{"id":4663,"url":"https://github.com/nashory/gans-awesome-applications","name":"gans-awesome-applications","description":"Curated list of awesome GAN applications and demo","projects_count":119,"last_synced_at":"2026-08-29T14:00:19.077Z","repository":{"id":40602917,"uuid":"106639043","full_name":"nashory/gans-awesome-applications","owner":"nashory","description":"Curated list of awesome GAN applications and demo","archived":false,"fork":false,"pushed_at":"2026-06-08T10:40:14.000Z","size":251,"stargazers_count":5100,"open_issues_count":20,"forks_count":814,"subscribers_count":196,"default_branch":"master","last_synced_at":"2026-08-10T00:10:08.557Z","etag":null,"topics":["applications","curated-list","demonstration","generative-adversarial-network","github","papers"],"latest_commit_sha":null,"homepage":null,"language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"cc0-1.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/nashory.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2017-10-12T03:19:02.000Z","updated_at":"2026-08-06T18:33:27.000Z","dependencies_parsed_at":"2024-01-13T06:21:24.330Z","dependency_job_id":"17d5b850-e2d2-4a68-a317-80dafb5e9a0c","html_url":"https://github.com/nashory/gans-awesome-applications","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/nashory/gans-awesome-applications","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nashory%2Fgans-awesome-applications","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nashory%2Fgans-awesome-applications/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nashory%2Fgans-awesome-applications/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nashory%2Fgans-awesome-applications/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/nashory","download_url":"https://codeload.github.com/nashory/gans-awesome-applications/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/nashory%2Fgans-awesome-applications/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":36970351,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-08-22T15:14:58.755Z","status":"online","status_checked_at":"2026-08-29T02:00:05.978Z","response_time":51,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"created_at":"2024-01-06T20:25:01.108Z","updated_at":"2026-08-29T14:00:19.077Z","primary_language":null,"list_of_lists":false,"displayable":true,"categories":["Applications using GANs","🏛 The landmark papers that I respect","Did not use GAN, but still interesting applications.","📚 GAN tutorials with easy and simple example code for starters","Trendy AI-application Articles","Author","🛠 Awesome GAN GitHub Projects and Tools","🧰 Implementations of various types of GANs collection","📰 Trendy AI-application Articles"],"sub_categories":["🔧 GAN Inversion and Latent Space Editing","🔄 Domain-transfer (e.g. style-transfer, pix2pix, sketch2image)","🕺 Human Pose Estimation","🖼 High-resolution image generation (large-scale image)","Font generation","🔤 Font generation","Interactive Image generation","Text2Image (text to image)","3D Object generation","✏ Image Editing","Face Aging","Domain-transfer (e.g. style-transfer, pix2pix, sketch2image)","🩹 Image Inpainting (hole filling)","Image Inpainting (hole filling)","🔍 Super-resolution","Super-resolution","🪄 Image Blending","High-resolution image generation (large-scale image)","⚡ Adversarial Diffusion Distillation (GAN-hybrid)","🛡 Adversarial Examples (Defense vs Attack)","Adversarial Examples (Defense vs Attack)","Object Detection/Recognition","Video (generation/prediction)","Synthetic Data Generation","Others","🧩 Others","Photorealistic Image generation (e.g. pix2pix, sketch2image)","Human Pose Estimation","🧊 3D Object generation","Foundational model code (official / canonical)","✍ Text2Image (text to image)","🎭 Face Stylization","🔡 Text and Sequence Generation","🚨 Anomaly Detection","👗 Virtual Try-On","🎬 Video (generation/prediction)","🔊 Audio and Speech Synthesis","🎮 Interactive Image generation","🗣 Talking Head and Face Reenactment","🖼 Photorealistic Image generation (e.g. pix2pix, sketch2image)","🎴 Anime character generation","👴 Face Aging","👁 Visual Saliency Prediction (attention prediction)","🎯 Object Detection/Recognition","🌐 3D-aware Image Synthesis","Real-world applications and tools","Anime character generation","Robotics","🧪 Synthetic Data Generation","🧑 Real-time face reconstruction"],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"https://raw.githubusercontent.com/nashory/gans-awesome-applications/master/jpg/gans.jpg\" alt=\"gans-awesome-applications banner\" width=\"100%\"\u003e\n\n# gans-awesome-applications\n\n**A curated list of awesome GAN _applications_ and demonstrations.