jd7h / xmem
Video object segmentation for short and long videos
Prediction
jd7h/xmem:f093cc6c631ea4bee9d4feba41608c814167f519c150322b4d79e537c5c7f38eModelID6wgovvdbddks32eafrkh7zbftyStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
{ "mask": "https://replicate.delivery/pbxt/JiS9TbTu6Rox3zodmka5fx5b75xMWuU8IkK5Dg9x50th2g3G/0001.png", "video": "https://replicate.delivery/pbxt/JiS9TA1ZdiFZe6wWbdWAYXm1k8a9iivOfvASBVshfZuUrjLK/raccoon_short.mp4" }
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 jd7h/xmem using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "jd7h/xmem:f093cc6c631ea4bee9d4feba41608c814167f519c150322b4d79e537c5c7f38e", { input: { mask: "https://replicate.delivery/pbxt/JiS9TbTu6Rox3zodmka5fx5b75xMWuU8IkK5Dg9x50th2g3G/0001.png", video: "https://replicate.delivery/pbxt/JiS9TA1ZdiFZe6wWbdWAYXm1k8a9iivOfvASBVshfZuUrjLK/raccoon_short.mp4" } } ); // 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 jd7h/xmem using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "jd7h/xmem:f093cc6c631ea4bee9d4feba41608c814167f519c150322b4d79e537c5c7f38e", input={ "mask": "https://replicate.delivery/pbxt/JiS9TbTu6Rox3zodmka5fx5b75xMWuU8IkK5Dg9x50th2g3G/0001.png", "video": "https://replicate.delivery/pbxt/JiS9TA1ZdiFZe6wWbdWAYXm1k8a9iivOfvASBVshfZuUrjLK/raccoon_short.mp4" } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run jd7h/xmem 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": "jd7h/xmem:f093cc6c631ea4bee9d4feba41608c814167f519c150322b4d79e537c5c7f38e", "input": { "mask": "https://replicate.delivery/pbxt/JiS9TbTu6Rox3zodmka5fx5b75xMWuU8IkK5Dg9x50th2g3G/0001.png", "video": "https://replicate.delivery/pbxt/JiS9TA1ZdiFZe6wWbdWAYXm1k8a9iivOfvASBVshfZuUrjLK/raccoon_short.mp4" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-17T16:26:21.233664Z", "created_at": "2023-10-17T16:25:56.878782Z", "data_removed": false, "error": null, "id": "6wgovvdbddks32eafrkh7zbfty", "input": { "mask": "https://replicate.delivery/pbxt/JiS9TbTu6Rox3zodmka5fx5b75xMWuU8IkK5Dg9x50th2g3G/0001.png", "video": "https://replicate.delivery/pbxt/JiS9TA1ZdiFZe6wWbdWAYXm1k8a9iivOfvASBVshfZuUrjLK/raccoon_short.mp4" }, "logs": "/root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\nwarnings.warn(\n/root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\nwarnings.warn(\n0% (0 of 152) | | Elapsed Time: 0:00:00 ETA: --:--:--\n0% (1 of 152) | | Elapsed Time: 0:00:03 ETA: 0:07:50\n1% (2 of 152) | | Elapsed Time: 0:00:03 ETA: 0:04:58\n3% (6 of 152) | | Elapsed Time: 0:00:04 ETA: 0:04:50\n6% (10 of 152) |# | Elapsed Time: 0:00:04 ETA: 0:00:59\n9% (14 of 152) |## | Elapsed Time: 0:00:04 ETA: 0:00:57\n10% (16 of 152) |## | Elapsed Time: 0:00:04 ETA: 0:00:36\n13% (20 of 152) |### | Elapsed Time: 0:00:04 ETA: 0:00:29\n15% (24 of 152) |### | Elapsed Time: 0:00:04 ETA: 0:00:28\n17% (26 of 152) |### | Elapsed Time: 0:00:04 ETA: 0:00:22\n19% (29 of 152) |#### | Elapsed Time: 0:00:04 ETA: 0:00:21\n20% (31 of 152) |#### | Elapsed Time: 0:00:04 ETA: 0:00:18\n21% (33 of 152) |#### | Elapsed Time: 0:00:04 ETA: 0:00:18\n23% (35 of 152) |##### | Elapsed Time: 0:00:04 ETA: 0:00:16\n25% (39 of 152) |##### | Elapsed Time: 0:00:04 ETA: 0:00:15\n26% (41 of 152) |###### | Elapsed Time: 0:00:04 ETA: 0:00:13\n28% (43 of 152) |###### | Elapsed Time: 0:00:04 ETA: 0:00:13\n29% (45 of 152) |###### | Elapsed Time: 0:00:05 ETA: 0:00:12\n32% (49 of 152) |####### | Elapsed Time: 0:00:05 ETA: 0:00:04\n33% (51 of 152) |####### | Elapsed Time: 0:00:05 ETA: 0:00:04\n35% (54 of 152) |######## | Elapsed Time: 0:00:05 ETA: 0:00:04\n36% (56 of 152) |######## | Elapsed Time: 0:00:05 ETA: 0:00:03\n39% (60 of 152) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03\n42% (64 of 152) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03\n43% (66 of 152) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03\n44% (68 of 152) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03\n46% (70 of 152) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03\n47% (72 of 152) |########## | Elapsed Time: 0:00:05 ETA: 0:00:02\n48% (74 of 152) |########### | Elapsed Time: 0:00:05 ETA: 0:00:02\n50% (76 of 152) |########### | Elapsed Time: 0:00:05 ETA: 0:00:02\n51% (79 of 152) |########### | Elapsed Time: 0:00:05 ETA: 0:00:02\n53% (81 of 152) |############ | Elapsed Time: 0:00:05 ETA: 0:00:02\n54% (83 of 152) |############ | Elapsed Time: 0:00:06 ETA: 0:00:01\n55% (85 of 152) |############ | Elapsed Time: 0:00:06 ETA: 0:00:01\n58% (89 of 152) |############# | Elapsed Time: 0:00:06 ETA: 0:00:01\n59% (91 