lucataco / depth-anything-video-sbs
POC implementation of Depth-anything to produce a 3D SBS video
- Public
- 199 runs
-
L40S
- GitHub
Prediction
lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455IDsqae64dbcfxyszbs2zx3tshbcuStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- ipd
- 6.34
- video
- encoder
- vits
{ "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSF1kXgU3qDkCwcH24bBK1LeNUu3J7AUtuXSbxqk8K43Y6ZC/wooly-720p.mp4", "encoder": "vits" }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", { input: { ipd: 6.34, video: "https://replicate.delivery/pbxt/KSF1kXgU3qDkCwcH24bBK1LeNUu3J7AUtuXSbxqk8K43Y6ZC/wooly-720p.mp4", encoder: "vits" } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", input={ "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSF1kXgU3qDkCwcH24bBK1LeNUu3J7AUtuXSbxqk8K43Y6ZC/wooly-720p.mp4", "encoder": "vits" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", "input": { "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSF1kXgU3qDkCwcH24bBK1LeNUu3J7AUtuXSbxqk8K43Y6ZC/wooly-720p.mp4", "encoder": "vits" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-23T15:47:57.178495Z", "created_at": "2024-02-23T15:46:12.713850Z", "data_removed": false, "error": null, "id": "sqae64dbcfxyszbs2zx3tshbcu", "input": { "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSF1kXgU3qDkCwcH24bBK1LeNUu3J7AUtuXSbxqk8K43Y6ZC/wooly-720p.mp4", "encoder": "vits" }, "logs": "Processing depth frames /tmp/tmpdznn39ecwooly-720p.mp4\n/root/.pyenv/versions/3.11.8/lib/python3.11/site-packages/transformers/pipelines/base.py:1123: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset\nwarnings.warn(\nffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --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\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nInput #0, image2, from '/tmp/stereo/%d.jpg':\nDuration: 00:00:12.00, start: 0.000000, bitrate: N/A\nStream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 2560x720 [SAR 1:1 DAR 32:9], 25 fps, 25 tbr, 25 tbn, 25 tbc\nStream mapping:\nStream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264))\nPress [q] to stop, [?] for help\n[swscaler @ 0x55f449d96b80] deprecated pixel format used, make sure you did set range correctly\n[libx264 @ 0x55f449bb6800] using SAR=1/1\n[libx264 @ 0x55f449bb6800] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2\n[libx264 @ 0x55f449bb6800] profile High, level 4.0, 4:2:0, 8-bit\n[libx264 @ 0x55f449bb6800] 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=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=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\nOutput #0, mp4, to '/tmp/output.mp4':\nMetadata:\nencoder : Lavf58.76.100\nStream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, bt470bg/unknown/unknown, progressive), 2560x720 [SAR 1:1 DAR 32:9], q=2-31, 30 fps, 15360 tbn\nMetadata:\nencoder : Lavc58.134.100 libx264\nSide data:\ncpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\nframe= 1 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed=N/A\nframe= 45 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 78 fps= 77 q=29.0 size= 512kB time=00:00:00.53 bitrate=7864.1kbits/s speed=0.528x\nframe= 123 fps= 81 q=29.0 size= 1280kB time=00:00:02.03 bitrate=5157.0kbits/s speed=1.34x\nframe= 168 fps= 83 q=29.0 size= 2048kB time=00:00:03.53 bitrate=4748.3kbits/s speed=1.75x\nframe= 212 fps= 84 q=29.0 size= 2816kB time=00:00:05.00 bitrate=4613.8kbits/s speed=1.98x\nframe= 256 fps= 85 q=29.0 size= 3840kB time=00:00:06.46 bitrate=4864.5kbits/s speed=2.13x\nframe= 296 fps= 83 q=26.0 size= 4864kB time=00:00:07.80 bitrate=5108.5kbits/s speed=2.19x\nframe= 300 fps= 76 q=-1.0 Lsize= 6486kB time=00:00:09.90 bitrate=5366.9kbits/s speed=2.49x\nvideo:6481kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.068886%\n[libx264 @ 0x55f449bb6800] frame I:2 Avg QP:21.73 size:306198\n[libx264 @ 0x55f449bb6800] frame P:76 Avg QP:23.74 size: 63982\n[libx264 @ 0x55f449bb6800] frame B:222 Avg QP:28.58 