**\n\n[![Awesome](https://awesome.re/badge.svg)](https://awesome.re)\n[![License: CC0-1.0](https://img.shields.io/badge/License-CC0%201.0-lightgrey.svg)](LICENSE)\n[![PRs Welcome](https://img.shields.io/badge/PRs-welcome-brightgreen.svg)](CONTRIBUTING.md)\n![Last Commit](https://img.shields.io/github/last-commit/nashory/gans-awesome-applications)\n![Stars](https://img.shields.io/github/stars/nashory/gans-awesome-applications?style=social)\n\n\u003c/div\u003e\n\n\u003e **Only awesome is awesome. This is a curation, not a collection.**\n\u003e\n\u003e This list is about what GANs are *used for*. General GAN papers whose contribution is the model\n\u003e itself (DCGAN, BEGAN, WGAN, …) are **not** included as entries — only genuine landmarks make the\n\u003e short list at the top. Pure theory / loss-function papers are out of scope; diffusion-only work is\n\u003e out of scope (GAN+diffusion hybrids are fine).\n\n🏷 **Legend:** 📄 paper · 💻 code · 🌐 project/demo · 🎬 video · 📝 blog\n\n🤝 Contributions welcome — see **[CONTRIBUTING.md](CONTRIBUTING.md)**.\n\n-----\n\n## 🏛 The landmark papers that I respect\n| Paper | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Generative Adversarial Networks | NeurIPS | 2014 | [📄](https://arxiv.org/abs/1406.2661) [💻](https://github.com/goodfeli/adversarial) |\n| Unsupervised Representation Learning with Deep Convolutional GANs (DCGAN) | ICLR | 2016 | [📄](https://arxiv.org/pdf/1511.06434) [💻](https://github.com/soumith/dcgan.torch) |\n| Improved Techniques for Training GANs | NeurIPS | 2016 | [📄](https://arxiv.org/pdf/1606.03498.pdf) [💻](https://github.com/openai/improved-gan) |\n| BEGAN: Boundary Equilibrium Generative Adversarial Networks | — | 2017 | [📄](https://arxiv.org/pdf/1703.10717) [💻](https://github.com/carpedm20/BEGAN-tensorflow) |\n| Training Generative Adversarial Networks with Limited Data (StyleGAN2-ADA) | NeurIPS | 2020 | [📄](https://arxiv.org/abs/2006.06676) [💻](https://github.com/NVlabs/stylegan2-ada-pytorch) |\n| The GAN is dead; long live the GAN! A Modern GAN Baseline (R3GAN) | NeurIPS | 2024 | [📄](https://arxiv.org/abs/2501.05441) [💻](https://github.com/brownvc/R3GAN) |\n\n-----\n\n## Contents\n\u003cdetails\u003e\n\u003csummary\u003e\u003cb\u003eClick to expand the table of contents\u003c/b\u003e — or just press \u003ckbd\u003ecommand\u003c/kbd\u003e/\u003ckbd\u003ectrl\u003c/kbd\u003e + \u003ckbd\u003eF\u003c/kbd\u003e to search for a keyword.\u003c/summary\u003e\n\n+ [Applications using GANs](#applications-using-gans)\n    + [🔤 Font generation](#-font-generation)\n    + [🎴 Anime character generation](#-anime-character-generation)\n    + [🎭 Face Stylization](#-face-stylization)\n    + [🎮 Interactive Image generation](#-interactive-image-generation)\n    + [🔧 GAN Inversion and Latent Space Editing](#-gan-inversion-and-latent-space-editing)\n    + [✍ Text2Image (text to image)](#-text2image-text-to-image)\n    + [⚡ Adversarial Diffusion Distillation (GAN-hybrid)](#-adversarial-diffusion-distillation-gan-hybrid)\n    + [🧊 3D Object generation](#-3d-object-generation)\n    + [🌐 3D-aware Image Synthesis](#-3d-aware-image-synthesis)\n    + [✏ Image Editing](#-image-editing)\n    + [👴 Face Aging](#-face-aging)\n    + [🕺 Human Pose Estimation](#-human-pose-estimation)\n    + [🗣 Talking Head and Face Reenactment](#-talking-head-and-face-reenactment)\n    + [👗 Virtual Try-On](#-virtual-try-on)\n    + [🔄 Domain-transfer (e.g. style-transfer, pix2pix, sketch2image)](#-domain-transfer-eg-style-transfer-pix2pix-sketch2image)\n    + [🩹 Image Inpainting (hole filling)](#-image-inpainting-hole-filling)\n    + [🪄 Image Blending](#-image-blending)\n    + [🔍 Super-resolution](#-super-resolution)\n    + [🖼 High-resolution image generation (large-scale image)](#-high-resolution-image-generation-large-scale-image)\n    + [🛡 Adversarial Examples (Defense vs Attack)](#-adversarial-examples-defense-vs-attack)\n    + [👁 Visual Saliency Prediction (attention