cdc14b74a5
* support ffmpeg stream for inference_realesrgan_video * fix code format Co-authored-by: yanzewu <yanzewu@tencent.com>
4.8 KiB
4.8 KiB
Anime Video Models
✅ We add small models that are optimized for anime videos :-)
More comparisons can be found in anime_comparisons.md
| Models | Scale | Description |
|---|---|---|
| realesr-animevideov3 | X4 1 | Anime video model with XS size |
Note:
1 This model can also be used for X1, X2, X3.
The following are some demos (best view in the full screen mode).
How to Use
PyTorch Inference
# download model
wget https://github.com/xinntao/Real-ESRGAN/releases/download/v0.2.5.0/realesr-animevideov3.pth -P realesrgan/weights
# inference
python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --stream
Usage:
--stream with this option, the enhanced frames are sent directly to a ffmpeg stream,
avoiding storing large (usually tens of GB) intermediate results.
NCNN Executable File
Step 1: Use ffmpeg to extract frames from video
ffmpeg -i onepiece_demo.mp4 -qscale:v 1 -qmin 1 -qmax 1 -vsync 0 tmp_frames/frame%08d.png
- Remember to create the folder
tmp_framesahead
Step 2: Inference with Real-ESRGAN executable file
-
Download the latest portable Windows / Linux / MacOS executable files for Intel/AMD/Nvidia GPU
-
Taking the Windows as example, run:
./realesrgan-ncnn-vulkan.exe -i tmp_frames -o out_frames -n realesr-animevideov3 -s 2 -f jpg- Remember to create the folder
out_framesahead
- Remember to create the folder
Step 3: Merge the enhanced frames back into a video
-
First obtain fps from input videos by
ffmpeg -i onepiece_demo.mp4Usage: -i input video pathYou will get the output similar to the following screenshot.
-
Merge frames
ffmpeg -r 23.98 -i out_frames/frame%08d.jpg -c:v libx264 -r 23.98 -pix_fmt yuv420p output.mp4Usage: -i input video path -c:v video encoder (usually we use libx264) -r fps, remember to modify it to meet your needs -pix_fmt pixel format in videoIf you also want to copy audio from the input videos, run:
ffmpeg -r 23.98 -i out_frames/frame%08d.jpg -i onepiece_demo.mp4 -map 0:v:0 -map 1:a:0 -c:a copy -c:v libx264 -r 23.98 -pix_fmt yuv420p output_w_audio.mp4Usage: -i input video path, here we use two input streams -c:v video encoder (usually we use libx264) -r fps, remember to modify it to meet your needs -pix_fmt pixel format in video
More Demos
-
Input video for One Piece:
-
Out video for One Piece
More comparisons