李云龙二次元风格化!打滚卖萌,使用了animeGANv2进行了视频的风格迁移

Overview

李云龙二次元风格化!一键star、fork,你也可以生成这样的团长!

打滚卖萌求star求fork!

0.效果展示

1.模型简介

1.1AnimeGANv2

本文使用了animeGANv2进行了视频的风格迁移。
animeGANv2,顾名思义,是其前作AnimeGAN的改进版,改进方向主要在以下4点:

  • 解决了生成的图像中的高频伪影问题。
  • 它易于训练,并能直接达到论文所述的效果。
  • 进一步减少生成器网络的参数数量。(现在生成器大小 8.17Mb)
  • 尽可能多地使用来自BD电影的新的高质量的风格数据。
    效果图参考:
    animeGANv2
    本文则是使用了paddlepaddle预训练好的animeGANv2模型对李云龙名场面视频进行了风格化迁移,详情请看下文分解。

2.实现思路

flow

3.素材准备

首先要找到自己要操作的视频素材,将视频的音频单独提取出来备用
我自己找的资源放在了codes/videos/liyunlong文件夹下,是李云龙名场面:
你咋不敢跟旅长干一架呢!→旅长我给你跪下了 名场面

4.代码实操:

话不多说,首先是环境的基本配置

  • 安装基本环境
!pip install -r codes/PaddleGAN-develop/requirements.txt
  • 导入基本环境
import paddle 
import os 
import sys 
sys.path.insert(0,'codes/PaddleGAN-develop')
from ppgan.apps import AnimeGANPredictor

5.GAN它!

友情提示:此处最好使用GPU环境,cpu推理属实是有点点慢
进行模型的推理:

使用paddlepaddle预训练好的animeGANv2模型对视频进行风格迁移:
from ppgan.apps import AnimeGANPredictor
import cv2

predictor = AnimeGANPredictor('',None,)
video_src = 'codes/videos/liyunlong/格式工厂混流 亮剑-03+亮剑-03+亮剑-04 00_00_23-.mp4'
video_ = cv2.VideoCapture(video_src)
video_name_ = os.path.basename(video_src)
total_frames = video_.get(cv2.CAP_PROP_FRAME_COUNT)
fps_ = video_.get(cv2.CAP_PROP_FPS)
print("video {}, fps:{}, total frames:{}...".format(video_name_, fps_, total_frames))
frame_count_ = 0
save_per_frames = 1
dst_dir = 'codes/videos/liyunlong/'
out_video = cv2.VideoWriter('{}/hayao_{}'.format(dst_dir, video_name_),
                                cv2.VideoWriter_fourcc(*'DIVX'), int(fps_),
                                (int(video_.get(3)), int(video_.get(4))))
print('now begin...')
while True:
    ret_, frame_ = video_.read()
    if not ret_:  # or len(fps_list_) == 0:
        print('end of video...')
        break
    result_frame = predictor.anime_image_only(frame_)
    if frame_count_ % save_per_frames == 0:
        out_video.write(result_frame)
    frame_count_ = frame_count_ + 1
    if frame_count_ % 100 == 0:
        print("{}/{} processed...".format(frame_count_, int(total_frames)), flush=False)

6.最终视频

合成最终所需要的视频:

# 合并生成的视频和之前分离的音频:
!ffmpeg -i codes/videos/liyunlong/hayao_格式工厂混流 亮剑-03+亮剑-03+亮剑-04 00_00_23-.mp4 -i codes/videos/liyunlong/音频1.aac -c:v copy -c:a aac -strict experimental codes/videos/liyunlong/李云龙二次元化.mp4

这样就大功告成啦~~~
你可以在此基础上:

  • 更换你喜欢的视频
  • 更换其他paddle预训练好的模型
  • 甚至可以尝试自己动手训练定制化的模型!

打滚卖萌求star、fork!

PaddleGAN 的基础上做了些微小的改动,鸣谢.

