame_interval": 4 }
Input Parameters
- video (required)
- Input video for segmentation
- instruction (required)
- Text instruction for the model
- frame_interval
- Frame interval for processing
Output Schema
- response
- Response
- masked_video
- Masked Video
Example Execution Logs
propagate in video: 0%| | 0/38 [00:00<?, ?it/s] propagate in video: 21%|██ | 8/38 [00:00<00:00, 75.45it/s] propagate in video: 42%|████▏ | 16/38 [00:00<00:00, 37.77it/s] propagate in video: 55%|█████▌ | 21/38 [00:00<00:00, 33.53it/s] propagate in video: 66%|██████▌ | 25/38 [00:00<00:00, 31.60it/s] propagate in video: 76%|███████▋ | 29/38 [00:00<00:00, 30.30it/s] propagate in video: 87%|████████▋ | 33/38 [00:01<00:00, 29.40it/s] propagate in video: 97%|█████████▋| 37/38 [00:01<00:00, 28.78it/s] propagate in video: 100%|██████████| 38/38 [00:01<00:00, 31.88it/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: 00:00:05.07, start: 0.000000, bitrate: 716 kb/s Stream #0:0: Video: mjpeg (Baseline) (MJPG / 0x47504A4D), yuvj420p(pc, bt470bg/unknown/unknown), 1280x720, 725 kb/s, 7.50 fps, 7.50 tbr, 7.50 tbn, 7.50 tbc Stream mapping: Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264)) Press [q] to stop, [?] for help [swscaler @ 0x57ac6030d1c0] deprecated pixel format used, make sure you did set range correctly [libx264 @ 0x57ac602dbc40] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512 [libx264 @ 0x57ac602dbc40] profile High, level 3.1, 4:2:0, 8-bit [libx264 @ 0x57ac602dbc40] 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), 1280x720, q=2-31, 7.50 fps, 15360 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=N/A frame= 38 fps=0.0 q=-1.0 Lsize= 47kB time=00:00:04.66 bitrate= 82.2kbits/s speed=22.2x video:46kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 2.827075% [libx264 @ 0x57ac602dbc40] frame I:1 Avg QP: 8.87 size: 2147 [libx264 @ 0x57ac602dbc40] frame P:10 Avg QP:21.02 size: 1495 [libx264 @ 0x57ac602dbc40] frame B:27 Avg QP:22.86 size: 1069 [libx264 @ 0x57ac602dbc40] consecutive B-frames: 5.3% 0.0% 0.0% 94.7% [libx264 @ 0x57ac602dbc40] mb I I16..4: 43.5% 54.5% 2.0% [libx264 @ 0x57ac602dbc40] mb P I16..4: 0.4% 0.6% 0.4% P16..4: 1.1% 1.1% 0.3% 0.0% 0.0% skip:96.1% [libx264 @ 0x57ac602dbc40] mb B I16..4: 0.3% 0.0% 0.0% B16..8: 1.5% 1.5% 0.3% direct: 0.1% skip:96.3% L0:48.6% L1:47.7% BI: 3.7% [libx264 @ 0x57ac602dbc40] 8x8 transform intra:48.9% inter:2.3% [libx264 @ 0x57ac602dbc40] coded y,uvDC,uvAC intra: 3.2% 0.0% 0.0% inter: 0.4% 0.0% 0.0% [libx264 @ 0x57ac602dbc40] i16 v,h,dc,p: 92% 2% 5% 0% [libx264 @ 0x57ac602dbc40] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 41% 2% 57% 0% 0% 0% 0% 0% 0% [libx264 @ 0x57ac602dbc40] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 45% 6% 37% 2% 1% 3% 1% 4% 1% [libx264 @ 0x57ac602dbc40] i8c dc,h,v,p: 100% 0% 0% 0% [libx264 @ 0x57ac602dbc40] Weighted P-Frames: Y:0.0% UV:0.0% [libx264 @ 0x57ac602dbc40] ref P L0: 61.6% 38.4% [libx264 @ 0x57ac602dbc40] ref B L0: 84.2% 15.8% [libx264 @ 0x57ac602dbc40] ref B L1: 89.8% 10.2% [libx264 @ 0x57ac602dbc40] kb/s:72.58
Version Details
- Version ID
2081445d08ac557a504b1b7642ba5ad629072b055164b32c75dd7b8b8705dddc
- Version Created
- February 21, 2025