size: 5231\n[libx264 @ 0x55f449bb6800] consecutive B-frames: 1.3% 0.0% 0.0% 98.7%\n[libx264 @ 0x55f449bb6800] mb I I16..4: 14.3% 55.8% 29.9%\n[libx264 @ 0x55f449bb6800] mb P I16..4: 1.8% 2.6% 0.6% P16..4: 39.0% 22.6% 18.1% 0.0% 0.0% skip:15.3%\n[libx264 @ 0x55f449bb6800] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 32.8% 2.8% 0.6% direct: 0.9% skip:62.8% L0:45.2% L1:46.0% BI: 8.8%\n[libx264 @ 0x55f449bb6800] 8x8 transform intra:53.5% inter:55.8%\n[libx264 @ 0x55f449bb6800] coded y,uvDC,uvAC intra: 49.5% 52.0% 8.4% inter: 12.1% 5.8% 0.0%\n[libx264 @ 0x55f449bb6800] i16 v,h,dc,p: 15% 31% 10% 44%\n[libx264 @ 0x55f449bb6800] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 18% 17% 28% 4% 7% 8% 7% 5% 7%\n[libx264 @ 0x55f449bb6800] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 17% 17% 11% 5% 12% 11% 11% 7% 8%\n[libx264 @ 0x55f449bb6800] i8c dc,h,v,p: 56% 23% 17% 4%\n[libx264 @ 0x55f449bb6800] Weighted P-Frames: Y:0.0% UV:0.0%\n[libx264 @ 0x55f449bb6800] ref P L0: 55.8% 17.3% 19.9% 6.9%\n[libx264 @ 0x55f449bb6800] ref B L0: 90.7% 8.0% 1.3%\n[libx264 @ 0x55f449bb6800] ref B L1: 97.2% 2.8%\n[libx264 @ 0x55f449bb6800] kb/s:5309.08\nTime taken for the whole run: 101.9380567073822 seconds", "metrics": { "predict_time": 104.38983, "total_time": 104.464645 }, "output": "https://replicate.delivery/pbxt/fwe0Mt7SHBv7vUp5ehc9mwcLnblaw4ERjn1wALyNdc8XBOzkA/output.mp4", "started_at": "2024-02-23T15:46:12.788665Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/sqae64dbcfxyszbs2zx3tshbcu", "cancel": "https://api.replicate.com/v1/predictions/sqae64dbcfxyszbs2zx3tshbcu/cancel" }, "version": "4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455" }
Generated inProcessing depth frames /tmp/tmpdznn39ecwooly-720p.mp4 /root/.pyenv/versions/3.11.8/lib/python3.11/site-packages/transformers/pipelines/base.py:1123: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset warnings.warn( 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/stereo/%d.jpg': Duration: 00:00:12.00, start: 0.000000, bitrate: N/A Stream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 2560x720 [SAR 1:1 DAR 32:9], 25 fps, 25 tbr, 25 tbn, 25 tbc Stream mapping: Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264)) Press [q] to stop, [?] for help [swscaler @ 0x55f449d96b80] deprecated pixel format used, make sure you did set range correctly [libx264 @ 0x55f449bb6800] using SAR=1/1 [libx264 @ 0x55f449bb6800] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 [libx264 @ 0x55f449bb6800] profile High, level 4.0, 4:2:0, 8-bit [libx264 @ 0x55f449bb6800] 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=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=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.mp4': Metadata: encoder : Lavf58.76.100 Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, bt470bg/unknown/unknown, progressive), 2560x720 [SAR 1:1 DAR 32:9], q=2-31, 30 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= 45 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x frame= 78 fps= 77 q=29.0 size= 512kB time=00:00:00.53 bitrate=7864.1kbits/s speed=0.528x frame= 123 fps= 81 q=29.0 size= 1280kB time=00:00:02.03 bitrate=5157.0kbits/s speed=1.34x frame= 168 fps= 83 q=29.0 size= 2048kB time=00:00:03.53 bitrate=4748.3kbits/s speed=1.75x frame= 212 fps= 84 q=29.0 size= 2816kB time=00:00:05.00 bitrate=4613.8kbits/s speed=1.98x frame= 256 fps= 85 q=29.0 size= 3840kB time=00:00:06.46 bitrate=4864.5kbits/s speed=2.13x frame= 296 fps= 83 q=26.0 size= 4864kB time=00:00:07.80 bitrate=5108.5kbits/s speed=2.19x frame= 300 fps= 76 q=-1.0 Lsize= 6486kB time=00:00:09.90 bitrate=5366.9kbits/s speed=2.49x video:6481kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.068886% [libx264 @ 0x55f449bb6800] frame I:2 Avg QP:21.73 size:306198 [libx264 @ 0x55f449bb6800] frame P:76 Avg QP:23.74 size: 63982 [libx264 @ 0x55f449bb6800] frame B:222 Avg QP:28.58 size: 5231 [libx264 @ 0x55f449bb6800] consecutive B-frames: 1.3% 0.0% 0.0% 98.7% [libx264 @ 0x55f449bb6800] mb I I16..4: 14.3% 55.8% 29.9% [libx264 @ 0x55f449bb6800] mb P I16..4: 1.8% 2.6% 0.6% P16..4: 39.0% 22.6% 18.1% 0.0% 0.0% skip:15.3% [libx264 @ 0x55f449bb6800] mb B I16..4: 0.0% 0.0% 0.0% B16..8: 32.8% 2.8% 0.6% direct: 0.9% skip:62.8% L0:45.2% L1:46.0% BI: 8.8% [libx264 @ 0x55f449bb6800] 8x8 transform intra:53.5% inter:55.8% [libx264 @ 0x55f449bb6800] coded y,uvDC,uvAC intra: 49.5% 52.0% 8.4% inter: 12.1% 5.8% 0.0% [libx264 @ 0x55f449bb6800] i16 v,h,dc,p: 15% 31% 10% 44% [libx264 @ 0x55f449bb6800] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 18% 17% 28% 4% 7% 8% 7% 5% 7% [libx264 @ 0x55f449bb6800] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 17% 17% 11% 5% 12% 11% 11% 7% 8% [libx264 @ 0x55f449bb6800] i8c dc,h,v,p: 56% 23% 17% 4% [libx264 @ 0x55f449bb6800] Weighted P-Frames: Y:0.0% UV:0.0% [libx264 @ 0x55f449bb6800] ref P L0: 55.8% 17.3% 19.9% 6.9% [libx264 @ 0x55f449bb6800] ref B L0: 90.7% 8.0% 1.3% [libx264 @ 0x55f449bb6800] ref B L1: 97.2% 2.8% [libx264 @ 0x55f449bb6800] kb/s:5309.08 Time taken for the whole run: 101.9380567073822 seconds
Prediction
lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455IDdztgyulbg43tus77xst2l4iskuStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- ipd
- 6.34
- video
- encoder
- vits
{ "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSEw2maIYTweNphjJg9v7v5J3ZzI48dk2Xd7DYHqUNqeWNJ2/glass.mp4", "encoder": "vits" }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", { input: { ipd: 6.34, video: "https://replicate.delivery/pbxt/KSEw2maIYTweNphjJg9v7v5J3ZzI48dk2Xd7DYHqUNqeWNJ2/glass.mp4", encoder: "vits" } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", input={ "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSEw2maIYTweNphjJg9v7v5J3ZzI48dk2Xd7DYHqUNqeWNJ2/glass.mp4", "encoder": "vits" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", "input": { "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSEw2maIYTweNphjJg9v7v5J3ZzI48dk2Xd7DYHqUNqeWNJ2/glass.mp4", "encoder": "vits" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-23T15:45:28.731340Z", "created_at": "2024-02-23T15:40:11.250369Z", "data_removed": false, "error": null, "id": "dztgyulbg43tus77xst2l4isku", "input": { "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSEw2maIYTweNphjJg9v7v5J3ZzI48dk2Xd7DYHqUNqeWNJ2/glass.mp4", "encoder": "vits" }, "logs": "config.json: 0%| | 0.00/954 [00:00<?, ?B/s]\nconfig.json: 100%|██████████| 954/954 [00:00<00:00, 7.36MB/s]\nmodel.safetensors: 0%| | 0.00/99.2M [00:00<?, ?B/s]\nmodel.safetensors: 11%|█ | 10.5M/99.2M [00:00<00:03, 22.5MB/s]\nmodel.safetensors: 42%|████▏ | 41.9M/99.2M [00:00<00:00, 81.2MB/s]\nmodel.safetensors: 74%|███████▍ | 73.4M/99.2M [00:00<00:00, 125MB/s] \nmodel.safetensors: 100%|██████████| 99.2M/99.2M [00:00<00:00, 118MB/s]\npreprocessor_config.json: 0%| | 0.00/437 [00:00<?, ?B/s]\npreprocessor_config.json: 100%|██████████| 437/437 [00:00<00:00, 1.33MB/s]\nProcessing depth frames /tmp/tmpt8hz3pt4glass.mp4\n/root/.pyenv/versions/3.11.8/lib/python3.11/site-packages/transformers/pipelines/base.py:1123: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset\nwarnings.warn(\nffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --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\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nInput #0, image2, from '/tmp/stereo/%d.jpg':\nDuration: 00:00:10.24, start: 0.000000, bitrate: N/A\nStream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 2560x720 [SAR 1:1 DAR 32:9], 25 fps, 25 tbr, 25 tbn, 25 tbc\nStream mapping:\nStream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264))\nPress [q] to stop, [?] for help\n[swscaler @ 0x55afa02bd780] deprecated pixel format used, make sure you did set range correctly\n[libx264 @ 0x55afa021e480] using SAR=1/1\n[libx264 @ 0x55afa021e480] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2\n[libx264 @ 0x55afa021e480] profile High, level 4.0, 4:2:0, 8-bit\n[libx264 @ 0x55afa021e480] 