of 152) |############# | Elapsed Time: 0:00:06 ETA: 0:00:01\n61% (93 of 152) |############## | Elapsed Time: 0:00:06 ETA: 0:00:01\n62% (95 of 152) |############## | Elapsed Time: 0:00:06 ETA: 0:00:01\n65% (99 of 152) |############## | Elapsed Time: 0:00:06 ETA: 0:00:01\n66% (101 of 152) |############## | Elapsed Time: 0:00:06 ETA: 0:00:01\n68% (104 of 152) |############### | Elapsed Time: 0:00:06 ETA: 0:00:01\n69% (106 of 152) |############### | Elapsed Time: 0:00:06 ETA: 0:00:01\n71% (108 of 152) |############### | Elapsed Time: 0:00:06 ETA: 0:00:01\n72% (110 of 152) |############### | Elapsed Time: 0:00:06 ETA: 0:00:01\n73% (112 of 152) |################ | Elapsed Time: 0:00:06 ETA: 0:00:01\n75% (114 of 152) |################ | Elapsed Time: 0:00:06 ETA: 0:00:00\n76% (116 of 152) |################ | Elapsed Time: 0:00:06 ETA: 0:00:00\n77% (118 of 152) |################# | Elapsed Time: 0:00:06 ETA: 0:00:00\n78% (120 of 152) |################# | Elapsed Time: 0:00:06 ETA: 0:00:00\n80% (122 of 152) |################# | Elapsed Time: 0:00:07 ETA: 0:00:00\n81% (124 of 152) |################# | Elapsed Time: 0:00:07 ETA: 0:00:00\n82% (126 of 152) |################## | Elapsed Time: 0:00:07 ETA: 0:00:00\n84% (129 of 152) |################## | Elapsed Time: 0:00:07 ETA: 0:00:00\n86% (131 of 152) |################## | Elapsed Time: 0:00:07 ETA: 0:00:00\n87% (133 of 152) |################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n88% (135 of 152) |################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n90% (137 of 152) |################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n91% (139 of 152) |#################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n92% (141 of 152) |#################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n94% (143 of 152) |#################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n95% (145 of 152) |#################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n96% (147 of 152) |##################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n98% (149 of 152) |##################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n99% (151 of 152) |##################### | Elapsed Time: 0:00:07 ETA: 0:00:00\n100% (152 of 152) |######################| Elapsed Time: 0:00:08 Time: 0:00:08\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 './results/default_video/*.png':\nDuration: 00:00:06.33, start: 0.000000, bitrate: N/A\nStream #0:0: Video: png, gray(pc), 854x480, 24 fps, 24 tbr, 24 tbn, 24 tbc\nStream mapping:\nStream #0:0 -> #0:0 (png (native) -> h264 (libx264))\nPress [q] to stop, [?] for help\n[libx264 @ 0x555c175adac0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2\n[libx264 @ 0x555c175adac0] profile High 4:4:4 Predictive, level 3.0, 4:0:0, 8-bit\n[libx264 @ 0x555c175adac0] 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=0 mixed_ref=1 me_range=16 chroma_me=0 trellis=0 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=0 chroma_qp_offset=0 threads=15 lookahead_threads=2 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc=cqp mbtree=0 qp=0\nOutput #0, mp4, to 'result.mp4':\nMetadata:\nencoder : Lavf58.76.100\nStream #0:0: Video: h264 (avc1 / 0x31637661), gray(pc, progressive), 854x480, q=2-31, 24 fps, 12288 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= 152 fps=0.0 q=-1.0 Lsize= 66kB time=00:00:06.29 bitrate= 86.2kbits/s speed=51.8x\nvideo:65kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 2.187439%\n[libx264 @ 0x555c175adac0] frame I:1 Avg QP: 0.00 size: 683\n[libx264 @ 0x555c175adac0] frame P:151 Avg QP: 0.00 size: 432\n[libx264 @ 0x555c175adac0] mb I I16..4: 99.9% 0.0% 0.1%\n[libx264 @ 0x555c175adac0] mb P I16..4: 0.8% 0.0% 0.0% P16..4: 1.4% 1.2% 0.3% 0.0% 0.0% skip:96.3%\n[libx264 @ 0x555c175adac0] 8x8 transform intra:0.1% inter:7.6%\n[libx264 @ 0x555c175adac0] coded y intra: 7.2% inter: 0.5%\n[libx264 @ 0x555c175adac0] i16 v,h,dc,p: 96% 3% 2% 0%\n[libx264 @ 0x555c175adac0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 25% 25% 50% 0% 0% 0% 0% 0% 0%\n[libx264 @ 0x555c175adac0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 39% 22% 34% 1% 1% 0% 1% 0% 1%\n[libx264 @ 0x555c175adac0] i8c dc,h,v,p: 100% 0% 0% 0%\n[libx264 @ 0x555c175adac0] Weighted P-Frames: Y:0.0%\n[libx264 @ 0x555c175adac0] ref P L0: 68.1% 0.0% 21.3% 10.6%\n[libx264 @ 0x555c175adac0] kb/s:83.18", "metrics": { "predict_time": 16.520851, "total_time": 24.354882 }, "output": "https://pbxt.replicate.delivery/GL8YzbfVyDw2XKnqf76jgzfhSfbgz2kT3P9GeIDqfT9KrnxbE/result.mp4", "started_at": "2023-10-17T16:26:04.712813Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/6wgovvdbddks32eafrkh7zbfty", "cancel": "https://api.replicate.com/v1/predictions/6wgovvdbddks32eafrkh7zbfty/cancel" }, "version": "f093cc6c631ea4bee9d4feba41608c814167f519c150322b4d79e537c5c7f38e" }
