lolz0r / ganless-hd
The basic idea is to utilize a U-Net, modified perceptual loss (pearson instead of MAE), learned basis functions, and "mean teacher" training in order to synthesize images of high quality without the normal troubles of training a GAN.
☆42Updated 5 years ago
Related projects ⓘ
Alternatives and complementary repositories for ganless-hd
- Original stylegan without blobs (without retraining).☆38Updated 4 years ago
- High resolution image to image translation using multi-scale gradients☆27Updated last year
- Content Transformation Block For Image Style Transfer [CVPR19]☆25Updated 4 years ago
- Information Distillation Generative Adversrial Network in PyTorch☆27Updated 4 years ago
- TCVC: Temporally Coherent Video Colorization, CRV 2019☆18Updated 5 years ago
- The Official TensorFlow Implementation for SPatchGAN (ICCV2021)☆55Updated last year
- Learning To Create Professional Sketch☆20Updated 3 years ago
- Implementation of Taming Transformers for High-Resolution Image Synthesis (https://arxiv.org/abs/2012.09841) in PyTorch☆16Updated 3 years ago
- Convert @NVlabs StyleGAN pkls to @taki0112 StyleGAN-Tensorflow checkpoints (copy over the weights)☆27Updated 5 years ago
- Across Scales & Across Dimensions - Temporal Super-Resolution using Deep Internal Learning☆42Updated 4 years ago
- ☆22Updated 2 years ago
- [ACCV 2018 Oral] Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation☆45Updated 3 years ago
- Official repository for MaGNET, ICLR 2022☆26Updated 2 years ago
- Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors (IJCV2022)☆45Updated 2 years ago
- Code for the ICME 2021 paper "SAFIN: Arbitrary Style Transfer With Self-Attentive Factorized Instance Normalization"☆34Updated 10 months ago
- Code Base for the work "Interactive Portrait Harmonization"☆28Updated last year
- ICCV2021 (poster)☆74Updated 3 years ago
- ☆40Updated 3 years ago
- ☆23Updated 4 years ago
- Open source repository at GitHub for Attention-based Stylisation for Exemplar Image Colourisation☆14Updated 2 years ago
- Train a StyleGAN2 model on Colaboratory to generate Steam banners.☆32Updated 3 years ago
- ☆16Updated 2 years ago
- BigGAN; Knowledge Distillation; Black-Box; Fast Training; 16x compression☆75Updated 3 years ago
- Study Friendly Implementation of Pix2Pix in Tensorflow☆13Updated 6 years ago
- ☆37Updated 2 years ago
- Adversarial Training for Solving Inverse Problems☆24Updated 4 years ago
- Repository for Fantastic Style Channels and Where to Find Them: A Submodular Framework for Discovering Diverse Directions in GANs☆27Updated 2 years ago
- StyleGAN2 - micro changes to enable perfect projecting☆10Updated 2 years ago
- ☆18Updated 2 years ago