Few Shot Patch Based TrainingThe official implementation of our SIGGRAPH 2020 paper Interactive Video Stylization Using Few-Shot Patch-Based Training
ConsinganPyTorch implementation of "Improved Techniques for Training Single-Image GANs" (WACV-21)
Inpainting gmcnnImage Inpainting via Generative Multi-column Convolutional Neural Networks, NeurIPS2018
SnappyPHP library allowing thumbnail, snapshot or PDF generation from a url or a html page. Wrapper for wkhtmltopdf/wkhtmltoimage
clip-guided-diffusionA CLI tool/python module for generating images from text using guided diffusion and CLIP from OpenAI.
AsymmetricGAN[ACCV 2018 Oral] Dual Generator Generative Adversarial Networks for Multi-Domain Image-to-Image Translation
lecam-ganRegularizing Generative Adversarial Networks under Limited Data (CVPR 2021)
ADL2019Applied Deep Learning (2019 Spring) @ NTU
swdunsupervised video and image generation
HugsVisionHugsVision is a easy to use huggingface wrapper for state-of-the-art computer vision
TargetCLIPOfficial PyTorch implementation of the paper Image-Based CLIP-Guided Essence Transfer.
AODAOfficial implementation of "Adversarial Open Domain Adaptation for Sketch-to-Photo Synthesis"(WACV 2022/CVPRW 2021)
CWRCode and dataset for Single Underwater Image Restoration by Contrastive Learning, IGARSS 2021, oral.
cfg-ganCFG-GAN: Composite functional gradient learning of generative adversarial models
OASISOfficial implementation of the paper "You Only Need Adversarial Supervision for Semantic Image Synthesis" (ICLR 2021)
TimeSeries2DBarChartImageCNNConversion of the time series values to 2-D stock bar chart images and prediction using CNN (using Keras-Tensorflow)
WGAN-GP-TensorFlowTensorFlow implementations of Wasserstein GAN with Gradient Penalty (WGAN-GP), Least Squares GAN (LSGAN), GANs with the hinge loss.
SDEditPyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations
NeuralTexGenImage-space texture optimization of 3D meshes using PyTorch
SuperStyleNetSuperStyleNet: Deep Image Synthesis with Superpixel Based Style Encoder (BMVC 2021)
texturize🤖🖌️ Generate photo-realistic textures based on source images. Remix, remake, mashup! Useful if you want to create variations on a theme or elaborate on an existing texture.
multiple-objects-ganImplementation for "Generating Multiple Objects at Spatially Distinct Locations" (ICLR 2019)
vqgan-clip-appLocal image generation using VQGAN-CLIP or CLIP guided diffusion
ru-dalleGenerate images from texts. In Russian
universum-contractstext-to-image generation gems / libraries incl. moonbirds, cyberpunks, coolcats, shiba inu doge, nouns & more
soft-intro-vae-pytorch[CVPR 2021 Oral] Official PyTorch implementation of Soft-IntroVAE from the paper "Soft-IntroVAE: Analyzing and Improving Introspective Variational Autoencoders"
CoCosNet-v2CoCosNet v2: Full-Resolution Correspondence Learning for Image Translation
MoCoGAN-HD[ICLR 2021 Spotlight] A Good Image Generator Is What You Need for High-Resolution Video Synthesis