prediction)](#-visual-saliency-prediction-attention-prediction)\n    + [🎯 Object Detection/Recognition](#-object-detectionrecognition)\n    + [🎬 Video (generation/prediction)](#-video-generationprediction)\n    + [🔊 Audio and Speech Synthesis](#-audio-and-speech-synthesis)\n    + [🔡 Text and Sequence Generation](#-text-and-sequence-generation)\n    + [🚨 Anomaly Detection](#-anomaly-detection)\n    + [🧪 Synthetic Data Generation](#-synthetic-data-generation)\n    + [🧩 Others](#-others)\n+ [Did not use GAN, but still interesting applications](#did-not-use-gan-but-still-interesting-applications)\n    + [🧑 Real-time face reconstruction](#-real-time-face-reconstruction)\n    + [🔍 Super-resolution](#-super-resolution-1)\n    + [🖼 Photorealistic Image generation (e.g. pix2pix, sketch2image)](#-photorealistic-image-generation-eg-pix2pix-sketch2image)\n    + [🕺 Human Pose Estimation](#-human-pose-estimation-1)\n    + [🧊 3D Object generation](#-3d-object-generation-1)\n+ [📚 GAN tutorials with easy and simple example code for starters](#-gan-tutorials-with-easy-and-simple-example-code-for-starters)\n+ [🛠 Awesome GAN GitHub Projects and Tools](#-awesome-gan-github-projects-and-tools)\n+ [🧰 Implementations of various types of GANs collection](#-implementations-of-various-types-of-gans-collection)\n+ [📰 Trendy AI-application Articles](#-trendy-ai-application-articles)\n\n\u003c/details\u003e\n\n-----\n\n## Applications using GANs\n\n### 🔤 Font generation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Learning Chinese Character Style with Conditional GAN (zi2zi) | — | 2017 | [💻](https://github.com/kaonashi-tyc/zi2zi) [📝](https://kaonashi-tyc.github.io/2017/04/06/zi2zi.html) |\n| Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning (AGIS-Net) | SIGGRAPH Asia | 2019 | [📄](http://arxiv.org/abs/1910.04987) [💻](https://github.com/hologerry/AGIS-Net) |\n| Attribute2Font: Creating Fonts You Want From Attributes | SIGGRAPH | 2020 | [📄](https://arxiv.org/abs/2005.07865) [💻](https://github.com/hologerry/Attr2Font) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🎴 Anime character generation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Towards the Automatic Anime Characters Creation with GANs | — | 2017 | [📄](https://arxiv.org/pdf/1708.05509) |\n| AnimeGANv2: Photo to Anime Style Transfer | — | 2021 | [💻](https://github.com/TachibanaYoshino/AnimeGANv2) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🎭 Face Stylization\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| JoJoGAN: One Shot Face Stylization | ECCV | 2022 | [📄](https://arxiv.org/abs/2112.11641) [💻](https://github.com/mchong6/JoJoGAN) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🎮 Interactive Image generation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Generative Visual Manipulation on the Natural Image Manifold (iGAN) | ECCV | 2016 | [📄](https://arxiv.org/pdf/1609.03552) [💻](https://github.com/junyanz/iGAN) |\n| Neural Photo Editing with Introspective Adversarial Networks | ICLR | 2017 | [📄](http://arxiv.org/abs/1609.07093) [💻](https://github.com/ajbrock/Neural-Photo-Editor) |\n| Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold (DragGAN) | SIGGRAPH | 2023 | [📄](https://arxiv.org/abs/2305.10973) [💻](https://github.com/XingangPan/DragGAN) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🔧 GAN Inversion and Latent Space Editing\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery | ICCV | 2021 | [📄](https://arxiv.org/abs/2103.17249) [💻](https://github.com/orpatashnik/StyleCLIP) |\n| Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation (pSp) | CVPR | 2021 | [📄](https://arxiv.org/abs/2008.00951) [💻](https://github.com/eladrich/pixel2style2pixel) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### ✍ Text2Image (text to image)\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| TAC-GAN: Text Conditioned Auxiliary Classifier GAN | — | 2017 | [📄](https://arxiv.org/pdf/1703.06412.pdf) [💻](https://github.com/dashayushman/TAC-GAN) |\n| StackGAN: Text to Photo-realistic Image Synthesis with Stacked GANs | ICCV | 2017 | [📄](https://arxiv.org/pdf/1612.03242.pdf) [💻](https://github.com/hanzhanggit/StackGAN) |\n| Generative Adversarial Text to Image Synthesis | ICML | 2016 | [📄](https://arxiv.org/pdf/1605.05396.pdf) [💻](https://github.com/paarthneekhara/text-to-image) [💻](https://github.com/reedscot/icml2016) |\n| Learning What and Where to Draw | NeurIPS | 2016 | [📄](http://www.scottreed.info/files/nips2016.pdf) [💻](https://github.com/reedscot/nips2016) |\n| AttnGAN: Fine-Grained Text to Image Generation with Attentional GANs | CVPR | 2018 | [📄](https://arxiv.org/abs/1711.10485) [💻](https://github.com/taoxugit/AttnGAN) |\n| GigaGAN: Scaling up GANs for Text-to-Image Synthesis | CVPR | 2023 | [📄](https://arxiv.org/abs/2303.05511) |\n| StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis | ICML | 2023 | [📄](https://arxiv.org/abs/2301.09515) [💻](https://github.com/autonomousvision/stylegan-t) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### ⚡ Adversarial Diffusion Distillation (GAN-hybrid)\n_GANs strike back in 2024–2026: adversarial objectives distill slow diffusion samplers into one/few-step image **and video** generators — where GANs are most alive in 2025–2026._\n\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs | CVPR | 2024 | [📄](https://arxiv.org/abs/2311.09257) |\n| Improved Distribution Matching Distillation for Fast Image Synthesis (DMD2) | NeurIPS | 2024 | [📄](https://arxiv.org/abs/2405.14867) [💻](https://github.com/tianweiy/DMD2) |\n| SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation | arXiv | 2025 | [📄](https://arxiv.org/abs/2503.09641) [💻](https://github.com/NVlabs/Sana) |\n| Diffusion Adversarial Post-Training for One-Step Video Generation (Seaweed-APT) | ICML | 2025 | [📄](https://arxiv.org/abs/2501.08316) [🌐](https://seaweed-apt.com/) |\n| Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation (Seaweed-APT2) | NeurIPS | 2025 | [📄](https://arxiv.org/abs/2506.09350) [🌐](https://seaweed-apt.com/2) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🧊 3D Object generation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Parametric 3D Exploration with Stacked Adversarial Networks (pix2vox) | — | 2016 | [💻](https://github.com/maxorange/pix2vox) [🎬](https://www.youtube.com/watch?v=ITATOXVvWEM) |\n| Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (3D-GAN) | NeurIPS | 2016 | [📄](http://papers.nips.cc/paper/6096-learning-a-probabilistic-latent-space-of-object-shapes-via-3d-generative-adversarial-modeling.pdf) [💻](https://github.com/zck119/3dgan-release) [🎬](https://www.youtube.com/watch?v=HO1LYJb818Q) |\n| 3D Shape Induction from 2D Views of Multiple Objects | — | 2016 | [📄](https://arxiv.org/pdf/1612.05872.pdf) |\n| Fully Convolutional Refined Auto-Encoding GANs for 3D Multi Object Scenes | — | 2017 | [💻](https://github.com/yunishi3/3D-FCR-alphaGAN) [📝](https://becominghuman.ai/3d-multi-object-gan-7b7cee4abf80) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🌐 3D-aware Image Synthesis\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Efficient Geometry-aware 3D Generative Adversarial Networks (EG3D) | CVPR | 2022 | [📄](https://arxiv.org/abs/2112.07945) [💻](https://github.com/NVlabs/eg3d) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### ✏ Image Editing\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Invertible Conditional GANs for Image Editing (IcGAN) | — | 2016 | [📄](https://arxiv.org/abs/1611.06355) [💻](https://github.com/Guim3/IcGAN) |\n| Image De-raining Using a Conditional GAN (ID-CGAN) | — | 2017 | [📄](https://arxiv.org/abs/1701.05957) [💻](https://github.com/hezhangsprinter/ID-CGAN) |\n| DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks | CVPR | 2018 | [📄](https://arxiv.org/abs/1711.07064) [💻](https://github.com/KupynOrest/DeblurGAN) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 👴 Face Aging\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Age Progression/Regression by Conditional Adversarial Autoencoder (CAAE) | CVPR | 2017 | [📄](https://arxiv.org/pdf/1702.08423) [💻](https://github.com/ZZUTK/Face-Aging-CAAE) |\n| CAN: Creative Adversarial Networks Generating \"Art\" | — | 2017 | [📄](https://arxiv.org/pdf/1706.07068.pdf) |\n| Face Aging with Conditional Generative Adversarial Networks | — | 2017 | [📄](https://arxiv.org/pdf/1702.01983.pdf) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🕺 Human Pose Estimation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Joint Discriminative and Generative Learning for Person Re-identification (DG-Net) | CVPR | 2019 | [📄](https://arxiv.org/abs/1904.07223) [💻](https://github.com/NVlabs/DG-Net) [🎬](https://www.youtube.com/watch?v=ubCrEAIpQs4) |\n| Pose Guided Person Image Generation | NeurIPS | 2017 | [📄](https://arxiv.org/abs/1705.09368) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🗣 Talking Head and Face Reenactment\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| First Order Motion Model for Image Animation | NeurIPS | 2019 | [📄](https://arxiv.org/abs/2003.00196) [💻](https://github.com/AliaksandrSiarohin/first-order-model) |\n| A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild (Wav2Lip) | ACM MM | 2020 | [📄](https://arxiv.org/abs/2008.10010) [💻](https://github.com/Rudrabha/Wav2Lip) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 👗 Virtual Try-On\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization | CVPR | 2021 | [📄](https://arxiv.org/abs/2103.16874) [💻](https://github.com/shadow2496/VITON-HD) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🔄 Domain-transfer (e.g. style-transfer, pix2pix, sketch2image)\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Image-to-Image Translation with Conditional Adversarial Networks (pix2pix) | CVPR | 2017 | [📄](https://arxiv.org/pdf/1611.07004) [💻](https://github.com/phillipi/pix2pix) [🎬](https://www.youtube.com/watch?v=VVqxbmUJorQ) |\n| Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (CycleGAN) | ICCV | 2017 | [📄](https://arxiv.org/pdf/1703.10593.pdf) [💻](https://github.com/junyanz/CycleGAN) [🎬](https://www.youtube.com/watch?v=JzgOfISLNjk) |\n| Learning to Discover Cross-Domain Relations with GANs (DiscoGAN) | ICML | 2017 | [📄](https://arxiv.org/pdf/1703.05192.pdf) [💻](https://github.com/carpedm20/DiscoGAN-pytorch) |\n| StarGAN: Unified Multi-Domain Image-to-Image Translation | CVPR | 2018 | [📄](https://arxiv.org/abs/1711.09020) [💻](https://github.com/yunjey/stargan) |\n| StarGAN v2: Diverse Image Synthesis for Multiple Domains | CVPR | 2020 | [📄](https://arxiv.org/abs/1912.01865) [💻](https://github.com/clovaai/stargan-v2) |\n| Multimodal Unsupervised Image-to-Image Translation (MUNIT) | ECCV | 2018 | [📄](https://arxiv.org/abs/1804.04732) [💻](https://github.com/NVlabs/MUNIT) |\n| Unsupervised Creation of Parameterized Avatars | — | 2017 | [📄](https://arxiv.org/pdf/1704.05693.pdf) |\n| Unsupervised Cross-Domain Image Generation (DTN) | ICLR | 2017 | [📄](https://openreview.net/pdf?id=Sk2Im59ex) |\n| Precomputed Real-Time Texture Synthesis with Markovian GANs (MGANs) | ECCV | 2016 | [📄](http://arxiv.org/abs/1604.04382) [💻](https://github.com/chuanli11/MGANs) |\n| Pixel-Level Domain Transfer (PixelDTGAN) | ECCV | 2016 | [📄](https://arxiv.org/pdf/1603.07442) [💻](https://github.com/fxia22/PixelDTGAN) |\n| TextureGAN: Controlling Deep Image Synthesis with Texture Patches | CVPR | 2018 | [📄](https://arxiv.org/pdf/1706.02823.pdf) [🌐](https://github.com/varunagrawal/t-gan-demo) |\n| Vincent AI Sketch Demo (NVIDIA, GTC Europe) | — | 2017 | [📝](https://blogs.nvidia.com/blog/2017/10/11/vincent-ai-sketch-demo-draws-in-throngs-at-gtc-europe/) [🎬](https://www.youtube.com/watch?v=kIcqXTUMwps) |\n| Deep Photo Style Transfer | CVPR | 2017 | [📄](https://arxiv.org/pdf/1703.07511.pdf) [💻](https://github.com/luanfujun/deep-photo-styletransfer) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🩹 Image Inpainting (hole filling)\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Context Encoders: Feature Learning by Inpainting | CVPR | 2016 | [📄](https://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Pathak_Context_Encoders_Feature_CVPR_2016_paper.pdf) [💻](https://github.com/pathak22/context-encoder) |\n| Semantic Image Inpainting with Perceptual and Contextual Losses | CVPR | 2017 | [📄](https://arxiv.org/abs/1607.07539) [💻](https://github.com/bamos/dcgan-completion.tensorflow) |\n| Semi-Supervised Learning with Context-Conditional GANs | — | 2016 | [📄](https://arxiv.org/pdf/1611.06430v1.pdf) |\n| Free-Form Image Inpainting with Gated Convolution (DeepFill v2) | ICCV | 2019 | [📄](https://arxiv.org/abs/1806.03589) [💻](https://github.com/JiahuiYu/generative_inpainting) |\n| Resolution-robust Large Mask Inpainting with Fourier Convolutions (LaMa) | WACV | 2022 | [📄](https://arxiv.org/abs/2109.07161) [💻](https://github.com/advimman/lama) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🪄 Image