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=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=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\nOutput #0, mp4, to '/tmp/output.mp4':\nMetadata:\nencoder : Lavf58.76.100\nStream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, bt470bg/unknown/unknown, progressive), 2560x720 [SAR 1:1 DAR 32:9], q=2-31, 30 fps, 15360 tbn\nMetadata:\nencoder : Lavc58.134.100 libx264\nSide data:\ncpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\nframe= 1 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 47 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 103 fps= 96 q=29.0 size= 256kB time=00:00:01.36 bitrate=1534.7kbits/s speed=1.27x\nframe= 160 fps=101 q=29.0 size= 768kB time=00:00:03.26 bitrate=1926.0kbits/s speed=2.07x\nframe= 216 fps=103 q=29.0 size= 1280kB time=00:00:05.13 bitrate=2042.7kbits/s speed=2.46x\nframe= 256 fps= 90 q=-1.0 Lsize= 3010kB time=00:00:08.43 bitrate=2923.7kbits/s speed=2.98x\nvideo:3006kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.129302%\n[libx264 @ 0x55afa021e480] frame I:2 Avg QP:21.32 size: 75844\n[libx264 @ 0x55afa021e480] frame P:65 Avg QP:22.61 size: 25363\n[libx264 @ 0x55afa021e480] frame B:189 Avg QP:24.81 size: 6757\n[libx264 @ 0x55afa021e480] consecutive B-frames: 1.6% 0.0% 0.0% 98.4%\n[libx264 @ 0x55afa021e480] mb I I16..4: 17.2% 73.0% 9.7%\n[libx264 @ 0x55afa021e480] mb P I16..4: 1.6% 4.8% 0.8% P16..4: 47.7% 9.3% 4.6% 0.0% 0.0% skip:31.2%\n[libx264 @ 0x55afa021e480] mb B I16..4: 0.1% 0.3% 0.1% B16..8: 36.4% 2.0% 0.4% direct: 0.7% skip:60.1% L0:47.9% L1:49.1% BI: 3.0%\n[libx264 @ 0x55afa021e480] 8x8 transform intra:67.8% inter:86.3%\n[libx264 @ 0x55afa021e480] coded y,uvDC,uvAC intra: 53.3% 70.8% 33.3% inter: 7.5% 12.7% 0.3%\n[libx264 @ 0x55afa021e480] i16 v,h,dc,p: 29% 32% 11% 27%\n[libx264 @ 0x55afa021e480] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 16% 27% 24% 4% 5% 4% 8% 5% 7%\n[libx264 @ 0x55afa021e480] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 16% 30% 11% 6% 8% 7% 11% 5% 7%\n[libx264 @ 0x55afa021e480] i8c dc,h,v,p: 46% 30% 17% 8%\n[libx264 @ 0x55afa021e480] Weighted P-Frames: Y:0.0% UV:0.0%\n[libx264 @ 0x55afa021e480] ref P L0: 59.5% 12.8% 22.2% 5.6%\n[libx264 @ 0x55afa021e480] ref B L0: 91.9% 7.1% 1.0%\n[libx264 @ 0x55afa021e480] ref B L1: 96.6% 3.4%\n[libx264 @ 0x55afa021e480] kb/s:2885.04\nTime taken for the whole run: 84.38096737861633 seconds", "metrics": { "predict_time": 89.802581, "total_time": 317.480971 }, "output": "https://replicate.delivery/pbxt/V1NTvayFdVbcGhtfmLcvH2rmSYRSJqsmCSxieVzOnRAUeNzkA/output.mp4", "started_at": "2024-02-23T15:43:58.928759Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/dztgyulbg43tus77xst2l4isku", "cancel": "https://api.replicate.com/v1/predictions/dztgyulbg43tus77xst2l4isku/cancel" }, "version": "4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455" }
Generated inconfig.json: 0%| | 0.00/954 [00:00<?, ?B/s] config.json: 100%|██████████| 954/954 [00:00<00:00, 7.36MB/s] model.safetensors: 0%| | 0.00/99.2M [00:00<?, ?B/s] model.safetensors: 11%|█ | 10.5M/99.2M [00:00<00:03, 22.5MB/s] model.safetensors: 42%|████▏ | 41.9M/99.2M [00:00<00:00, 81.2MB/s] model.safetensors: 74%|███████▍ | 73.4M/99.2M [00:00<00:00, 125MB/s] model.safetensors: 100%|██████████| 99.2M/99.2M [00:00<00:00, 118MB/s] preprocessor_config.json: 0%| | 0.00/437 [00:00<?, ?B/s] preprocessor_config.json: 100%|██████████| 437/437 [00:00<00:00, 1.33MB/s] Processing depth frames /tmp/tmpt8hz3pt4glass.mp4 /root/.pyenv/versions/3.11.8/lib/python3.11/site-packages/transformers/pipelines/base.py:1123: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset warnings.warn( 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/stereo/%d.jpg': Duration: 00:00:10.24, start: 0.000000, bitrate: N/A Stream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 2560x720 [SAR 1:1 DAR 32:9], 25 fps, 25 tbr, 25 tbn, 25 tbc Stream mapping: Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264)) Press [q] to stop, [?] for help [swscaler @ 0x55afa02bd780] deprecated pixel format used, make sure you did set range correctly [libx264 @ 0x55afa021e480] using SAR=1/1 [libx264 @ 0x55afa021e480] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 [libx264 @ 0x55afa021e480] profile High, level 4.0, 4:2:0, 8-bit [libx264 @ 0x55afa021e480] 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=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=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.mp4': Metadata: encoder : Lavf58.76.100 Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, bt470bg/unknown/unknown, progressive), 2560x720 [SAR 1:1 DAR 32:9], q=2-31, 30 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= 0x frame= 47 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x frame= 103 fps= 96 q=29.0 size= 256kB time=00:00:01.36 bitrate=1534.7kbits/s speed=1.27x frame= 160 fps=101 q=29.0 size= 768kB time=00:00:03.26 bitrate=1926.0kbits/s speed=2.07x frame= 216 fps=103 q=29.0 size= 1280kB time=00:00:05.13 bitrate=2042.7kbits/s speed=2.46x frame= 256 fps= 90 q=-1.0 Lsize= 3010kB time=00:00:08.43 bitrate=2923.7kbits/s speed=2.98x video:3006kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.129302% [libx264 @ 0x55afa021e480] frame I:2 Avg QP:21.32 size: 75844 [libx264 @ 0x55afa021e480] frame P:65 Avg QP:22.61 size: 25363 [libx264 @ 0x55afa021e480] frame B:189 Avg QP:24.81 size: 6757 [libx264 @ 0x55afa021e480] consecutive B-frames: 1.6% 0.0% 0.0% 98.4% [libx264 @ 0x55afa021e480] mb I I16..4: 17.2% 73.0% 9.7% [libx264 @ 0x55afa021e480] mb P I16..4: 1.6% 4.8% 0.8% P16..4: 47.7% 9.3% 4.6% 0.0% 0.0% skip:31.2% [libx264 @ 0x55afa021e480] mb B I16..4: 0.1% 0.3% 0.1% B16..8: 36.4% 2.0% 0.4% direct: 0.7% skip:60.1% L0:47.9% L1:49.1% BI: 3.0% [libx264 @ 0x55afa021e480] 8x8 transform intra:67.8% inter:86.3% [libx264 @ 0x55afa021e480] coded y,uvDC,uvAC intra: 53.3% 70.8% 33.3% inter: 7.5% 12.7% 0.3% [libx264 @ 0x55afa021e480] i16 v,h,dc,p: 29% 32% 11% 27% [libx264 @ 0x55afa021e480] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 16% 27% 24% 4% 5% 4% 8% 5% 7% [libx264 @ 0x55afa021e480] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 16% 30% 11% 6% 8% 7% 11% 5% 7% [libx264 @ 0x55afa021e480] i8c dc,h,v,p: 46% 30% 17% 8% [libx264 @ 0x55afa021e480] Weighted P-Frames: Y:0.0% UV:0.0% [libx264 @ 0x55afa021e480] ref P L0: 59.5% 12.8% 22.2% 5.6% [libx264 @ 0x55afa021e480] ref B L0: 91.9% 7.1% 1.0% [libx264 @ 0x55afa021e480] ref B L1: 96.6% 3.4% [libx264 @ 0x55afa021e480] kb/s:2885.04 Time taken for the whole run: 84.38096737861633 seconds
Prediction
lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455ID35gj4cdbgf5c5yfq5tc3zyu4piStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
- ipd
- 6.34
- video
- encoder
- vits
{ "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSF8urJwcwtikx8aExSpcg6QpBGTCSV7dZvRr7w2o6QwDqd8/big-eyed-fluff-ball.mp4", "encoder": "vits" }
Install Replicate’s Node.js client library:npm install replicate
Import and set up the client:import Replicate from "replicate"; import fs from "node:fs"; const replicate = new Replicate({ auth: process.env.REPLICATE_API_TOKEN, });
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", { input: { ipd: 6.34, video: "https://replicate.delivery/pbxt/KSF8urJwcwtikx8aExSpcg6QpBGTCSV7dZvRr7w2o6QwDqd8/big-eyed-fluff-ball.mp4", encoder: "vits" } } ); // To access the file URL: console.log(output.url()); //=> "http://example.com" // To write the file to disk: fs.writeFile("my-image.png", output);
To learn more, take a look at the guide on getting started with Node.js.
Install Replicate’s Python client library:pip install replicate
Import the client:import replicate
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", input={ "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSF8urJwcwtikx8aExSpcg6QpBGTCSV7dZvRr7w2o6QwDqd8/big-eyed-fluff-ball.mp4", "encoder": "vits" } ) print(output)
To learn more, take a look at the guide on getting started with Python.