Generated in/root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( /root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( 0% (0 of 152) | | Elapsed Time: 0:00:00 ETA: --:--:-- 0% (1 of 152) | | Elapsed Time: 0:00:03 ETA: 0:07:50 1% (2 of 152) | | Elapsed Time: 0:00:03 ETA: 0:04:58 3% (6 of 152) | | Elapsed Time: 0:00:04 ETA: 0:04:50 6% (10 of 152) |# | Elapsed Time: 0:00:04 ETA: 0:00:59 9% (14 of 152) |## | Elapsed Time: 0:00:04 ETA: 0:00:57 10% (16 of 152) |## | Elapsed Time: 0:00:04 ETA: 0:00:36 13% (20 of 152) |### | Elapsed Time: 0:00:04 ETA: 0:00:29 15% (24 of 152) |### | Elapsed Time: 0:00:04 ETA: 0:00:28 17% (26 of 152) |### | Elapsed Time: 0:00:04 ETA: 0:00:22 19% (29 of 152) |#### | Elapsed Time: 0:00:04 ETA: 0:00:21 20% (31 of 152) |#### | Elapsed Time: 0:00:04 ETA: 0:00:18 21% (33 of 152) |#### | Elapsed Time: 0:00:04 ETA: 0:00:18 23% (35 of 152) |##### | Elapsed Time: 0:00:04 ETA: 0:00:16 25% (39 of 152) |##### | Elapsed Time: 0:00:04 ETA: 0:00:15 26% (41 of 152) |###### | Elapsed Time: 0:00:04 ETA: 0:00:13 28% (43 of 152) |###### | Elapsed Time: 0:00:04 ETA: 0:00:13 29% (45 of 152) |###### | Elapsed Time: 0:00:05 ETA: 0:00:12 32% (49 of 152) |####### | Elapsed Time: 0:00:05 ETA: 0:00:04 33% (51 of 152) |####### | Elapsed Time: 0:00:05 ETA: 0:00:04 35% (54 of 152) |######## | Elapsed Time: 0:00:05 ETA: 0:00:04 36% (56 of 152) |######## | Elapsed Time: 0:00:05 ETA: 0:00:03 39% (60 of 152) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03 42% (64 of 152) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03 43% (66 of 152) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03 44% (68 of 152) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03 46% (70 of 152) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03 47% (72 of 152) |########## | Elapsed Time: 0:00:05 ETA: 0:00:02 48% (74 of 152) |########### | Elapsed Time: 0:00:05 ETA: 0:00:02 50% (76 of 152) |########### | Elapsed Time: 0:00:05 ETA: 0:00:02 51% (79 of 152) |########### | Elapsed Time: 0:00:05 ETA: 0:00:02 53% (81 of 152) |############ | Elapsed Time: 0:00:05 ETA: 0:00:02 54% (83 of 152) |############ | Elapsed Time: 0:00:06 ETA: 0:00:01 55% (85 of 152) |############ | Elapsed Time: 0:00:06 ETA: 0:00:01 58% (89 of 152) |############# | Elapsed Time: 0:00:06 ETA: 0:00:01 59% (91 of 152) |############# | Elapsed Time: 0:00:06 ETA: 0:00:01 61% (93 of 152) |############## | Elapsed Time: 0:00:06 ETA: 0:00:01 62% (95 of 152) |############## | Elapsed Time: 0:00:06 ETA: 0:00:01 65% (99 of 152) |############## | Elapsed Time: 0:00:06 ETA: 0:00:01 66% (101 of 152) |############## | Elapsed Time: 0:00:06 ETA: 0:00:01 68% (104 of 152) |############### | Elapsed Time: 0:00:06 ETA: 0:00:01 69% (106 of 152) |############### | Elapsed Time: 0:00:06 ETA: 0:00:01 71% (108 of 152) |############### | Elapsed Time: 0:00:06 ETA: 0:00:01 72% (110 of 152) |############### | Elapsed Time: 0:00:06 ETA: 0:00:01 73% (112 of 152) |################ | Elapsed Time: 0:00:06 ETA: 0:00:01 75% (114 of 152) |################ | Elapsed Time: 0:00:06 ETA: 0:00:00 76% (116 of 152) |################ | Elapsed Time: 0:00:06 ETA: 0:00:00 77% (118 of 152) |################# | Elapsed Time: 0:00:06 ETA: 0:00:00 78% (120 of 152) |################# | Elapsed Time: 0:00:06 ETA: 0:00:00 80% (122 of 152) |################# | Elapsed Time: 0:00:07 ETA: 0:00:00 81% (124 of 152) |################# | Elapsed Time: 0:00:07 ETA: 0:00:00 82% (126 of 152) |################## | Elapsed Time: 0:00:07 ETA: 0:00:00 84% (129 of 152) |################## | Elapsed Time: 0:00:07 ETA: 0:00:00 86% (131 of 152) |################## | Elapsed Time: 0:00:07 ETA: 0:00:00 87% (133 of 152) |################### | Elapsed Time: 0:00:07 ETA: 0:00:00 88% (135 of 152) |################### | Elapsed Time: 0:00:07 ETA: 0:00:00 90% (137 of 152) |################### | Elapsed Time: 0:00:07 ETA: 0:00:00 91% (139 of 152) |#################### | Elapsed Time: 0:00:07 ETA: 0:00:00 92% (141 of 152) |#################### | Elapsed Time: 0:00:07 ETA: 0:00:00 94% (143 of 152) |#################### | Elapsed Time: 0:00:07 ETA: 0:00:00 95% (145 of 152) |#################### | Elapsed