Blending\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| GP-GAN: Towards Realistic High-Resolution Image Blending | ACM MM | 2019 | [📄](https://arxiv.org/abs/1703.07195) [💻](https://github.com/wuhuikai/GP-GAN) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🔍 Super-resolution\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Image Super-Resolution Through Deep Learning (srez) | — | 2016 | [💻](https://github.com/david-gpu/srez) |\n| Photo-Realistic Single Image Super-Resolution Using a GAN (SRGAN) | CVPR | 2017 | [📄](https://arxiv.org/abs/1609.04802) [💻](https://github.com/tensorlayer/SRGAN) |\n| High-Quality Face Image Super-Resolution Using Conditional GANs | — | 2017 | [📄](https://arxiv.org/pdf/1707.00737.pdf) |\n| Analyzing Perception-Distortion Tradeoff (EPSR) | ECCVW | 2018 | [📄](https://arxiv.org/pdf/1811.00344.pdf) [💻](https://github.com/subeeshvasu/2018_subeesh_epsr_eccvw) |\n| ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks | ECCVW | 2018 | [📄](https://arxiv.org/abs/1809.00219) [💻](https://github.com/xinntao/ESRGAN) |\n| Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data | ICCVW | 2021 | [📄](https://arxiv.org/abs/2107.10833) [💻](https://github.com/xinntao/Real-ESRGAN) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🖼 High-resolution image generation (large-scale image)\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Generating Large Images from Latent Vectors | — | 2016 | [💻](https://github.com/hardmaru/cppn-gan-vae-tensorflow) [📝](http://blog.otoro.net/2016/04/01/generating-large-images-from-latent-vectors/) |\n| Progressive Growing of GANs for Improved Quality, Stability, and Variation (PGGAN) | ICLR | 2018 | [📄](http://research.nvidia.com/sites/default/files/pubs/2017-10_Progressive-Growing-of//karras2017gan-paper.pdf) [💻](https://github.com/tkarras/progressive_growing_of_gans) |\n| Large Scale GAN Training for High Fidelity Natural Image Synthesis (BigGAN) | ICLR | 2019 | [📄](https://arxiv.org/abs/1809.11096) |\n| SinGAN: Learning a Generative Model from a Single Natural Image | ICCV | 2019 | [📄](https://arxiv.org/abs/1905.01164) [💻](https://github.com/tamarott/SinGAN) |\n| Analyzing and Improving the Image Quality of StyleGAN (StyleGAN2) | CVPR | 2020 | [📄](https://arxiv.org/abs/1912.04958) [💻](https://github.com/NVlabs/stylegan2) |\n| Alias-Free Generative Adversarial Networks (StyleGAN3) | NeurIPS | 2021 | [📄](https://arxiv.org/abs/2106.12423) [💻](https://github.com/NVlabs/stylegan3) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🛡 Adversarial Examples (Defense vs Attack)\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| SafetyNet: Detecting and Rejecting Adversarial Examples Robustly | ICCV | 2017 | [📄](https://arxiv.org/abs/1704.00103) |\n| Adversarial Examples for Generative Models | — | 2017 | [📄](https://arxiv.org/pdf/1702.06832.pdf) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 👁 Visual Saliency Prediction (attention prediction)\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| SalGAN: Visual Saliency Prediction with Generative Adversarial Networks | — | 2017 | [📄](https://arxiv.org/pdf/1701.01081) [💻](https://github.com/imatge-upc/saliency-salgan-2017) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🎯 Object Detection/Recognition\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Perceptual Generative Adversarial Networks for Small Object Detection | CVPR | 2017 | [📄](https://arxiv.org/pdf/1706.05274) |\n| Adversarial Generation of Training Examples for Vehicle License Plate Recognition | — | 2017 | [📄](https://arxiv.org/pdf/1707.03124.pdf) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🎬 Video (generation/prediction)\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Deep Multi-Scale Video Prediction Beyond Mean Square Error | ICLR | 2016 | [📄](https://arxiv.org/pdf/1511.05440.pdf) [💻](https://github.com/dyelax/Adversarial_Video_Generation) |\n| Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation (TecoGAN) | SIGGRAPH | 2020 | [📄](https://arxiv.org/abs/1811.09393) [💻](https://github.com/thunil/TecoGAN) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🔊 Audio and Speech Synthesis\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Adversarial Audio Synthesis (WaveGAN) | ICLR | 2019 | [📄](https://arxiv.org/abs/1802.04208) [💻](https://github.com/chrisdonahue/wavegan) |\n| HiFi-GAN: GANs for Efficient and High Fidelity Speech Synthesis | NeurIPS | 2020 | [📄](https://arxiv.org/abs/2010.05646) [💻](https://github.com/jik876/hifi-gan) |\n| BigVGAN: A Universal Neural Vocoder with Large-Scale Training (v2 2024) | ICLR | 2023 | [📄](https://arxiv.org/abs/2206.04658) [💻](https://github.com/NVIDIA/BigVGAN) |\n| Vocos: Closing the Gap between Time-domain and Fourier-based Neural Vocoders | ICLR | 2024 | [📄](https://arxiv.org/abs/2306.00814) [💻](https://github.com/gemelo-ai/vocos) |\n| BemaGANv2: Discriminator Combination Strategies for GAN-based Vocoders in Long-Term Audio | arXiv | 2025 | [📄](https://arxiv.org/abs/2506.09487) [💻](https://github.com/dinhoitt/BemaGANv2) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🔡 Text and Sequence Generation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient | AAAI | 2017 | [📄](https://arxiv.org/abs/1609.05473) [💻](https://github.com/LantaoYu/SeqGAN) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🚨 Anomaly Detection\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Unsupervised Anomaly Detection with GANs to Guide Marker Discovery (AnoGAN) | IPMI | 2017 | [📄](https://arxiv.org/abs/1703.05921) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🧪 Synthetic Data Generation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Learning from Simulated and Unsupervised Images through Adversarial Training (SimGAN) | CVPR | 2017 | [📄](https://arxiv.org/pdf/1612.07828.pdf) [💻](https://github.com/carpedm20/simulated-unsupervised-tensorflow) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🧩 Others\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| (Physics) Location-Aware Generative Adversarial Networks for Physics Synthesis | — | 2017 | [📄](https://arxiv.org/pdf/1701.05927.pdf) [💻](https://github.com/hep-lbdl/adversarial-jets) |\n| (General) Spectral Normalization for Generative Adversarial Networks | ICLR | 2018 | [📄](https://openreview.net/pdf?id=B1QRgziT-) [💻](https://github.com/minhnhat93/tf-SNDCGAN) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n-----\n\n## Did not use GAN, but still interesting applications.\n\n### 🧑 Real-time face reconstruction\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction (MoFA) | ICCV | 2017 | [📄](https://arxiv.org/pdf/1703.10580.pdf) [💻](https://github.com/waxz/MoFA) [🎬](https://www.youtube.com/watch?v=uIMpHZYB8fI) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🔍 Super-resolution\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup | SIGGRAPH | 2016 | [🌐](http://hi.cs.waseda.ac.jp/~esimo/en/research/sketch/) [🎬](https://www.youtube.com/watch?v=4MfG9CDufPA) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🖼 Photorealistic Image generation (e.g. pix2pix, sketch2image)\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies | SIGGRAPH | 2016 | [🎬](https://www.youtube.com/watch?v=a3sgFQjEfp4) |\n| PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing | SIGGRAPH | 2009 | [📄](https://www.researchgate.net/profile/Eli_Shechtman/publication/220184392_PatchMatch_A_Randomized_Correspondence_Algorithm_for_Structural_Image_Editing/links/02e7e520897b12bf0f000000.pdf) [💻](https://github.com/younesse-cv/PatchMatch) [🎬](https://www.youtube.com/watch?v=n3aoc36V8LM) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🕺 Human Pose Estimation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation | — | 2017 | [📄](https://arxiv.org/pdf/1705.02407.pdf) [💻](https://github.com/Guanghan/GNet-pose) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n### 🧊 3D Object generation\n| Title | Venue | Year | Links |\n|:--|:--:|:--:|:--|\n| 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction | ECCV | 2016 | [📄](http://arxiv.org/abs/1604.00449) [💻](https://github.com/chrischoy/3D-R2N2) |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n-----\n\n## 📚 GAN tutorials with easy and simple example code for starters\n+ [1D Generative Adversarial Network Demo](http://notebooks.aylien.com/research/gan/gan_simple.html)\n+ [starter from \"How to Train a GAN?\" at NIPS2016](https://github.com/soumith/ganhacks)\n+ [NIPS 2016 Tutorial: Generative Adversarial Networks](https://arxiv.org/abs/1701.00160)\n+ [OpenAI - Generative Models](https://blog.openai.com/generative-models/)\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n----\n\n## 🛠 Awesome GAN GitHub Projects and Tools\nGenuinely awesome, widely-used GitHub repos built on GANs — usable code and tools, not just papers. Star counts update automatically.