Run lucataco/depth-anything-video-sbs using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
curl -s -X POST \ -H "Authorization: Bearer $REPLICATE_API_TOKEN" \ -H "Content-Type: application/json" \ -H "Prefer: wait" \ -d $'{ "version": "lucataco/depth-anything-video-sbs:4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455", "input": { "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSF8urJwcwtikx8aExSpcg6QpBGTCSV7dZvRr7w2o6QwDqd8/big-eyed-fluff-ball.mp4", "encoder": "vits" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2024-02-23T15:59:53.625187Z", "created_at": "2024-02-23T15:53:47.128015Z", "data_removed": false, "error": null, "id": "35gj4cdbgf5c5yfq5tc3zyu4pi", "input": { "ipd": 6.34, "video": "https://replicate.delivery/pbxt/KSF8urJwcwtikx8aExSpcg6QpBGTCSV7dZvRr7w2o6QwDqd8/big-eyed-fluff-ball.mp4", "encoder": "vits" }, "logs": "config.json: 0%| | 0.00/954 [00:00<?, ?B/s]\nconfig.json: 100%|██████████| 954/954 [00:00<00:00, 6.21MB/s]\nmodel.safetensors: 0%| | 0.00/99.2M [00:00<?, ?B/s]\nmodel.safetensors: 11%|█ | 10.5M/99.2M [00:00<00:01, 61.0MB/s]\nmodel.safetensors: 63%|██████▎ | 62.9M/99.2M [00:00<00:00, 267MB/s] \nmodel.safetensors: 100%|██████████| 99.2M/99.2M [00:00<00:00, 279MB/s]\npreprocessor_config.json: 0%| | 0.00/437 [00:00<?, ?B/s]\npreprocessor_config.json: 100%|██████████| 437/437 [00:00<00:00, 2.83MB/s]\nProcessing depth frames /tmp/tmpwpr9i2mybig-eyed-fluff-ball.mp4\n/root/.pyenv/versions/3.11.8/lib/python3.11/site-packages/transformers/pipelines/base.py:1123: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset\nwarnings.warn(\nffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers\nbuilt with gcc 11 (Ubuntu 11.2.0-19ubuntu1)\nconfiguration: --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\nlibavutil 56. 70.100 / 56. 70.100\nlibavcodec 58.134.100 / 58.134.100\nlibavformat 58. 76.100 / 58. 76.100\nlibavdevice 58. 13.100 / 58. 13.100\nlibavfilter 7.110.100 / 7.110.100\nlibswscale 5. 9.100 / 5. 9.100\nlibswresample 3. 9.100 / 3. 9.100\nlibpostproc 55. 9.100 / 55. 9.100\nInput #0, image2, from '/tmp/stereo/%d.jpg':\nDuration: 00:00:10.24, start: 0.000000, bitrate: N/A\nStream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 3840x1088 [SAR 1:1 DAR 60:17], 25 fps, 25 tbr, 25 tbn, 25 tbc\nStream mapping:\nStream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264))\nPress [q] to stop, [?] for help\n[swscaler @ 0x56289629ea00] deprecated pixel format used, make sure you did set range correctly\n[libx264 @ 0x562895f1ea80] using SAR=1/1\n[libx264 @ 0x562895f1ea80] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2\n[libx264 @ 0x562895f1ea80] profile High, level 5.0, 4:2:0, 8-bit\n[libx264 @ 0x562895f1ea80] 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=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=crf mbtree=1 crf=23.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00\nOutput #0, mp4, to '/tmp/output.mp4':\nMetadata:\nencoder : Lavf58.76.100\nStream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, bt470bg/unknown/unknown, progressive), 3840x1088 [SAR 1:1 DAR 60:17], q=2-31, 30 fps, 15360 tbn\nMetadata:\nencoder : Lavc58.134.100 libx264\nSide data:\ncpb: bitrate max/min/avg: 0/0/0 buffer size: 0 vbv_delay: N/A\nframe= 1 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed=N/A\nframe= 12 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 24 fps= 23 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 36 fps= 23 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 47 fps= 19 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 57 fps= 19 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x\nframe= 68 fps= 19 q=29.0 size= 1024kB time=00:00:00.20 bitrate=41931.3kbits/s speed=0.0561x\nframe= 78 fps= 19 q=29.0 size= 2048kB time=00:00:00.53 bitrate=31454.2kbits/s speed=0.131x\nframe= 90 fps= 19 q=29.0 size= 3328kB time=00:00:00.93 bitrate=29208.7kbits/s speed=0.201x\nframe= 99 fps= 19 q=29.0 size= 4352kB time=00:00:01.23 bitrate=28905.5kbits/s speed=0.238x\nframe= 109 fps= 19 q=29.0 size= 5376kB time=00:00:01.56 bitrate=28109.8kbits/s speed=0.275x\nframe= 119 fps= 19 q=29.0 size= 6400kB time=00:00:01.90 bitrate=27593.4kbits/s speed=0.305x\nframe= 128 