nashory/gans-awesome-applications
nashory/gans-awesome-applications is one of the open-source repositories TopGit tracks, currently at 5.1k stars. Curated list of awesome GAN applications and demo
Snapshot summary built from the project's own GitHub metadata — there's no written TopGit review yet. The page will update automatically when a full review is published.
TopGit writes full reviews for the most-starred, most-requested repositories. This page is a snapshot until then — see the READ ME tab for the original README in full.
Snapshot
Top contributors
Show top contributors
gans-awesome-applications
A curated list of awesome GAN applications and demonstrations.
Only awesome is awesome. This is a curation, not a collection.
This list is about what GANs are used for. General GAN papers whose contribution is the model itself (DCGAN, BEGAN, WGAN, …) are not included as entries — only genuine landmarks make the short list at the top. Pure theory / loss-function papers are out of scope; diffusion-only work is out of scope (GAN+diffusion hybrids are fine).
🏷 Legend: 📄 paper · 💻 code · 🌐 project/demo · 🎬 video · 📝 blog
🤝 Contributions welcome — see CONTRIBUTING.md.
🏛 The landmark papers that I respect
| Paper | Venue | Year | Links |
|---|---|---|---|
| Generative Adversarial Networks | NeurIPS | 2014 | 📄 💻 |
| Unsupervised Representation Learning with Deep Convolutional GANs (DCGAN) | ICLR | 2016 | 📄 💻 |
| Improved Techniques for Training GANs | NeurIPS | 2016 | 📄 💻 |
| BEGAN: Boundary Equilibrium Generative Adversarial Networks | — | 2017 | 📄 💻 |
| Training Generative Adversarial Networks with Limited Data (StyleGAN2-ADA) | NeurIPS | 2020 | 📄 💻 |
| The GAN is dead; long live the GAN! A Modern GAN Baseline (R3GAN) | NeurIPS | 2024 | 📄 💻 |
Contents
Click to expand the table of contents — or just press command/ctrl + F to search for a keyword.
- Applications using GANs
- 🔤 Font generation
- 🎴 Anime character generation
- 🎭 Face Stylization
- 🎮 Interactive Image generation
- 🔧 GAN Inversion and Latent Space Editing
- ✍ Text2Image (text to image)
- ⚡ Adversarial Diffusion Distillation (GAN-hybrid)
- 🧊 3D Object generation
- 🌐 3D-aware Image Synthesis
- ✏ Image Editing
- 👴 Face Aging
- 🕺 Human Pose Estimation
- 🗣 Talking Head and Face Reenactment
- 👗 Virtual Try-On
- 🔄 Domain-transfer (e.g. style-transfer, pix2pix, sketch2image)
- 🩹 Image Inpainting (hole filling)
- 🪄 Image Blending
- 🔍 Super-resolution
- 🖼 High-resolution image generation (large-scale image)
- 🛡 Adversarial Examples (Defense vs Attack)
- 👁 Visual Saliency Prediction (attention prediction)
- 🎯 Object Detection/Recognition
- 🎬 Video (generation/prediction)
- 🔊 Audio and Speech Synthesis
- 🔡 Text and Sequence Generation
- 🚨 Anomaly Detection
- 🧪 Synthetic Data Generation
- 🧩 Others
- Did not use GAN, but still interesting applications
- 🧑 Real-time face reconstruction
- 🔍 Super-resolution
- 🖼 Photorealistic Image generation (e.g. pix2pix, sketch2image)
- 🕺 Human Pose Estimation
- 🧊 3D Object generation
- 📚 GAN tutorials with easy and simple example code for starters
- 🛠 Awesome GAN GitHub Projects and Tools
- 🧰 Implementations of various types of GANs collection
- 📰 Trendy AI-application Articles
Applications using GANs
🔤 Font generation
| Title | Venue | Year | Links |
|---|---|---|---|
| Learning Chinese Character Style with Conditional GAN (zi2zi) | — | 2017 | 💻 📝 |
| Artistic Glyph Image Synthesis via One-Stage Few-Shot Learning (AGIS-Net) | SIGGRAPH Asia | 2019 | 📄 💻 |
| Attribute2Font: Creating Fonts You Want From Attributes | SIGGRAPH | 2020 | 📄 💻 |
↑ back to Contents