Time: 0:00:07 ETA: 0:00:00 96% (147 of 152) |##################### | Elapsed Time: 0:00:07 ETA: 0:00:00 98% (149 of 152) |##################### | Elapsed Time: 0:00:07 ETA: 0:00:00 99% (151 of 152) |##################### | Elapsed Time: 0:00:07 ETA: 0:00:00 100% (152 of 152) |######################| Elapsed Time: 0:00:08 Time: 0:00:08 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 './results/default_video/*.png': Duration: 00:00:06.33, start: 0.000000, bitrate: N/A Stream #0:0: Video: png, gray(pc), 854x480, 24 fps, 24 tbr, 24 tbn, 24 tbc Stream mapping: Stream #0:0 -> #0:0 (png (native) -> h264 (libx264)) Press [q] to stop, [?] for help [libx264 @ 0x555c175adac0] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 [libx264 @ 0x555c175adac0] profile High 4:4:4 Predictive, level 3.0, 4:0:0, 8-bit [libx264 @ 0x555c175adac0] 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=0 mixed_ref=1 me_range=16 chroma_me=0 trellis=0 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=0 chroma_qp_offset=0 threads=15 lookahead_threads=2 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc=cqp mbtree=0 qp=0 Output #0, mp4, to 'result.mp4': Metadata: encoder : Lavf58.76.100 Stream #0:0: Video: h264 (avc1 / 0x31637661), gray(pc, progressive), 854x480, q=2-31, 24 fps, 12288 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= 152 fps=0.0 q=-1.0 Lsize= 66kB time=00:00:06.29 bitrate= 86.2kbits/s speed=51.8x video:65kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 2.187439% [libx264 @ 0x555c175adac0] frame I:1 Avg QP: 0.00 size: 683 [libx264 @ 0x555c175adac0] frame P:151 Avg QP: 0.00 size: 432 [libx264 @ 0x555c175adac0] mb I I16..4: 99.9% 0.0% 0.1% [libx264 @ 0x555c175adac0] mb P I16..4: 0.8% 0.0% 0.0% P16..4: 1.4% 1.2% 0.3% 0.0% 0.0% skip:96.3% [libx264 @ 0x555c175adac0] 8x8 transform intra:0.1% inter:7.6% [libx264 @ 0x555c175adac0] coded y intra: 7.2% inter: 0.5% [libx264 @ 0x555c175adac0] i16 v,h,dc,p: 96% 3% 2% 0% [libx264 @ 0x555c175adac0] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 25% 25% 50% 0% 0% 0% 0% 0% 0% [libx264 @ 0x555c175adac0] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 39% 22% 34% 1% 1% 0% 1% 0% 1% [libx264 @ 0x555c175adac0] i8c dc,h,v,p: 100% 0% 0% 0% [libx264 @ 0x555c175adac0] Weighted P-Frames: Y:0.0% [libx264 @ 0x555c175adac0] ref P L0: 68.1% 0.0% 21.3% 10.6% [libx264 @ 0x555c175adac0] kb/s:83.18
Prediction
jd7h/xmem:c91f8f6cd0f08dbc43909529df1e5bd09d715f478cfd4c526f7bbd2d3a0c2eb2ModelIDxha6tqlbdb5ythydwg5sfqaigiStatusSucceededSourceWebHardwareA40 (Large)Total durationCreatedInput
{ "mask": "https://replicate.delivery/pbxt/JlFv6BH7eWJN9CA8l1EIDEBKmB26BLqlrFAqgqRZgZKsP7ww/kitten_masked_first_frame.png", "video": "https://replicate.delivery/pbxt/JlFv6WgBgiQcFKkQF0Vb1aSzUzGHEgnLFJrWUtaq3XMnfebc/kitten_short.mp4" }
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 jd7h/xmem using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
const output = await replicate.run( "jd7h/xmem:c91f8f6cd0f08dbc43909529df1e5bd09d715f478cfd4c526f7bbd2d3a0c2eb2", { input: { mask: "https://replicate.delivery/pbxt/JlFv6BH7eWJN9CA8l1EIDEBKmB26BLqlrFAqgqRZgZKsP7ww/kitten_masked_first_frame.png", video: "https://replicate.delivery/pbxt/JlFv6WgBgiQcFKkQF0Vb1aSzUzGHEgnLFJrWUtaq3XMnfebc/kitten_short.mp4" } } ); // 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 jd7h/xmem using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.
output = replicate.run( "jd7h/xmem:c91f8f6cd0f08dbc43909529df1e5bd09d715f478cfd4c526f7bbd2d3a0c2eb2", input={ "mask": "https://replicate.delivery/pbxt/JlFv6BH7eWJN9CA8l1EIDEBKmB26BLqlrFAqgqRZgZKsP7ww/kitten_masked_first_frame.png", "video": "https://replicate.delivery/pbxt/JlFv6WgBgiQcFKkQF0Vb1aSzUzGHEgnLFJrWUtaq3XMnfebc/kitten_short.mp4" } ) # To access the file URL: print(output.url()) #=> "http://example.com" # To write the file to disk: with open("my-image.png", "wb") as file: file.write(output.read())
To learn more, take a look at the guide on getting started with Python.
Run jd7h/xmem 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": "jd7h/xmem:c91f8f6cd0f08dbc43909529df1e5bd09d715f478cfd4c526f7bbd2d3a0c2eb2", "input": { "mask": "https://replicate.delivery/pbxt/JlFv6BH7eWJN9CA8l1EIDEBKmB26BLqlrFAqgqRZgZKsP7ww/kitten_masked_first_frame.png", "video": "https://replicate.delivery/pbxt/JlFv6WgBgiQcFKkQF0Vb1aSzUzGHEgnLFJrWUtaq3XMnfebc/kitten_short.mp4" } }' \ https://api.replicate.com/v1/predictions
To learn more, take a look at Replicate’s HTTP API reference docs.