fps= 19 q=29.0 size= 7424kB time=00:00:02.20 bitrate=27643.6kbits/s speed=0.325x\nframe= 139 fps= 19 q=29.0 size= 8448kB time=00:00:02.56 bitrate=26962.8kbits/s speed=0.348x\nframe= 151 fps= 19 q=29.0 size= 9472kB time=00:00:02.96 bitrate=26155.0kbits/s speed=0.374x\nframe= 159 fps= 19 q=29.0 size= 10496kB time=00:00:03.23 bitrate=26592.3kbits/s speed=0.382x\nframe= 174 fps= 19 q=29.0 size= 12032kB time=00:00:03.73 bitrate=26401.3kbits/s speed=0.411x\nframe= 187 fps= 19 q=29.0 size= 13056kB time=00:00:04.16 bitrate=25668.8kbits/s speed=0.433x\nframe= 197 fps= 19 q=29.0 size= 14080kB time=00:00:04.50 bitrate=25631.6kbits/s speed=0.444x\nframe= 210 fps= 20 q=29.0 size= 14848kB time=00:00:04.93 bitrate=24655.5kbits/s speed=0.462x\nframe= 227 fps= 20 q=29.0 size= 15872kB time=00:00:05.50 bitrate=23640.4kbits/s speed=0.491x\nframe= 240 fps= 20 q=29.0 size= 16384kB time=00:00:05.93 bitrate=22620.8kbits/s speed=0.506x\nframe= 256 fps= 21 q=29.0 size= 16896kB time=00:00:06.46 bitrate=21403.8kbits/s speed=0.528x\nframe= 256 fps= 19 q=-1.0 Lsize= 19548kB time=00:00:08.43 bitrate=18988.1kbits/s speed=0.624x\nvideo:19543kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.021212%\n[libx264 @ 0x562895f1ea80] frame I:2 Avg QP:23.69 size:243581\n[libx264 @ 0x562895f1ea80] frame P:65 Avg QP:25.13 size:127613\n[libx264 @ 0x562895f1ea80] frame B:189 Avg QP:27.91 size: 59417\n[libx264 @ 0x562895f1ea80] consecutive B-frames: 1.6% 0.0% 0.0% 98.4%\n[libx264 @ 0x562895f1ea80] mb I I16..4: 12.5% 75.6% 11.9%\n[libx264 @ 0x562895f1ea80] mb P I16..4: 5.2% 20.6% 5.7% P16..4: 36.1% 13.3% 4.8% 0.0% 0.0% skip:14.3%\n[libx264 @ 0x562895f1ea80] mb B I16..4: 0.6% 2.1% 1.6% B16..8: 38.9% 7.9% 1.6% direct: 4.2% skip:43.1% L0:48.9% L1:42.8% BI: 8.3%\n[libx264 @ 0x562895f1ea80] 8x8 transform intra:61.7% inter:75.5%\n[libx264 @ 0x562895f1ea80] coded y,uvDC,uvAC intra: 68.9% 80.7% 25.3% inter: 19.9% 26.2% 0.4%\n[libx264 @ 0x562895f1ea80] i16 v,h,dc,p: 15% 24% 5% 56%\n[libx264 @ 0x562895f1ea80] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 15% 21% 11% 6% 9% 9% 11% 8% 9%\n[libx264 @ 0x562895f1ea80] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 15% 18% 12% 7% 14% 11% 11% 7% 7%\n[libx264 @ 0x562895f1ea80] i8c dc,h,v,p: 38% 27% 15% 20%\n[libx264 @ 0x562895f1ea80] Weighted P-Frames: Y:0.0% UV:0.0%\n[libx264 @ 0x562895f1ea80] ref P L0: 68.2% 14.9% 13.5% 3.4%\n[libx264 @ 0x562895f1ea80] ref B L0: 93.6% 5.8% 0.6%\n[libx264 @ 0x562895f1ea80] ref B L1: 97.8% 2.2%\n[libx264 @ 0x562895f1ea80] kb/s:18761.06\nTime taken for the whole run: 228.6421160697937 seconds", "metrics": { "predict_time": 230.241391, "total_time": 366.497172 }, "output": "https://replicate.delivery/pbxt/OxOWeP2gXsVRDSLTM6Rev0fJcc2luOy5zzM1QtdqfhrhvcmJB/output.mp4", "started_at": "2024-02-23T15:56:03.383796Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/35gj4cdbgf5c5yfq5tc3zyu4pi", "cancel": "https://api.replicate.com/v1/predictions/35gj4cdbgf5c5yfq5tc3zyu4pi/cancel" }, "version": "4f5b3a0a3f9162241ae530f78bae4db053bf1fd58165c2a789114593655fe455" }
Generated inconfig.json: 0%| | 0.00/954 [00:00<?, ?B/s] config.json: 100%|██████████| 954/954 [00:00<00:00, 6.21MB/s] model.safetensors: 0%| | 0.00/99.2M [00:00<?, ?B/s] model.safetensors: 11%|█ | 10.5M/99.2M [00:00<00:01, 61.0MB/s] model.safetensors: 63%|██████▎ | 62.9M/99.2M [00:00<00:00, 267MB/s] model.safetensors: 100%|██████████| 99.2M/99.2M [00:00<00:00, 279MB/s] preprocessor_config.json: 0%| | 0.00/437 [00:00<?, ?B/s] preprocessor_config.json: 100%|██████████| 437/437 [00:00<00:00, 2.83MB/s] Processing depth frames /tmp/tmpwpr9i2mybig-eyed-fluff-ball.mp4 /root/.pyenv/versions/3.11.8/lib/python3.11/site-packages/transformers/pipelines/base.py:1123: UserWarning: You seem to be using the pipelines sequentially on GPU. In order to maximize efficiency please use a dataset warnings.warn( 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/stereo/%d.jpg': Duration: 00:00:10.24, start: 0.000000, bitrate: N/A Stream #0:0: Video: mjpeg (Baseline), yuvj420p(pc, bt470bg/unknown/unknown), 3840x1088 [SAR 1:1 DAR 60:17], 25 fps, 25 tbr, 25 tbn, 25 tbc Stream mapping: Stream #0:0 -> #0:0 (mjpeg (native) -> h264 (libx264)) Press [q] to stop, [?] for help [swscaler @ 0x56289629ea00] deprecated pixel format used, make sure you did set range correctly [libx264 @ 0x562895f1ea80] using SAR=1/1 [libx264 @ 0x562895f1ea80] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 [libx264 @ 0x562895f1ea80] profile High, level 5.0, 4:2:0, 8-bit [libx264 @ 0x562895f1ea80] 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=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=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.mp4': Metadata: encoder : Lavf58.76.100 Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, bt470bg/unknown/unknown, progressive), 3840x1088 [SAR 1:1 DAR 60:17], q=2-31, 30 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= 12 fps=0.0 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x frame= 24 fps= 23 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x frame= 36 fps= 23 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x frame= 47 fps= 19 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x frame= 57 fps= 19 q=0.0 size= 0kB time=00:00:00.00 bitrate=N/A speed= 0x frame= 68 fps= 19 q=29.0 size= 1024kB time=00:00:00.20 bitrate=41931.3kbits/s speed=0.0561x frame= 78 fps= 19 q=29.0 size= 2048kB time=00:00:00.53 bitrate=31454.2kbits/s speed=0.131x frame= 90 fps= 19 q=29.0 size= 3328kB time=00:00:00.93 bitrate=29208.7kbits/s speed=0.201x frame= 99 fps= 19 q=29.0 size= 4352kB time=00:00:01.23 bitrate=28905.5kbits/s speed=0.238x frame= 109 fps= 19 q=29.0 size= 5376kB time=00:00:01.56 bitrate=28109.8kbits/s speed=0.275x frame= 119 fps= 19 q=29.0 size= 6400kB time=00:00:01.90 bitrate=27593.4kbits/s speed=0.305x frame= 128 fps= 19 q=29.0 size= 7424kB time=00:00:02.20 bitrate=27643.6kbits/s speed=0.325x frame= 139 fps= 19 q=29.0 size= 8448kB time=00:00:02.56 bitrate=26962.8kbits/s speed=0.348x frame= 151 fps= 19 q=29.0 size= 9472kB time=00:00:02.96 bitrate=26155.0kbits/s speed=0.374x frame= 159 fps= 19 q=29.0 size= 10496kB time=00:00:03.23 bitrate=26592.3kbits/s speed=0.382x frame= 174 fps= 19 q=29.0 size= 12032kB time=00:00:03.73 bitrate=26401.3kbits/s speed=0.411x frame= 187 fps= 19 q=29.0 size= 13056kB time=00:00:04.16 bitrate=25668.8kbits/s speed=0.433x frame= 197 fps= 19 q=29.0 size= 14080kB time=00:00:04.50 bitrate=25631.6kbits/s speed=0.444x frame= 210 fps= 20 q=29.0 size= 14848kB time=00:00:04.93 bitrate=24655.5kbits/s speed=0.462x frame= 227 fps= 20 q=29.0 size= 15872kB time=00:00:05.50 bitrate=23640.4kbits/s speed=0.491x frame= 240 fps= 20 q=29.0 size= 16384kB time=00:00:05.93 bitrate=22620.8kbits/s speed=0.506x frame= 256 fps= 21 q=29.0 size= 16896kB time=00:00:06.46 bitrate=21403.8kbits/s speed=0.528x frame= 256 fps= 19 q=-1.0 Lsize= 19548kB time=00:00:08.43 bitrate=18988.1kbits/s speed=0.624x video:19543kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.021212% [libx264 @ 0x562895f1ea80] frame I:2 Avg QP:23.69 size:243581 [libx264 @ 0x562895f1ea80] frame P:65 Avg QP:25.13 size:127613 [libx264 @ 0x562895f1ea80] frame B:189 Avg QP:27.91 size: 59417 [libx264 @ 0x562895f1ea80] consecutive B-frames: 1.6% 0.0% 0.0% 98.4% [libx264 @ 0x562895f1ea80] mb I I16..4: 12.5% 75.6% 11.9% [libx264 @ 0x562895f1ea80] mb P I16..4: 5.2% 20.6% 5.7% P16..4: 36.1% 13.3% 4.8% 0.0% 0.0% skip:14.3% [libx264 @ 0x562895f1ea80] mb B I16..4: 0.6% 2.1% 1.6% B16..8: 38.9% 7.9% 1.6% direct: 4.2% skip:43.1% L0:48.9% L1:42.8% BI: 8.3% [libx264 @ 0x562895f1ea80] 8x8 transform intra:61.7% inter:75.5% [libx264 @ 0x562895f1ea80] coded y,uvDC,uvAC intra: 68.9% 80.7% 25.3% inter: 19.9% 26.2% 0.4% [libx264 @ 0x562895f1ea80] i16 v,h,dc,p: 15% 24% 5% 56% [libx264 @ 0x562895f1ea80] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 15% 21% 11% 6% 9% 9% 11% 8% 9% [libx264 @ 0x562895f1ea80] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 15% 18% 12% 7% 14% 11% 11% 7% 7% [libx264 @ 0x562895f1ea80] i8c dc,h,v,p: 38% 27% 15% 20% [libx264 @ 0x562895f1ea80] Weighted P-Frames: Y:0.0% UV:0.0% [libx264 @ 0x562895f1ea80] ref P L0: 68.2% 14.9% 13.5% 3.4% [libx264 @ 0x562895f1ea80] ref B L0: 93.6% 5.8% 0.6% [libx264 @ 0x562895f1ea80] ref B L1: 97.8% 2.2% [libx264 @ 0x562895f1ea80] kb/s:18761.06 Time taken for the whole run: 228.6421160697937 seconds
Want to make some of these yourself?
Run this model