https://github.com/bilibili/ailab/blob/main/Real-CUGAN/README_EN.md Skip to content Sign up * Why GitHub? + Features + Mobile + Actions + Codespaces + Packages + Security + Code review + Issues + Integrations + GitHub Sponsors + Customer stories * Team * Enterprise * Explore + Explore GitHub + Learn and contribute + Topics + Collections + Trending + Learning Lab + Open source guides + Connect with others + The ReadME Project + Events + Community forum + GitHub Education + GitHub Stars program * Marketplace * Pricing + Plans + Compare plans + Contact Sales + Education [ ] * # In this repository All GitHub | Jump to | * No suggested jump to results * # In this repository All GitHub | Jump to | * # In this organization All GitHub | Jump to | * # In this repository All GitHub | Jump to | Sign in Sign up {{ message }} bilibili / ailab Public * Notifications * Fork 99 * Star 1k * * Code * Issues 14 * Pull requests 2 * Actions * Projects 0 * Wiki * Security * Insights More * Code * Issues * Pull requests * Actions * Projects * Wiki * Security * Insights Permalink main Switch branches/tags [ ] Branches Tags Could not load branches Nothing to show {{ refName }} default View all branches Could not load tags Nothing to show {{ refName }} default View all tags ailab/Real-CUGAN/README_EN.md Go to file * Go to file T * Go to line L * * Copy path * Copy permalink This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository. @lj1995-computer-vision lj1995-computer-vision Windows-GUI/Web service are now supported! ... Latest commit d74ee26 Feb 7, 2022 History Windows-GUI/Web service are now supported! 1 contributor Users who have contributed to this file [ ] Real Cascade U-Nets for Anime Image Super Resolution 1. Comparasion 2. For windows users Executable file: System environment: config file: a. common settings b. settings for video task 3. For waifu2x-caffe users We support two weights for waifu2x-caffe users now: 4. Python environment dependence 5. For VapourSynth users 6. Model Zoo 7. TODO: 8. Acknowledgement 132 lines (103 sloc) 8.23 KB Raw Blame * Open with Desktop * View raw * * View blame Real Cascade U-Nets for Anime Image Super Resolution Real-CUGAN is an AI super resolution model for anime images, trained in a million scale anime dataset, using the same architecture as Waifu2x-CUNet. It supports 2x\3x\4x super resolving. For different enhancement strength, now 2x Real-CUGAN supports 5 model weights, 3x/ 4x Real-CUGAN supports 3 model weights. Real-CUGAN packages an executable environment for windows users. GUI and web version are also supported now. If you find Real-CUGAN helpful for your anime videos/projects, please help staring this repo or share it to your friends, thanks! Update progress(Windows-GUI/Web) 1. Comparasion demo-video.mp4 * visual effect comparasion texture chanllenge case compare1 line chanllenge case compare2 heavy artifact case compare3 bokeh effect case compare4 * Detailed comparasion Waifu2x Real-ESRGAN(Anime6B) Real-CUGAN (CUNet) Private anime Private anime training Million scale traning set training set, unknown magnitude high quality set, unknown and quality patch training magnitude set and quality speed(times) Baseline 2.2x 1x The sharpening strength Sharper line can't is the largest. The style than deblur; painting style may be waifu2x. Bokeh visual effect artifacts changed. The lines may effect region are not be incorrectly maintained completely reconstructed. The bokeh better. Texture removed effect region may be preserved better. forced to be clear. numbers of existing windows-apps compatibility , PyTorch,VapourSynth, the same as Caffe, NCNN waifu2x PyTorch, NCNN, VapourSynth supports 5 different multiple only support default enhancement enhancement denoise enhancement strength strength for 2x, strength 3 for 3x, 3 for 4x now 2x+3x+4x are SR resolution 1x+2x 4x supported now, and 1x model is training 2. For windows users modify config.py, and double click go.bat to execute Real-CUGAN. * Executable file: BaiduDrive(extract code:ds2a) |GithubRelease |HecaiDrive (extract code:baRo) | GoogleDrive * System environment: + [?] Tested in windows10 64bit. + [?] Light version: cuda >= 10.0. [(Heavy version: cuda >= 11.1 )] + Note that 30 series nvidia GPU only supports heavy version. * config file: a. common settings + mode: image/video; + model_path: the path of model weights(2x model has 4 weight files, 3x/4x model only has 1 weight file); + device: cuda device number. If you want to use multiple GPUs to super resolve images, it's recommanded to manually divide the tasks into different folders and fill in different cuda device numbers; + you need fill in the input and output dir path for image task, and the input and output video file path for video task. b. settings for video task + nt: the threading number of each GPU. If the video memory is enough, >=2 is recommended (for faster inference). + n_gpu: the number of GPUs you will use. + encode_params: if you don't know how to use ffmpeg, you shouldn't change it. + half: FP16 inference or FP32 inference. 'True' is recommended. + tile: 0~4 is supported. The bigger the number, the less video memory is needed, and the lower inference speed it is. 3. For waifu2x-caffe users We support two weights for waifu2x-caffe users now: Real-CUGAN2x standard version and Real-CUGAN2x no crop line version BaiduDrive(extract code:ds2a) |GithubRelease |HecaiDrive(extract code:baRo) | GoogleDrive Users can replace the original weights with the new ones (remember to backup the original weights if you want to reuse them), and use the original setting to super resolve images. due to the crop mechanism of waifu2x-caffe, for standard version ,big crop_size is recommanded, or the crop line artifact may be caused. If crop line edge artifact is found, please use our windows package or the 'no crop line' version. The tile_mode of windows package version is lossless. The 'no edge artifact' version waifu2x-caffe weights may cause more texture loss. For developers, it is recommended to use the whole image as input. Pytorch version (tile mode) is recommended if you want the program to require less video memory. 4. Python environment dependence torch>=1.0.0 numpy opencv-python moviepy upcunet_v3.py:model file and image inference script inference_video.py: a simple script for inferencing anime videos using Real-CUGAN 5. For VapourSynth users Please see Readme 6. Model Zoo You can download the weights from netdisk links. 1x 2x 3x/4x denoise only no denoise no denoise/1x/ no denoise/3x are strength version supported, 2x/3x are supported now, 1x/ training... supported now 2x:training... conservative training... supported now version fast model under investigation 7. TODO: * [ ] Lightweight/fast version * [ ] Adjustable denoise, deblock, deblur, sharpening strength * [ ] Super resolve the image to specified resolution end to end * [ ] Optimize texture retention and reduce AI processing artifacts * [*] Simple GUI 8. Acknowledgement The training code is from but not limited to:RealESRGAN. The original waifu2x-cunet architecture is from:CUNet. Update progress: * Windows GUI (PyTorch version), Squirrel Anime Enhance v0.0.3 * Web service (CPU-PyTorch version),by mnixry Thanks for their contribution! [ ] Go * (c) 2022 GitHub, Inc. * Terms * Privacy * Security * Status * Docs * Contact GitHub * Pricing * API * Training * Blog * About You can't perform that action at this time. You signed in with another tab or window. Reload to refresh your session. You signed out in another tab or window. Reload to refresh your session.