chenxwh/depth-any-video 🔢✓🖼️ → 🖼️

▶️ 227 runs 📅 Oct 2024 ⚙️ Cog 0.9.23 🔗 GitHub 📄 Paper ⚖️ License
depth-estimation video-to-video

About

Depth Any Video with Scalable Synthetic Data

Example Output

Output

Performance Metrics

85.38s Prediction Time
153.46s Total Time
All Input Parameters
{
  "num_frames": 32,
  "denoise_steps": 3,
  "input_is_video": true,
  "max_resolution": 960,
  "decode_chunk_size": 16,
  "num_interp_frames": 16,
  "num_overlap_frames": 6,
  "input_image_or_video": "https://replicate.delivery/pbxt/LpLOdVyL2oJaitdfNvGpMvJI0cqfmrGKrclST5AmbNUN4LaV/wooly_mammoth.mp4"
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
num_frames Type: integerDefault: 32
Number of frames to infer per forward. This should be an even number
denoise_steps Type: integerDefault: 3
Number of denoising steps, 1-3 steps work fine
input_is_video Type: booleanDefault: true
Specify if the input is a video.
max_resolution Type: integerDefault: 1024
Maximum resolution for inference
decode_chunk_size Type: integerDefault: 16
Number of frames to decode per forward
num_interp_frames Type: integerDefault: 16
Number of frames for inpaint inference
num_overlap_frames Type: integerDefault: 6
Number of frames to overlap between windows
input_image_or_video (required) Type: string
Input image or video
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Using seed: 60885
  0%|          | 0/15 [00:00<?, ?it/s]
  7%|▋         | 1/15 [00:02<00:30,  2.20s/it]
 13%|█▎        | 2/15 [00:04<00:28,  2.19s/it]
 20%|██        | 3/15 [00:06<00:26,  2.19s/it]
 27%|██▋       | 4/15 [00:08<00:24,  2.19s/it]
 33%|███▎      | 5/15 [00:10<00:21,  2.19s/it]
 40%|████      | 6/15 [00:13<00:19,  2.19s/it]
 47%|████▋     | 7/15 [00:15<00:17,  2.19s/it]
 53%|█████▎    | 8/15 [00:17<00:15,  2.19s/it]
 60%|██████    | 9/15 [00:19<00:13,  2.19s/it]
 67%|██████▋   | 10/15 [00:21<00:10,  2.19s/it]
 73%|███████▎  | 11/15 [00:24<00:08,  2.19s/it]
 80%|████████  | 12/15 [00:26<00:06,  2.20s/it]
 87%|████████▋ | 13/15 [00:28<00:04,  2.20s/it]
 93%|█████████▎| 14/15 [00:30<00:02,  2.20s/it]
100%|██████████| 15/15 [00:32<00:00,  2.19s/it]
100%|██████████| 15/15 [00:32<00:00,  2.19s/it]
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/tmp/%06d.png':
Duration: 00:00:06.13, start: 0.000000, bitrate: N/A
Stream #0:0: Video: png, rgb24(pc), 960x512, 30 fps, 30 tbr, 30 tbn, 30 tbc
Stream mapping:
Stream #0:0 -> #0:0 (png (native) -> h264 (libx264))
Press [q] to stop, [?] for help
[libx264 @ 0x581d7458cfc0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 AVX512
[libx264 @ 0x581d7458cfc0] profile High 4:4:4 Predictive, level 3.1, 4:4:4, 8-bit
[libx264 @ 0x581d7458cfc0] 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=4 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=2 keyint=250 keyint_min=25 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=abr mbtree=1 bitrate=5626 ratetol=1.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00
Output #0, mp4, to '/tmp/out.mp4':
Metadata:
encoder         : Lavf58.76.100
Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv444p(tv, progressive), 960x512, q=2-31, 5626 kb/s, 30 fps, 15360 tbn
Metadata:
encoder         : Lavc58.134.100 libx264
Side data:
cpb: bitrate max/min/avg: 0/0/5626000 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=  102 fps=0.0 q=11.0 size=    1024kB time=00:00:01.33 bitrate=6291.4kbits/s speed=2.59x
frame=  179 fps=176 q=11.0 size=    2816kB time=00:00:03.90 bitrate=5915.0kbits/s speed=3.83x
frame=  184 fps=134 q=-1.0 Lsize=    4457kB time=00:00:06.03 bitrate=6051.6kbits/s speed=4.38x
video:4454kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.068497%
[libx264 @ 0x581d7458cfc0] frame I:1     Avg QP: 7.93  size: 22042
[libx264 @ 0x581d7458cfc0] frame P:46    Avg QP: 4.74  size: 46927
[libx264 @ 0x581d7458cfc0] frame B:137   Avg QP: 6.83  size: 17368
[libx264 @ 0x581d7458cfc0] consecutive B-frames:  0.5%  0.0%  1.6% 97.8%
[libx264 @ 0x581d7458cfc0] mb I  I16..4: 50.5% 30.8% 18.7%
[libx264 @ 0x581d7458cfc0] mb P  I16..4:  2.7%  5.6%  4.3%  P16..4: 13.5% 17.8% 19.2%  0.0%  0.0%    skip:36.7%
[libx264 @ 0x581d7458cfc0] mb B  I16..4:  0.4%  0.6%  0.3%  B16..8: 20.5% 11.4%  7.0%  direct: 8.7%  skip:51.2%  L0:43.1% L1:42.5% BI:14.3%
[libx264 @ 0x581d7458cfc0] final ratefactor: 5.11
[libx264 @ 0x581d7458cfc0] 8x8 transform intra:43.0% inter:32.8%
[libx264 @ 0x581d7458cfc0] coded y,u,v intra: 65.5% 31.4% 55.3% inter: 25.0% 10.1% 16.5%
[libx264 @ 0x581d7458cfc0] i16 v,h,dc,p: 49% 22% 15% 15%
[libx264 @ 0x581d7458cfc0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 14% 33% 42%  1%  2%  2%  2%  1%  3%
[libx264 @ 0x581d7458cfc0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 19% 46% 16%  2%  2%  2%  4%  2%  6%
[libx264 @ 0x581d7458cfc0] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x581d7458cfc0] ref P L0: 55.4%  4.3% 22.3% 18.0%
[libx264 @ 0x581d7458cfc0] ref B L0: 76.6% 18.5%  4.9%
[libx264 @ 0x581d7458cfc0] ref B L1: 90.3%  9.7%
[libx264 @ 0x581d7458cfc0] kb/s:5947.97
Version Details
Version ID
4055afe2aba32ab3d2dbccc4fabb240bf643db7fe56f33c1f9535d948b219495
Version Created
October 20, 2024
Run on Replicate →