anime_video_model.md

Anime Video Models

✅ We add small models that are optimized for anime videos :-)
More comparisons can be found in anime_comparisons.md

• How to Use
• PyTorch Inference
• ncnn Executable File
  • Step 1: Use ffmpeg to extract frames from video
  • Step 2: Inference with Real-ESRGAN executable file
  • Step 3: Merge the enhanced frames back into a video
• More Demos

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).

naruto_X2_compare.MP4

The.Monkey.King_X2_compare.MP4

Fate.stay.night.UBW.X2.Compare.MP4

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
# single gpu and single process inference
CUDA_VISIBLE_DEVICES=0 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2
# single gpu and multi process inference (you can use multi-processing to improve GPU utilization)
CUDA_VISIBLE_DEVICES=0 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --num_process_per_gpu 2
# multi gpu and multi process inference
CUDA_VISIBLE_DEVICES=0,1,2,3 python inference_realesrgan_video.py -i inputs/video/onepiece_demo.mp4 -n realesr-animevideov3 -s 2 --suffix outx2 --num_process_per_gpu 2

Usage:
--num_process_per_gpu    The total number of process is num_gpu * num_process_per_gpu. The bottleneck of
                         the program lies on the IO, so the GPUs are usually not fully utilized. To alleviate
                         this issue, you can use multi-processing by setting this parameter. As long as it
                         does not exceed the CUDA memory
--extract_frame_first    If you encounter ffmpeg error when using multi-processing, you can turn this option on.

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_frames ahead

Step 2: Inference with Real-ESRGAN executable file

1. Download the latest portable Windows / Linux / MacOS executable files for Intel/AMD/Nvidia GPU

2. 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_frames ahead

Step 3: Merge the enhanced frames back into a video

1. First obtain fps from input videos by

   ffmpeg -i onepiece_demo.mp4

   Usage:
   -i                   input video path

   You will get the output similar to the following screenshot.

   

2. Merge frames

   ffmpeg -r 23.98 -i out_frames/frame%08d.jpg -c:v libx264 -r 23.98 -pix_fmt yuv420p output.mp4

   Usage:
   -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 video

   If 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.mp4

   Usage:
   -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:

  onepiece_demo.mp4

• Out video for One Piece

  onepiece_demo_outx4.mp4

More comparisons

The.Legend.Of.Nezha_X4_compare.MP4