🎴 Anime character generation
| Title | Venue | Year | Links |
|---|---|---|---|
| Towards the Automatic Anime Characters Creation with GANs | — | 2017 | 📄 |
| AnimeGANv2: Photo to Anime Style Transfer | — | 2021 | 💻 |
↑ back to Contents
🎭 Face Stylization
| Title | Venue | Year | Links |
|---|---|---|---|
| JoJoGAN: One Shot Face Stylization | ECCV | 2022 | 📄 💻 |
↑ back to Contents
🎮 Interactive Image generation
| Title | Venue | Year | Links |
|---|---|---|---|
| Generative Visual Manipulation on the Natural Image Manifold (iGAN) | ECCV | 2016 | 📄 💻 |
| Neural Photo Editing with Introspective Adversarial Networks | ICLR | 2017 | 📄 💻 |
| Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold (DragGAN) | SIGGRAPH | 2023 | 📄 💻 |
↑ back to Contents
🔧 GAN Inversion and Latent Space Editing
| Title | Venue | Year | Links |
|---|---|---|---|
| StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery | ICCV | 2021 | 📄 💻 |
| Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation (pSp) | CVPR | 2021 | 📄 💻 |
↑ back to Contents
✍ Text2Image (text to image)
| Title | Venue | Year | Links |
|---|---|---|---|
| TAC-GAN: Text Conditioned Auxiliary Classifier GAN | — | 2017 | 📄 💻 |
| StackGAN: Text to Photo-realistic Image Synthesis with Stacked GANs | ICCV | 2017 | 📄 💻 |
| Generative Adversarial Text to Image Synthesis | ICML | 2016 | 📄 💻 💻 |
| Learning What and Where to Draw | NeurIPS | 2016 | 📄 💻 |
| AttnGAN: Fine-Grained Text to Image Generation with Attentional GANs | CVPR | 2018 | 📄 💻 |
| GigaGAN: Scaling up GANs for Text-to-Image Synthesis | CVPR | 2023 | 📄 |
| StyleGAN-T: Unlocking the Power of GANs for Fast Large-Scale Text-to-Image Synthesis | ICML | 2023 | 📄 💻 |
↑ back to Contents
⚡ Adversarial Diffusion Distillation (GAN-hybrid)
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.
| Title | Venue | Year | Links |
|---|---|---|---|
| UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANs | CVPR | 2024 | 📄 |
| Improved Distribution Matching Distillation for Fast Image Synthesis (DMD2) | NeurIPS | 2024 | 📄 💻 |
| SANA-Sprint: One-Step Diffusion with Continuous-Time Consistency Distillation | arXiv | 2025 | 📄 💻 |
| Diffusion Adversarial Post-Training for One-Step Video Generation (Seaweed-APT) | ICML | 2025 | 📄 🌐 |
| Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation (Seaweed-APT2) | NeurIPS | 2025 | 📄 🌐 |
↑ back to Contents
🧊 3D Object generation
| Title | Venue | Year | Links |
|---|---|---|---|
| Parametric 3D Exploration with Stacked Adversarial Networks (pix2vox) | — | 2016 | 💻 🎬 |
| Learning a Probabilistic Latent Space of Object Shapes via 3D Generative-Adversarial Modeling (3D-GAN) | NeurIPS | 2016 | 📄 💻 🎬 |
| 3D Shape Induction from 2D Views of Multiple Objects | — | 2016 | 📄 |
| Fully Convolutional Refined Auto-Encoding GANs for 3D Multi Object Scenes | — | 2017 | 💻 📝 |
↑ back to Contents
🌐 3D-aware Image Synthesis
| Title | Venue | Year | Links |
|---|---|---|---|
| Efficient Geometry-aware 3D Generative Adversarial Networks (EG3D) | CVPR | 2022 | 📄 💻 |
↑ back to Contents
✏ Image Editing
| Title | Venue | Year | Links |
|---|---|---|---|
| Invertible Conditional GANs for Image Editing (IcGAN) | — | 2016 | 📄 💻 |
| Image De-raining Using a Conditional GAN (ID-CGAN) | — | 2017 | 📄 💻 |
| DeblurGAN: Blind Motion Deblurring Using Conditional Adversarial Networks | CVPR | 2018 | 📄 💻 |
↑ back to Contents
👴 Face Aging
| Title | Venue | Year | Links |
|---|---|---|---|
| Age Progression/Regression by Conditional Adversarial Autoencoder (CAAE) | CVPR | 2017 | 📄 💻 |
| CAN: Creative Adversarial Networks Generating "Art" | — | 2017 | 📄 |
