fofr/lcm-animation 🔢🖼️📝✓ → 🖼️

▶️ 30.7K runs 📅 Oct 2023 ⚙️ Cog 0.8.6 🔗 GitHub ⚖️ License

controlnet image-to-video text-to-video

About

Fast animation using a latent consistency model

Example Output

Output

Performance Metrics

8.80s Prediction Time

83.92s Total Time

All Input Parameters

{
  "width": 512,
  "height": 512,
  "end_prompt": "Self-portrait watercolour, a beautiful cyborg with purple hair, 8k",
  "iterations": 24,
  "start_prompt": "Self-portrait oil painting, a beautiful cyborg with golden hair, 8k",
  "return_frames": false,
  "guidance_scale": 8,
  "zoom_increment": 0,
  "prompt_strength": 0.3,
  "num_inference_steps": 2
}

Input Parameters

seed Type: integer: Random seed. Leave blank to randomize the seed
image Type: string: Starting image if not using a prompt
width Type: integerDefault: 512: Width of output. Lower if out of memory
height Type: integerDefault: 512: Height of output. Lower if out of memory
end_prompt Type: stringDefault: Self-portrait watercolour, a beautiful cyborg with purple hair, 8k: Prompt to animate towards
iterations Type: integerDefault: 12: Number of times to repeat the img2img pipeline
start_prompt Type: stringDefault: Self-portrait oil painting, a beautiful cyborg with golden hair, 8k: Prompt to start with, if not using an image
return_frames Type: booleanDefault: false: Return a tar file with all the frames alongside the video
guidance_scale Type: numberDefault: 8Range: 1 - 20: Scale for classifier-free guidance
zoom_increment Type: integerDefault: 0Range: 0 - 4: Zoom increment percentage for each frame
prompt_strength Type: numberDefault: 0.2Range: 0 - 1: Prompt strength when using img2img. 1.0 corresponds to full destruction of information in image
canny_low_threshold Type: numberDefault: 100Range: 1 - 255: Canny low threshold
num_inference_steps Type: integerDefault: 8Range: 1 - 50: Number of denoising steps. Recommend 1 to 8 steps.
canny_high_threshold Type: numberDefault: 200Range: 1 - 255: Canny high threshold
control_guidance_end Type: numberDefault: 1Range: 0 - 1: Controlnet end
use_canny_control_net Type: booleanDefault: true: Use canny edge detection to guide animation
control_guidance_start Type: numberDefault: 0Range: 0 - 1: Controlnet start
controlnet_conditioning_scale Type: numberDefault: 2Range: 0.1 - 4: Controlnet conditioning scale

