sunfjun/stable-video-diffusion 🔢🖼️❓ → 🖼️

▶️ 102.0K runs 📅 Mar 2024 ⚙️ Cog 0.9.5
image-to-video

About

Example Output

Output

Performance Metrics

31.78s Prediction Time
184.23s Total Time
All Input Parameters
{
  "cond_aug": 0.02,
  "decoding_t": 14,
  "input_image": "https://replicate.delivery/pbxt/KcAKZ1wW2WJmjM0Xov9I0VCvjNwCmau64PkNnJUVVWk67Q6d/2261702010499_.pic.jpg",
  "video_length": "14_frames_with_svd",
  "sizing_strategy": "maintain_aspect_ratio",
  "motion_bucket_id": 127,
  "frames_per_second": 6
}
Input Parameters
seed Type: integer
Random seed. Leave blank to randomize the seed
cond_aug Type: numberDefault: 0.02
Amount of noise to add to input image
decoding_t Type: integerDefault: 14
Number of frames to decode at a time
input_image (required) Type: string
Input image
video_length Default: 14_frames_with_svd
Use svd to generate 14 frames or svd_xt for 25 frames
sizing_strategy Default: maintain_aspect_ratio
Decide how to resize the input image
motion_bucket_id Type: integerDefault: 127Range: 1 - 255
Increase overall motion in the generated video
frames_per_second Type: integerDefault: 6Range: 5 - 30
Frames per second
Output Schema