Output
{ "completed_at": "2023-10-25T13:22:06.197459Z", "created_at": "2023-10-25T13:20:39.037850Z", "data_removed": false, "error": null, "id": "xha6tqlbdb5ythydwg5sfqaigi", "input": { "mask": "https://replicate.delivery/pbxt/JlFv6BH7eWJN9CA8l1EIDEBKmB26BLqlrFAqgqRZgZKsP7ww/kitten_masked_first_frame.png", "video": "https://replicate.delivery/pbxt/JlFv6WgBgiQcFKkQF0Vb1aSzUzGHEgnLFJrWUtaq3XMnfebc/kitten_short.mp4" }, "logs": "/root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\nwarnings.warn(\n/root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True).\nwarnings.warn(\n0% (0 of 201) | | Elapsed Time: 0:00:00 ETA: --:--:--\n0% (1 of 201) | | Elapsed Time: 0:00:02 ETA: 0:07:42\n0% (2 of 201) | | Elapsed Time: 0:00:03 ETA: 0:05:13\n2% (6 of 201) | | Elapsed Time: 0:00:03 ETA: 0:01:46\n3% (8 of 201) | | Elapsed Time: 0:00:03 ETA: 0:01:45\n5% (11 of 201) |# | Elapsed Time: 0:00:03 ETA: 0:00:59\n6% (13 of 201) |# | Elapsed Time: 0:00:03 ETA: 0:00:58\n7% (16 of 201) |# | Elapsed Time: 0:00:03 ETA: 0:00:41\n8% (18 of 201) |## | Elapsed Time: 0:00:03 ETA: 0:00:40\n10% (21 of 201) |## | Elapsed Time: 0:00:03 ETA: 0:00:31\n11% (23 of 201) |## | Elapsed Time: 0:00:03 ETA: 0:00:31\n12% (26 of 201) |## | Elapsed Time: 0:00:03 ETA: 0:00:26\n13% (28 of 201) |### | Elapsed Time: 0:00:03 ETA: 0:00:25\n15% (31 of 201) |### | Elapsed Time: 0:00:04 ETA: 0:00:22\n16% (34 of 201) |### | Elapsed Time: 0:00:04 ETA: 0:00:21\n17% (36 of 201) |#### | Elapsed Time: 0:00:04 ETA: 0:00:19\n19% (39 of 201) |#### | Elapsed Time: 0:00:04 ETA: 0:00:18\n20% (41 of 201) |#### | Elapsed Time: 0:00:04 ETA: 0:00:08\n21% (44 of 201) |##### | Elapsed Time: 0:00:04 ETA: 0:00:07\n22% (46 of 201) |##### | Elapsed Time: 0:00:04 ETA: 0:00:07\n24% (49 of 201) |##### | Elapsed Time: 0:00:04 ETA: 0:00:07\n25% (51 of 201) |##### | Elapsed Time: 0:00:04 ETA: 0:00:06\n26% (54 of 201) |###### | Elapsed Time: 0:00:04 ETA: 0:00:06\n27% (56 of 201) |###### | Elapsed Time: 0:00:04 ETA: 0:00:06\n29% (59 of 201) |###### | Elapsed Time: 0:00:04 ETA: 0:00:06\n30% (62 of 201) |####### | Elapsed Time: 0:00:04 ETA: 0:00:06\n31% (64 of 201) |####### | Elapsed Time: 0:00:05 ETA: 0:00:05\n33% (67 of 201) |####### | Elapsed Time: 0:00:05 ETA: 0:00:05\n34% (69 of 201) |####### | Elapsed Time: 0:00:05 ETA: 0:00:05\n35% (72 of 201) |######## | Elapsed Time: 0:00:05 ETA: 0:00:03\n36% (74 of 201) |######## | Elapsed Time: 0:00:05 ETA: 0:00:03\n38% (77 of 201) |######## | Elapsed Time: 0:00:05 ETA: 0:00:03\n39% (79 of 201) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03\n40% (82 of 201) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03\n41% (84 of 201) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03\n43% (87 of 201) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03\n44% (90 of 201) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03\n45% (92 of 201) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03\n47% (95 of 201) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03\n48% (97 of 201) |########### | Elapsed Time: 0:00:06 ETA: 0:00:03\n49% (100 of 201) |########## | Elapsed Time: 0:00:06 ETA: 0:00:03\n50% (102 of 201) |########### | Elapsed Time: 0:00:06 ETA: 0:00:02\n52% (105 of 201) |########### | Elapsed Time: 0:00:06 ETA: 0:00:02\n53% (107 of 201) |########### | Elapsed Time: 0:00:06 ETA: 0:00:02\n54% (110 of 201) |############ | Elapsed Time: 0:00:06 ETA: 0:00:02\n55% (112 of 201) |############ | Elapsed Time: 0:00:06 ETA: 0:00:02\n57% (115 of 201) |############ | Elapsed Time: 0:00:06 ETA: 0:00:02\n58% (118 of 201) |############ | Elapsed Time: 0:00:06 ETA: 0:00:02\n59% (120 of 201) |############# | Elapsed Time: 0:00:06 ETA: 0:00:02\n61% (123 of 201) |############# | Elapsed Time: 0:00:06 ETA: 0:00:02\n62% (125 of 201) |############# | Elapsed Time: 0:00:06 ETA: 0:00:02\n63% (128 of 201) |############## | Elapsed Time: 0:00:06 ETA: 0:00:02\n64% (130 of 201) |############## | Elapsed Time: 0:00:07 ETA: 0:00:02\n66% (133 of 201) |############## | Elapsed Time: 0:00:07 ETA: 0:00:02\n67% (135 of 201) |############## | Elapsed Time: 0:00:07 ETA: 0:00:02\n68% (138 of 201) |############### | Elapsed Time: 0:00:07 ETA: 0:00:01\n69% (140 of 201) |############### | Elapsed Time: 0:00:07 ETA: 0:00:01\n71% (143 