| Face Aging with Conditional Generative Adversarial Networks | — | 2017 | 📄 |
↑ back to Contents
🕺 Human Pose Estimation
| Title | Venue | Year | Links |
|---|---|---|---|
| Joint Discriminative and Generative Learning for Person Re-identification (DG-Net) | CVPR | 2019 | 📄 💻 🎬 |
| Pose Guided Person Image Generation | NeurIPS | 2017 | 📄 |
↑ back to Contents
🗣 Talking Head and Face Reenactment
| Title | Venue | Year | Links |
|---|---|---|---|
| First Order Motion Model for Image Animation | NeurIPS | 2019 | 📄 💻 |
| A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild (Wav2Lip) | ACM MM | 2020 | 📄 💻 |
↑ back to Contents
👗 Virtual Try-On
| Title | Venue | Year | Links |
|---|---|---|---|
| VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization | CVPR | 2021 | 📄 💻 |
↑ back to Contents
🔄 Domain-transfer (e.g. style-transfer, pix2pix, sketch2image)
| Title | Venue | Year | Links |
|---|---|---|---|
| Image-to-Image Translation with Conditional Adversarial Networks (pix2pix) | CVPR | 2017 | 📄 💻 🎬 |
| Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks (CycleGAN) | ICCV | 2017 | 📄 💻 🎬 |
| Learning to Discover Cross-Domain Relations with GANs (DiscoGAN) | ICML | 2017 | 📄 💻 |
| StarGAN: Unified Multi-Domain Image-to-Image Translation | CVPR | 2018 | 📄 💻 |
| StarGAN v2: Diverse Image Synthesis for Multiple Domains | CVPR | 2020 | 📄 💻 |
| Multimodal Unsupervised Image-to-Image Translation (MUNIT) | ECCV | 2018 | 📄 💻 |
| Unsupervised Creation of Parameterized Avatars | — | 2017 | 📄 |
| Unsupervised Cross-Domain Image Generation (DTN) | ICLR | 2017 | 📄 |
| Precomputed Real-Time Texture Synthesis with Markovian GANs (MGANs) | ECCV | 2016 | 📄 💻 |
| Pixel-Level Domain Transfer (PixelDTGAN) | ECCV | 2016 | 📄 💻 |
| TextureGAN: Controlling Deep Image Synthesis with Texture Patches | CVPR | 2018 | 📄 🌐 |
| Vincent AI Sketch Demo (NVIDIA, GTC Europe) | — | 2017 | 📝 🎬 |
| Deep Photo Style Transfer | CVPR | 2017 | 📄 💻 |
↑ back to Contents
🩹 Image Inpainting (hole filling)
| Title | Venue | Year | Links |
|---|---|---|---|
| Context Encoders: Feature Learning by Inpainting | CVPR | 2016 | 📄 💻 |
| Semantic Image Inpainting with Perceptual and Contextual Losses | CVPR | 2017 | 📄 💻 |
| Semi-Supervised Learning with Context-Conditional GANs | — | 2016 | 📄 |
| Free-Form Image Inpainting with Gated Convolution (DeepFill v2) | ICCV | 2019 | 📄 💻 |
| Resolution-robust Large Mask Inpainting with Fourier Convolutions (LaMa) | WACV | 2022 | 📄 💻 |
↑ back to Contents
🪄 Image Blending
| Title | Venue | Year | Links |
|---|---|---|---|
| GP-GAN: Towards Realistic High-Resolution Image Blending | ACM MM | 2019 | 📄 💻 |
↑ back to Contents
🔍 Super-resolution
| Title | Venue | Year | Links |
|---|---|---|---|
| Image Super-Resolution Through Deep Learning (srez) | — | 2016 | 💻 |
| Photo-Realistic Single Image Super-Resolution Using a GAN (SRGAN) | CVPR | 2017 | 📄 💻 |
| High-Quality Face Image Super-Resolution Using Conditional GANs | — | 2017 | 📄 |
| Analyzing Perception-Distortion Tradeoff (EPSR) | ECCVW | 2018 | 📄 💻 |
| ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks | ECCVW | 2018 | 📄 💻 |
| Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data | ICCVW | 2021 | 📄 💻 |
↑ back to Contents
🖼 High-resolution image generation (large-scale image)
| Title | Venue | Year | Links |
|---|---|---|---|
| Generating Large Images from Latent Vectors | — | 2016 | 💻 📝 |
| Progressive Growing of GANs for Improved Quality, Stability, and Variation (PGGAN) | ICLR | 2018 | 📄 💻 |
| Large Scale GAN Training for High Fidelity Natural Image Synthesis (BigGAN) | ICLR | 2019 | 📄 |