Output

Type: stringFormat: uri

Example Execution Logs
Using seed: 31401
Resizing but keeping aspect ratio
Using dimensions 576x576
Set consts
Loaded model
WARNING: The conditioning frame you provided is not 576x1024. This leads to suboptimal performance as model was only trained on 576x1024. Consider increasing `cond_aug`.
##############################  Sampling setting  ##############################
Sampler: EulerEDMSampler
Discretization: EDMDiscretization
Guider: LinearPredictionGuider
Sampling with EulerEDMSampler for 26 steps:   0%|          | 0/26 [00:00<?, ?it/s]/root/.pyenv/versions/3.10.14/lib/python3.10/site-packages/torch/utils/checkpoint.py:31: UserWarning: None of the inputs have requires_grad=True. Gradients will be None
warnings.warn("None of the inputs have requires_grad=True. Gradients will be None")
Sampling with EulerEDMSampler for 26 steps:   4%|▍         | 1/26 [00:01<00:25,  1.03s/it]
Sampling with EulerEDMSampler for 26 steps:   8%|▊         | 2/26 [00:01<00:23,  1.02it/s]
Sampling with EulerEDMSampler for 26 steps:  12%|█▏        | 3/26 [00:02<00:22,  1.01it/s]
Sampling with EulerEDMSampler for 26 steps:  15%|█▌        | 4/26 [00:03<00:21,  1.00it/s]
Sampling with EulerEDMSampler for 26 steps:  19%|█▉        | 5/26 [00:04<00:20,  1.00it/s]
Sampling with EulerEDMSampler for 26 steps:  23%|██▎       | 6/26 [00:05<00:20,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  27%|██▋       | 7/26 [00:06<00:19,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  31%|███       | 8/26 [00:08<00:18,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  35%|███▍      | 9/26 [00:09<00:17,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  38%|███▊      | 10/26 [00:10<00:16,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  42%|████▏     | 11/26 [00:11<00:15,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  46%|████▌     | 12/26 [00:12<00:14,  1.01s/it]
Sampling with EulerEDMSampler for 26 steps:  50%|█████     | 13/26 [00:13<00:13,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  54%|█████▍    | 14/26 [00:14<00:12,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  58%|█████▊    | 15/26 [00:15<00:11,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  62%|██████▏   | 16/26 [00:16<00:10,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  65%|██████▌   | 17/26 [00:17<00:09,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  69%|██████▉   | 18/26 [00:18<00:08,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  73%|███████▎  | 19/26 [00:19<00:07,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  77%|███████▋  | 20/26 [00:20<00:06,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  81%|████████  | 21/26 [00:21<00:05,  1.01s/it]
Sampling with EulerEDMSampler for 26 steps:  85%|████████▍ | 22/26 [00:22<00:04,  1.00s/it]
Sampling with EulerEDMSampler for 26 steps:  88%|████████▊ | 23/26 [00:23<00:03,  1.01s/it]
Sampling with EulerEDMSampler for 26 steps:  92%|█████████▏| 24/26 [00:24<00:02,  1.01s/it]
Sampling with EulerEDMSampler for 26 steps:  96%|█████████▌| 25/26 [00:25<00:01,  1.01s/it]
Sampling with EulerEDMSampler for 26 steps:  96%|█████████▌| 25/26 [00:25<00:01,  1.00s/it]
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil      56. 70.100 / 56. 70.100
libavcodec     58.134.100 / 58.134.100
libavformat    58. 76.100 / 58. 76.100
libavdevice    58. 13.100 / 58. 13.100
libavfilter     7.110.100 /  7.110.100
libswscale      5.  9.100 /  5.  9.100
libswresample   3.  9.100 /  3.  9.100
libpostproc    55.  9.100 / 55.  9.100
Input #0, image2, from 'output//frame_%06d.png':
Duration: 00:00:00.56, start: 0.000000, bitrate: N/A
Stream #0:0: Video: png, rgb24(pc), 576x576, 25 fps, 25 tbr, 25 tbn, 25 tbc
Stream mapping:
Stream #0:0 -> #0:0 (png (native) -> h264 (libx264))
Press [q] to stop, [?] for help
[libx264 @ 0x55b8f5378a80] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2
[libx264 @ 0x55b8f5378a80] profile High, level 2.2, 4:2:0, 8-bit
[libx264 @ 0x55b8f5378a80] 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=7 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 'output/000000.mp4':
Metadata:
encoder         : Lavf58.76.100
Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 576x576, q=2-31, 7 fps, 14336 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=   14 fps=0.0 q=-1.0 Lsize=     241kB time=00:00:01.57 bitrate=1255.4kbits/s speed=15.1x
video:240kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.418609%
[libx264 @ 0x55b8f5378a80] frame I:1     Avg QP:19.60  size: 18557
[libx264 @ 0x55b8f5378a80] frame P:4     Avg QP:20.37  size: 19512
[libx264 @ 0x55b8f5378a80] frame B:9     Avg QP:22.02  size: 16476
[libx264 @ 0x55b8f5378a80] consecutive B-frames: 14.3%  0.0%  0.0% 85.7%
[libx264 @ 0x55b8f5378a80] mb I  I16..4: 25.2% 41.3% 33.6%
[libx264 @ 0x55b8f5378a80] mb P  I16..4: 11.2% 11.6% 24.8%  P16..4: 17.1%  9.1%  6.9%  0.0%  0.0%    skip:19.2%
[libx264 @ 0x55b8f5378a80] mb B  I16..4:  5.3%  4.3% 13.7%  B16..8: 23.2% 13.8%  5.5%  direct: 6.9%  skip:27.3%  L0:46.2% L1:42.5% BI:11.4%
[libx264 @ 0x55b8f5378a80] 8x8 transform intra:25.3% inter:46.8%
[libx264 @ 0x55b8f5378a80] coded y,uvDC,uvAC intra: 60.4% 64.0% 49.1% inter: 26.9% 27.9% 14.8%
[libx264 @ 0x55b8f5378a80] i16 v,h,dc,p: 57% 23% 13%  7%
[libx264 @ 0x55b8f5378a80] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 40% 12% 22%  4%  5%  5%  3%  4%  4%
[libx264 @ 0x55b8f5378a80] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 31% 14% 21%  6%  4%  7%  5%  7%  5%
[libx264 @ 0x55b8f5378a80] i8c dc,h,v,p: 58% 14% 21%  7%
[libx264 @ 0x55b8f5378a80] Weighted P-Frames: Y:0.0% UV:0.0%
[libx264 @ 0x55b8f5378a80] ref P L0: 62.0%  7.1% 21.6%  9.3%
[libx264 @ 0x55b8f5378a80] ref B L0: 83.6% 14.4%  2.0%
[libx264 @ 0x55b8f5378a80] ref B L1: 94.1%  5.9%
[libx264 @ 0x55b8f5378a80] kb/s:979.54
Version Details
Version ID
d68b6e09eedbac7a49e3d8644999d93579c386a083768235cabca88796d70d82
Version Created
March 22, 2024
Run on Replicate →