Output Schema

Output

Type: array • Items Type: string • Items Format: uri

Example Execution Logs

Using seed: 21366
txt2img mode
  0%|          | 0/8 [00:00<?, ?it/s]
 12%|█▎        | 1/8 [00:00<00:01,  4.53it/s]
 62%|██████▎   | 5/8 [00:00<00:00, 17.16it/s]
100%|██████████| 8/8 [00:00<00:00, 18.66it/s]
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 32.36it/s]
img2img iteration 1
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.40it/s]
img2img iteration 2
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.01it/s]
img2img iteration 3
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.28it/s]
img2img iteration 4
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 31.30it/s]
img2img iteration 5
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.02it/s]
img2img iteration 6
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.13it/s]
img2img iteration 7
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.41it/s]
img2img iteration 8
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 32.49it/s]
img2img iteration 9
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 32.98it/s]
img2img iteration 10
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 32.79it/s]
img2img iteration 11
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.32it/s]
img2img iteration 12
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.08it/s]
img2img iteration 13
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.23it/s]
img2img iteration 14
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.04it/s]
img2img iteration 15
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 32.96it/s]
img2img iteration 16
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.03it/s]
img2img iteration 17
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.03it/s]
img2img iteration 18
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.01it/s]
img2img iteration 19
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.06it/s]
img2img iteration 20
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.20it/s]
img2img iteration 21
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.20it/s]
img2img iteration 22
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.18it/s]
img2img iteration 23
  0%|          | 0/2 [00:00<?, ?it/s]
100%|██████████| 2/2 [00:00<00:00, 33.38it/s]
ffmpeg version 4.4.2-0ubuntu0.22.04.1 Copyright (c) 2000-2021 the FFmpeg developers
built with gcc 11 (Ubuntu 11.2.0-19ubuntu1)
configuration: --prefix=/usr --extra-version=0ubuntu0.22.04.1 --toolchain=hardened --libdir=/usr/lib/x86_64-linux-gnu --incdir=/usr/include/x86_64-linux-gnu --arch=amd64 --enable-gpl --disable-stripping --enable-gnutls --enable-ladspa --enable-libaom --enable-libass --enable-libbluray --enable-libbs2b --enable-libcaca --enable-libcdio --enable-libcodec2 --enable-libdav1d --enable-libflite --enable-libfontconfig --enable-libfreetype --enable-libfribidi --enable-libgme --enable-libgsm --enable-libjack --enable-libmp3lame --enable-libmysofa --enable-libopenjpeg --enable-libopenmpt --enable-libopus --enable-libpulse --enable-librabbitmq --enable-librubberband --enable-libshine --enable-libsnappy --enable-libsoxr --enable-libspeex --enable-libsrt --enable-libssh --enable-libtheora --enable-libtwolame --enable-libvidstab --enable-libvorbis --enable-libvpx --enable-libwebp --enable-libx265 --enable-libxml2 --enable-libxvid --enable-libzimg --enable-libzmq --enable-libzvbi --enable-lv2 --enable-omx --enable-openal --enable-opencl --enable-opengl --enable-sdl2 --enable-pocketsphinx --enable-librsvg --enable-libmfx --enable-libdc1394 --enable-libdrm --enable-libiec61883 --enable-chromaprint --enable-frei0r --enable-libx264 --enable-shared
libavutil      56. 70.100 / 56. 70.100
libavcodec     58.134.100 / 58.134.100
libavformat    58. 76.100 / 58. 76.100
libavdevice    58. 13.100 / 58. 13.100
libavfilter     7.110.100 /  7.110.100
libswscale      5.  9.100 /  5.  9.100
libswresample   3.  9.100 /  3.  9.100
libpostproc    55.  9.100 / 55.  9.100
Input #0, image2, from '/tmp/out-*.png':
Duration: 00:00:02.00, start: 0.000000, bitrate: N/A
Stream #0:0: Video: png, rgb24(pc), 512x512, 12 fps, 12 tbr, 12 tbn, 12 tbc
Stream mapping:
Stream #0:0 -> #0:0 (png (native) -> h264 (libx264))
Press [q] to stop, [?] for help
[libx264 @ 0x557015088c80] using cpu capabilities: MMX2 SSE2Fast SSSE3 SSE4.2 AVX FMA3 BMI2 AVX2
[libx264 @ 0x557015088c80] profile High, level 2.2, 4:2:0, 8-bit
[libx264 @ 0x557015088c80] 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=12 scenecut=40 intra_refresh=0 rc_lookahead=40 rc=crf mbtree=1 crf=17.0 qcomp=0.60 qpmin=0 qpmax=69 qpstep=4 ip_ratio=1.40 aq=1:1.00
Output #0, mp4, to '/tmp/output_video.mp4':
Metadata:
encoder         : Lavf58.76.100
Stream #0:0: Video: h264 (avc1 / 0x31637661), yuv420p(tv, progressive), 512x512, q=2-31, 12 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=   24 fps=0.0 q=-1.0 Lsize=     589kB time=00:00:01.75 bitrate=2757.7kbits/s speed=8.26x
video:588kB audio:0kB subtitle:0kB other streams:0kB global headers:0kB muxing overhead: 0.189158%
[libx264 @ 0x557015088c80] frame I:1     Avg QP:17.80  size: 39194
[libx264 @ 0x557015088c80] frame P:6     Avg QP:17.38  size: 25997
[libx264 @ 0x557015088c80] frame B:17    Avg QP:17.91  size: 23899
[libx264 @ 0x557015088c80] consecutive B-frames:  4.2%  0.0% 12.5% 83.3%
[libx264 @ 0x557015088c80] mb I  I16..4:  5.8% 47.5% 46.8%
[libx264 @ 0x557015088c80] mb P  I16..4:  5.6% 40.0% 27.8%  P16..4: 11.2% 10.9%  4.4%  0.0%  0.0%    skip: 0.1%
[libx264 @ 0x557015088c80] mb B  I16..4:  2.7% 20.8% 18.9%  B16..8: 20.6% 20.2%  7.7%  direct: 8.1%  skip: 1.0%  L0:41.5% L1:38.8% BI:19.7%
[libx264 @ 0x557015088c80] 8x8 transform intra:50.9% inter:64.3%
[libx264 @ 0x557015088c80] coded y,uvDC,uvAC intra: 87.4% 73.0% 42.9% inter: 75.8% 85.4% 3.6%
[libx264 @ 0x557015088c80] i16 v,h,dc,p: 32% 15%  4% 49%
[libx264 @ 0x557015088c80] i8 v,h,dc,ddl,ddr,vr,hd,vl,hu: 22%  8% 18%  7%  9% 13%  6% 11%  6%
[libx264 @ 0x557015088c80] i4 v,h,dc,ddl,ddr,vr,hd,vl,hu: 19%  9% 12% 10% 12% 14%  8% 10%  6%
[libx264 @ 0x557015088c80] i8c dc,h,v,p: 57% 13% 23%  8%
[libx264 @ 0x557015088c80] Weighted P-Frames: Y:50.0% UV:50.0%
[libx264 @ 0x557015088c80] ref P L0: 52.0% 10.5% 22.6% 12.0%  2.9%
[libx264 @ 0x557015088c80] ref B L0: 77.0% 18.6%  4.4%
[libx264 @ 0x557015088c80] ref B L1: 89.1% 10.9%
[libx264 @ 0x557015088c80] kb/s:2405.81

Version Details

Version ID: 5c69907b2c7395f9d83dfed08015aed48fe92ee197c029ace377b357cf7ca029
Version Created: November 20, 2023

Run on Replicate →