of 201) |############### | Elapsed Time: 0:00:07 ETA: 0:00:01\n72% (146 of 201) |############### | Elapsed Time: 0:00:07 ETA: 0:00:01\n73% (148 of 201) |################ | Elapsed Time: 0:00:07 ETA: 0:00:01\n75% (151 of 201) |################ | Elapsed Time: 0:00:07 ETA: 0:00:01\n76% (153 of 201) |################ | Elapsed Time: 0:00:07 ETA: 0:00:01\n77% (156 of 201) |################# | Elapsed Time: 0:00:07 ETA: 0:00:01\n78% (158 of 201) |################# | Elapsed Time: 0:00:07 ETA: 0:00:01\n80% (161 of 201) |################# | Elapsed Time: 0:00:08 ETA: 0:00:01\n81% (163 of 201) |################# | Elapsed Time: 0:00:08 ETA: 0:00:01\n82% (166 of 201) |################## | Elapsed Time: 0:00:08 ETA: 0:00:01\n83% (168 of 201) |################## | Elapsed Time: 0:00:08 ETA: 0:00:01\n85% (171 of 201) |################## | Elapsed Time: 0:00:08 ETA: 0:00:00\n86% (174 of 201) |################### | Elapsed Time: 0:00:08 ETA: 0:00:00\n87% (176 of 201) |################### | Elapsed Time: 0:00:08 ETA: 0:00:00\n89% (179 of 201) |################### | Elapsed Time: 0:00:08 ETA: 0:00:00\n90% (181 of 201) |################### | Elapsed Time: 0:00:08 ETA: 0:00:00\n91% (184 of 201) |#################### | Elapsed Time: 0:00:08 ETA: 0:00:00\n92% (186 of 201) |#################### | Elapsed Time: 0:00:08 ETA: 0:00:00\n94% (189 of 201) |#################### | Elapsed Time: 0:00:08 ETA: 0:00:00\n95% (191 of 201) |#################### | Elapsed Time: 0:00:08 ETA: 0:00:00\n96% (194 of 201) |##################### | Elapsed Time: 0:00:09 ETA: 0:00:00\n97% (196 of 201) |##################### | Elapsed Time: 0:00:09 ETA: 0:00:00\n99% (199 of 201) |##################### | Elapsed Time: 0:00:09 ETA: 0:00:00\n100% (201 of 201) |######################| Elapsed Time: 0:00:09 Time: 0:00:09\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 './results/default_video/*.png':\nDuration: 00:00:08.38, start: 0.000000, bitrate: N/A\nStream #0:0: Video: png, gray(pc), 1280x720, 24 fps, 24 tbr, 24 tbn, 24 tbc\nStream mapping:\nStream #0:0 -> #0:0 (png (native) -> h264 (libx264))\nPress [q] to stop, [?] for help\n[libx264 @ 0x5594f244fb00] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2\n[libx264 @ 0x5594f244fb00] profile High 4:4:4 Predictive, level 3.1, 4:0:0, 8-bit\n[libx264 @ 0x5594f244fb00] 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=0 mixed_ref=1 me_range=16 chroma_me=0 trellis=0 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=0 chroma_qp_offset=0 threads=22 lookahead_threads=3 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc=cqp mbtree=0 qp=0\nOutput #0, mp4, to 'result.mp4':\nMetadata:\nencoder : Lavf58.76.100\nStream #0:0: Video: h264 (avc1 / 0x31637661), gray(pc, progressive), 1280x720, q=2-31, 24 fps, 12288 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= 201 fps=0.0 q=-1.0 Lsize= 115kB time=00:00:08.33 bitrate= 112.8kbits/s speed=32.8x\nvideo:113kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.421016%\n[libx264 @ 0x5594f244fb00] frame I:1 Avg QP: 0.00 size: 1048\n[libx264 @ 0x5594f244fb00] frame P:200 Avg QP: 0.00 size: 572\n[libx264 @ 0x5594f244fb00] mb I I16..4: 99.9% 0.0% 0.1%\n[libx264 @ 0x5594f244fb00] mb P I16..4: 0.9% 0.0% 0.0% P16..4: 1.1% 0.7% 0.1% 0.0% 0.0% skip:97.1%\n[libx264 @ 0x5594f244fb00] 8x8 transform intra:0.0% inter:6.7%\n[libx264 @ 0x5594f244fb00] coded y intra: 8.7% inter: 0.3%\n[libx264 @ 0x5594f244fb00] i16 v,h,dc,p: 92% 7% 1% 0%\n[libx264 @ 0x5594f244fb00] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 38% 38% 25% 0% 0% 0% 0% 0% 0%\n[libx264 @ 0x5594f244fb00] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 30% 25% 40% 3% 1% 1% 0% 0% 1%\n[libx264 @ 0x5594f244fb00] i8c dc,h,v,p: 100% 0% 0% 0%\n[libx264 @ 0x5594f244fb00] Weighted P-Frames: Y:0.0%\n[libx264 @ 0x5594f244fb00] ref P L0: 72.6% 0.0% 17.7% 9.7%\n[libx264 @ 0x5594f244fb00] kb/s:110.21", "metrics": { "predict_time": 17.126336, "total_time": 87.159609 }, "output": "https://pbxt.replicate.delivery/mZfayeYfnYTfwTzYhUgelUawveVYYxjzemjmsmHNSl51ehsxRA/result.mp4", "started_at": "2023-10-25T13:21:49.071123Z", "status": "succeeded", "urls": { "get": "https://api.replicate.com/v1/predictions/xha6tqlbdb5ythydwg5sfqaigi", "cancel": "https://api.replicate.com/v1/predictions/xha6tqlbdb5ythydwg5sfqaigi/cancel" }, "version": "c91f8f6cd0f08dbc43909529df1e5bd09d715f478cfd4c526f7bbd2d3a0c2eb2" }