Owner
oukohou
Hello there.
oukohou
DP-CL(Continual Learning with Differential Privacy)

DP-CL(Continual Learning with Differential Privacy) This is the official implementation of the Continual Learning with Differential Privacy. If you us

Phung Lai 3 Nov 04, 2022
The source code of the ICCV2021 paper "PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering"

The source code of the ICCV2021 paper "PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering"

Ren Yurui 261 Jan 09, 2023
68 keypoint annotations for COFW test data

68 keypoint annotations for COFW test data This repository contains manually annotated 68 keypoints for COFW test data (original annotation of CFOW da

31 Dec 06, 2022
Code implementation of "Sparsity Probe: Analysis tool for Deep Learning Models"

Sparsity Probe: Analysis tool for Deep Learning Models This repository is a limited implementation of Sparsity Probe: Analysis tool for Deep Learning

3 Jun 09, 2021
PyTorch code for 'Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning'

Efficient Single Image Super-Resolution Using Dual Path Connections with Multiple Scale Learning This repository is for EMSRDPN introduced in the foll

7 Feb 10, 2022
Deep Learning ❤️ OneFlow

Deep Learning with OneFlow made easy 🚀 ! Carefree? carefree-learn aims to provide CAREFREE usages for both users and developers. User Side Computer V

21 Oct 27, 2022
Activity image-based video retrieval

Cross-modal-retrieval Our approach is focus on Activity Image-to-Video Retrieval (AIVR) task. The compared methods are state-of-the-art single modalit

BCMI 75 Oct 21, 2021
Python script to download the celebA-HQ dataset from google drive

download-celebA-HQ Python script to download and create the celebA-HQ dataset. WARNING from the author. I believe this script is broken since a few mo

133 Dec 21, 2022
Moiré Attack (MA): A New Potential Risk of Screen Photos [NeurIPS 2021]

Moiré Attack (MA): A New Potential Risk of Screen Photos [NeurIPS 2021] This repository is the official implementation of Moiré Attack (MA): A New Pot

Dantong Niu 22 Dec 24, 2022
ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi-Object Segmentation

ClevrTex This repository contains dataset generation code for ClevrTex benchmark from paper: ClevrTex: A Texture-Rich Benchmark for Unsupervised Multi

Laurynas Karazija 26 Dec 21, 2022
Code and data for ACL2021 paper Cross-Lingual Abstractive Summarization with Limited Parallel Resources.

Multi-Task Framework for Cross-Lingual Abstractive Summarization (MCLAS) The code for ACL2021 paper Cross-Lingual Abstractive Summarization with Limit

Yu Bai 43 Nov 07, 2022
Deep Markov Factor Analysis (NeurIPS2021)

Deep Markov Factor Analysis (DMFA) Codes and experiments for deep Markov factor analysis (DMFA) model accepted for publication at NeurIPS2021: A. Farn

Sarah Ostadabbas 2 Dec 16, 2022
Driller: augmenting AFL with symbolic execution!

Driller Driller is an implementation of the driller paper. This implementation was built on top of AFL with angr being used as a symbolic tracer. Dril

Shellphish 791 Jan 06, 2023
This repo provides a demo for the CVPR 2021 paper "A Fourier-based Framework for Domain Generalization" on the PACS dataset.

FACT This repo provides a demo for the CVPR 2021 paper "A Fourier-based Framework for Domain Generalization" on the PACS dataset. To cite, please use:

105 Dec 17, 2022
Monocular 3D pose estimation. OpenVINO. CPU inference or iGPU (OpenCL) inference.

human-pose-estimation-3d-python-cpp RealSenseD435 (RGB) 480x640 + CPU Corei9 45 FPS (Depth is not used) 1. Run 1-1. RealSenseD435 (RGB) 480x640 + CPU

Katsuya Hyodo 8 Oct 03, 2022
O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning (CoRL 2021)

O2O-Afford: Annotation-Free Large-Scale Object-Object Affordance Learning Object-object Interaction Affordance Learning. For a given object-object int

Kaichun Mo 26 Nov 04, 2022
Experiments on continual learning from a stream of pretrained models.

Ex-model CL Ex-model continual learning is a setting where a stream of experts (i.e. model's parameters) is available and a CL model learns from them

Antonio Carta 6 Dec 04, 2022
Direct application of DALLE-2 to video synthesis, using factored space-time Unet and Transformers

DALLE2 Video (wip) ** only to be built after DALLE2 image is done and replicated, and the importance of the prior network is validated ** Direct appli

Phil Wang 105 May 15, 2022
An implementation of a sequence to sequence neural network using an encoder-decoder

Keras implementation of a sequence to sequence model for time series prediction using an encoder-decoder architecture. I created this post to share a

Luke Tonin 195 Dec 17, 2022