\n\n### Real-world applications and tools\n| Repo | Stars | What it does |\n|:--|:--:|:--|\n| [TencentARC/GFPGAN](https://github.com/TencentARC/GFPGAN) | ![](https://img.shields.io/github/stars/TencentARC/GFPGAN?style=flat\u0026label=%E2%AD%90\u0026color=gold) | Practical real-world face restoration |\n| [jantic/DeOldify](https://github.com/jantic/DeOldify) | ![](https://img.shields.io/github/stars/jantic/DeOldify?style=flat\u0026label=%E2%AD%90\u0026color=gold) | Colorize and restore old photos and video *(archived)* |\n\n### Foundational model code (official / canonical)\n| Repo | Stars | What it does |\n|:--|:--:|:--|\n| [junyanz/pytorch-CycleGAN-and-pix2pix](https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix) | ![](https://img.shields.io/github/stars/junyanz/pytorch-CycleGAN-and-pix2pix?style=flat\u0026label=%E2%AD%90\u0026color=gold) | Official CycleGAN + pix2pix in PyTorch |\n| [NVlabs/stylegan](https://github.com/NVlabs/stylegan) | ![](https://img.shields.io/github/stars/NVlabs/stylegan?style=flat\u0026label=%E2%AD%90\u0026color=gold) | Official StyleGAN |\n| [NVlabs/SPADE](https://github.com/NVlabs/SPADE) | ![](https://img.shields.io/github/stars/NVlabs/SPADE?style=flat\u0026label=%E2%AD%90\u0026color=gold) | Semantic image synthesis, a.k.a. GauGAN |\n| [NVIDIA/pix2pixHD](https://github.com/NVIDIA/pix2pixHD) | ![](https://img.shields.io/github/stars/NVIDIA/pix2pixHD?style=flat\u0026label=%E2%AD%90\u0026color=gold) | High-resolution image synthesis and manipulation |\n| [ajbrock/BigGAN-PyTorch](https://github.com/ajbrock/BigGAN-PyTorch) | ![](https://img.shields.io/github/stars/ajbrock/BigGAN-PyTorch?style=flat\u0026label=%E2%AD%90\u0026color=gold) | The author's PyTorch BigGAN |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n----\n\n## 🧰 Implementations of various types of GANs collection\n| Repo | Stars | Framework |\n|:--|:--:|:--|\n| [nashory/gans-collection.torch](https://github.com/nashory/gans-collection.torch) | ![](https://img.shields.io/github/stars/nashory/gans-collection.torch?style=flat\u0026label=%E2%AD%90\u0026color=gold) | Torch7 |\n| [hwalsuklee/tensorflow-generative-model-collections](https://github.com/hwalsuklee/tensorflow-generative-model-collections) | ![](https://img.shields.io/github/stars/hwalsuklee/tensorflow-generative-model-collections?style=flat\u0026label=%E2%AD%90\u0026color=gold) | TensorFlow |\n| [wiseodd/generative-models](https://github.com/wiseodd/generative-models) | ![](https://img.shields.io/github/stars/wiseodd/generative-models?style=flat\u0026label=%E2%AD%90\u0026color=gold) | PyTorch \u0026 TensorFlow |\n| [aboev/arae-tf](https://github.com/aboev/arae-tf) | ![](https://img.shields.io/github/stars/aboev/arae-tf?style=flat\u0026label=%E2%AD%90\u0026color=gold) | TensorFlow |\n| [eriklindernoren/PyTorch-GAN](https://github.com/eriklindernoren/PyTorch-GAN) | ![](https://img.shields.io/github/stars/eriklindernoren/PyTorch-GAN?style=flat\u0026label=%E2%AD%90\u0026color=gold) | PyTorch — dozens of GANs |\n| [eriklindernoren/Keras-GAN](https://github.com/eriklindernoren/Keras-GAN) | ![](https://img.shields.io/github/stars/eriklindernoren/Keras-GAN?style=flat\u0026label=%E2%AD%90\u0026color=gold) | Keras — many GANs |\n| [NVlabs/imaginaire](https://github.com/NVlabs/imaginaire) | ![](https://img.shields.io/github/stars/NVlabs/imaginaire?style=flat\u0026label=%E2%AD%90\u0026color=gold) | PyTorch — NVIDIA image \u0026 video synthesis GANs |\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n___\n\n## 📰 Trendy AI-application Articles\n+ [Artificial intelligence can say yes to the dress](https://qz.com/1090267/artificial-intelligence-can-now-show-you-how-those-pants-will-fit/)\n\n\u003csub\u003e\u003ca href=\"#contents\"\u003e↑ back to Contents\u003c/a\u003e\u003c/sub\u003e\n\n-----\n\n## Author\nMinchul Shin, [@nashory](https://github.com/nashory)\n\n__Any recommendations to add to the list are welcome — see [CONTRIBUTING.md](CONTRIBUTING.md) and feel free to make pull requests! :)__\n","projects_url":"https://awesome.ecosyste.ms/api/v1/lists/nashory%2Fgans-awesome-applications/projects"}