Generated in/root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( /root/.pyenv/versions/3.11.6/lib/python3.11/site-packages/torchvision/transforms/functional.py:1603: UserWarning: The default value of the antialias parameter of all the resizing transforms (Resize(), RandomResizedCrop(), etc.) will change from None to True in v0.17, in order to be consistent across the PIL and Tensor backends. To suppress this warning, directly pass antialias=True (recommended, future default), antialias=None (current default, which means False for Tensors and True for PIL), or antialias=False (only works on Tensors - PIL will still use antialiasing). This also applies if you are using the inference transforms from the models weights: update the call to weights.transforms(antialias=True). warnings.warn( 0% (0 of 201) | | Elapsed Time: 0:00:00 ETA: --:--:-- 0% (1 of 201) | | Elapsed Time: 0:00:02 ETA: 0:07:42 0% (2 of 201) | | Elapsed Time: 0:00:03 ETA: 0:05:13 2% (6 of 201) | | Elapsed Time: 0:00:03 ETA: 0:01:46 3% (8 of 201) | | Elapsed Time: 0:00:03 ETA: 0:01:45 5% (11 of 201) |# | Elapsed Time: 0:00:03 ETA: 0:00:59 6% (13 of 201) |# | Elapsed Time: 0:00:03 ETA: 0:00:58 7% (16 of 201) |# | Elapsed Time: 0:00:03 ETA: 0:00:41 8% (18 of 201) |## | Elapsed Time: 0:00:03 ETA: 0:00:40 10% (21 of 201) |## | Elapsed Time: 0:00:03 ETA: 0:00:31 11% (23 of 201) |## | Elapsed Time: 0:00:03 ETA: 0:00:31 12% (26 of 201) |## | Elapsed Time: 0:00:03 ETA: 0:00:26 13% (28 of 201) |### | Elapsed Time: 0:00:03 ETA: 0:00:25 15% (31 of 201) |### | Elapsed Time: 0:00:04 ETA: 0:00:22 16% (34 of 201) |### | Elapsed Time: 0:00:04 ETA: 0:00:21 17% (36 of 201) |#### | Elapsed Time: 0:00:04 ETA: 0:00:19 19% (39 of 201) |#### | Elapsed Time: 0:00:04 ETA: 0:00:18 20% (41 of 201) |#### | Elapsed Time: 0:00:04 ETA: 0:00:08 21% (44 of 201) |##### | Elapsed Time: 0:00:04 ETA: 0:00:07 22% (46 of 201) |##### | Elapsed Time: 0:00:04 ETA: 0:00:07 24% (49 of 201) |##### | Elapsed Time: 0:00:04 ETA: 0:00:07 25% (51 of 201) |##### | Elapsed Time: 0:00:04 ETA: 0:00:06 26% (54 of 201) |###### | Elapsed Time: 0:00:04 ETA: 0:00:06 27% (56 of 201) |###### | Elapsed Time: 0:00:04 ETA: 0:00:06 29% (59 of 201) |###### | Elapsed Time: 0:00:04 ETA: 0:00:06 30% (62 of 201) |####### | Elapsed Time: 0:00:04 ETA: 0:00:06 31% (64 of 201) |####### | Elapsed Time: 0:00:05 ETA: 0:00:05 33% (67 of 201) |####### | Elapsed Time: 0:00:05 ETA: 0:00:05 34% (69 of 201) |####### | Elapsed Time: 0:00:05 ETA: 0:00:05 35% (72 of 201) |######## | Elapsed Time: 0:00:05 ETA: 0:00:03 36% (74 of 201) |######## | Elapsed Time: 0:00:05 ETA: 0:00:03 38% (77 of 201) |######## | Elapsed Time: 0:00:05 ETA: 0:00:03 39% (79 of 201) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03 40% (82 of 201) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03 41% (84 of 201) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03 43% (87 of 201) |######### | Elapsed Time: 0:00:05 ETA: 0:00:03 44% (90 of 201) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03 45% (92 of 201) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03 47% (95 of 201) |########## | Elapsed Time: 0:00:05 ETA: 0:00:03 48% (97 of 201) |########### | Elapsed Time: 0:00:06 ETA: 0:00:03 49% (100 of 201) |########## | Elapsed Time: 0:00:06 ETA: 0:00:03 50% (102 of 201) |########### | Elapsed Time: 0:00:06 ETA: 0:00:02 52% (105 of 201) |########### | Elapsed Time: 0:00:06 ETA: 0:00:02 53% (107 of 201) |########### | Elapsed Time: 0:00:06 ETA: 0:00:02 54% (110 of 201) |############ | Elapsed Time: 0:00:06 ETA: 0:00:02 55% (112 of 201) |############ | Elapsed Time: 0:00:06 ETA: 0:00:02 57% (115 of 201) |############ | Elapsed Time: 0:00:06 ETA: 0:00:02 58% (118 of 201) |############ | Elapsed Time: 0:00:06 ETA: 0:00:02 59% (120 of 201) |############# | Elapsed Time: 0:00:06 ETA: 0:00:02 61% (123 of 201) |############# | Elapsed Time: 0:00:06 ETA: 0:00:02 62% (125 of 201) |############# | Elapsed Time: 0:00:06 ETA: 0:00:02 63% (128 of 201) |############## | Elapsed Time: 0:00:06 ETA: 0:00:02 64% (130 of 201) |############## | Elapsed Time: 0:00:07 ETA: 0:00:02 66% (133 of 201) |############## | Elapsed Time: 0:00:07 ETA: 0:00:02 67% (135 of 201) |############## | Elapsed Time: 0:00:07 ETA: 0:00:02 68% (138 of 201) |############### | Elapsed Time: 0:00:07 ETA: 0:00:01 69% (140 of 201) |############### | Elapsed Time: 0:00:07 ETA: 0:00:01 71% (143 of 201) |############### | Elapsed Time: 0:00:07 ETA: 0:00:01 72% (146 of 201) |############### | Elapsed Time: 0:00:07 ETA: 0:00:01 73% (148 of 201) |################ | Elapsed Time: 0:00:07 ETA: 0:00:01 75% (151 of 201) |################ | Elapsed Time: 0:00:07 ETA: 0:00:01 76% (153 of 201) |################ | Elapsed Time: 0:00:07 ETA: 0:00:01 77% (156 of 201) |################# | Elapsed Time: 0:00:07 ETA: 0:00:01 78% (158 of 201) |################# | Elapsed Time: 0:00:07 ETA: 0:00:01 80% (161 of 201) |################# | Elapsed Time: 0:00:08 ETA: 0:00:01 81% (163 of 201) |################# | Elapsed Time: 0:00:08 ETA: 0:00:01 82% (166 of 201) |################## | Elapsed Time: 0:00:08 ETA: 0:00:01 83% (168 of 201) |################## | Elapsed Time: 0:00:08 ETA: 0:00:01 85% (171 of 201) |################## | Elapsed Time: 0:00:08 ETA: 0:00:00 86% (174 of 201) |################### | Elapsed Time: 0:00:08 ETA: 0:00:00 87% (176 of 201) |################### | Elapsed Time: 0:00:08 ETA: 0:00:00 89% (179 of 201) |################### | Elapsed Time: 0:00:08 ETA: 0:00:00 90% (181 of 201) |################### | Elapsed Time: 0:00:08 ETA: 0:00:00 91% (184 of 201) |#################### | Elapsed Time: 0:00:08 ETA: 0:00:00 92% (186 of 201) |#################### | Elapsed Time: 0:00:08 ETA: 0:00:00 94% (189 of 201) |#################### | Elapsed Time: 0:00:08 ETA: 0:00:00 95% (191 of 201) |#################### | Elapsed Time: 0:00:08 ETA: 0:00:00 96% (194 of 201) |##################### | Elapsed Time: 0:00:09 ETA: 0:00:00 97% (196 of 201) |##################### | Elapsed Time: 0:00:09 ETA: 0:00:00 99% (199 of 201) |##################### | Elapsed Time: 0:00:09 ETA: 0:00:00 100% (201 of 201) |######################| Elapsed Time: 0:00:09 Time: 0:00:09 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 './results/default_video/*.png': Duration: 00:00:08.38, start: 0.000000, bitrate: N/A Stream #0:0: Video: png, gray(pc), 1280x720, 24 fps, 24 tbr, 24 tbn, 24 tbc Stream mapping: Stream #0:0 -> #0:0 (png (native) -> h264 (libx264)) Press [q] to stop, [?] for help [libx264 @ 0x5594f244fb00] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2 [libx264 @ 0x5594f244fb00] profile High 4:4:4 Predictive, level 3.1, 4:0:0, 8-bit [libx264 @ 0x5594f244fb00] 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=0 mixed_ref=1 me_range=16 chroma_me=0 trellis=0 8x8dct=1 cqm=0 deadzone=21,11 fast_pskip=0 chroma_qp_offset=0 threads=22 lookahead_threads=3 sliced_threads=0 nr=0 decimate=1 interlaced=0 bluray_compat=0 constrained_intra=0 bframes=0 weightp=2 keyint=250 keyint_min=24 scenecut=40 intra_refresh=0 rc=cqp mbtree=0 qp=0 Output #0, mp4, to 'result.mp4': Metadata: encoder : Lavf58.76.100 Stream #0:0: Video: h264 (avc1 / 0x31637661), gray(pc, progressive), 1280x720, q=2-31, 24 fps, 12288 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= 201 fps=0.0 q=-1.0 Lsize= 115kB time=00:00:08.33 bitrate= 112.8kbits/s speed=32.8x video:113kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 1.421016% [libx264 @ 0x5594f244fb00] frame I:1 Avg QP: 0.00 size: 1048 [libx264 @ 0x5594f244fb00] frame P:200 Avg QP: 0.00 size: 572 [libx264 @ 0x5594f244fb00] mb I I16..4: 99.9% 0.0% 0.1% [libx264 @ 0x5594f244fb00] mb P I16..4: 0.9% 0.0% 0.0% P16..4: 1.1% 0.7% 0.1% 0.0% 0.0% skip:97.1% [libx264 @ 0x5594f244fb00] 8x8 transform intra:0.0% inter:6.7% [libx264 @ 0x5594f244fb00] coded y intra: 8.7% inter: 0.3% [libx264 @ 0x5594f244fb00] i16 v,h,dc,p: 92% 7% 1% 0% [libx264 @ 0x5594f244fb00] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 38% 38% 25% 0% 0% 0% 0% 0% 0% [libx264 @ 0x5594f244fb00] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 30% 25% 40% 3% 1% 1% 0% 0% 1% [libx264 @ 0x5594f244fb00] i8c dc,h,v,p: 100% 0% 0% 0% [libx264 @ 0x5594f244fb00] Weighted P-Frames: Y:0.0% [libx264 @ 0x5594f244fb00] ref P L0: 72.6% 0.0% 17.7% 9.7% [libx264 @ 0x5594f244fb00] kb/s:110.21
Want to make some of these yourself?
Run this model