| SinGAN: Learning a Generative Model from a Single Natural Image | ICCV | 2019 | 📄 💻 |
| Analyzing and Improving the Image Quality of StyleGAN (StyleGAN2) | CVPR | 2020 | 📄 💻 |
| Alias-Free Generative Adversarial Networks (StyleGAN3) | NeurIPS | 2021 | 📄 💻 |
↑ back to Contents
🛡 Adversarial Examples (Defense vs Attack)
| Title | Venue | Year | Links |
|---|---|---|---|
| SafetyNet: Detecting and Rejecting Adversarial Examples Robustly | ICCV | 2017 | 📄 |
| Adversarial Examples for Generative Models | — | 2017 | 📄 |
↑ back to Contents
👁 Visual Saliency Prediction (attention prediction)
| Title | Venue | Year | Links |
|---|---|---|---|
| SalGAN: Visual Saliency Prediction with Generative Adversarial Networks | — | 2017 | 📄 💻 |
↑ back to Contents
🎯 Object Detection/Recognition
| Title | Venue | Year | Links |
|---|---|---|---|
| Perceptual Generative Adversarial Networks for Small Object Detection | CVPR | 2017 | 📄 |
| Adversarial Generation of Training Examples for Vehicle License Plate Recognition | — | 2017 | 📄 |
↑ back to Contents
🎬 Video (generation/prediction)
| Title | Venue | Year | Links |
|---|---|---|---|
| Deep Multi-Scale Video Prediction Beyond Mean Square Error | ICLR | 2016 | 📄 💻 |
| Learning Temporal Coherence via Self-Supervision for GAN-based Video Generation (TecoGAN) | SIGGRAPH | 2020 | 📄 💻 |
↑ back to Contents
🔊 Audio and Speech Synthesis
| Title | Venue | Year | Links |
|---|---|---|---|
| Adversarial Audio Synthesis (WaveGAN) | ICLR | 2019 | 📄 💻 |
| HiFi-GAN: GANs for Efficient and High Fidelity Speech Synthesis | NeurIPS | 2020 | 📄 💻 |
| BigVGAN: A Universal Neural Vocoder with Large-Scale Training (v2 2024) | ICLR | 2023 | 📄 💻 |
| Vocos: Closing the Gap between Time-domain and Fourier-based Neural Vocoders | ICLR | 2024 | 📄 💻 |
| BemaGANv2: Discriminator Combination Strategies for GAN-based Vocoders in Long-Term Audio | arXiv | 2025 | 📄 💻 |
↑ back to Contents
🔡 Text and Sequence Generation
| Title | Venue | Year | Links |
|---|---|---|---|
| SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient | AAAI | 2017 | 📄 💻 |
↑ back to Contents
🚨 Anomaly Detection
| Title | Venue | Year | Links |
|---|---|---|---|
| Unsupervised Anomaly Detection with GANs to Guide Marker Discovery (AnoGAN) | IPMI | 2017 | 📄 |
↑ back to Contents
🧪 Synthetic Data Generation
| Title | Venue | Year | Links |
|---|---|---|---|
| Learning from Simulated and Unsupervised Images through Adversarial Training (SimGAN) | CVPR | 2017 | 📄 💻 |
↑ back to Contents
🧩 Others
| Title | Venue | Year | Links |
|---|---|---|---|
| (Physics) Location-Aware Generative Adversarial Networks for Physics Synthesis | — | 2017 | 📄 💻 |
| (General) Spectral Normalization for Generative Adversarial Networks | ICLR | 2018 | 📄 💻 |
↑ back to Contents
Did not use GAN, but still interesting applications.
🧑 Real-time face reconstruction
| Title | Venue | Year | Links |
|---|---|---|---|
| Model-based Deep Convolutional Face Autoencoder for Unsupervised Monocular Reconstruction (MoFA) | ICCV | 2017 | 📄 💻 🎬 |
↑ back to Contents
🔍 Super-resolution
| Title | Venue | Year | Links |
|---|---|---|---|
| Learning to Simplify: Fully Convolutional Networks for Rough Sketch Cleanup | SIGGRAPH | 2016 | 🌐 🎬 |
↑ back to Contents
🖼 Photorealistic Image generation (e.g. pix2pix, sketch2image)
| Title | Venue | Year | Links |
|---|---|---|---|
| The Sketchy Database: Learning to Retrieve Badly Drawn Bunnies | SIGGRAPH | 2016 | 🎬 |
| PatchMatch: A Randomized Correspondence Algorithm for Structural Image Editing | SIGGRAPH | 2009 | 📄 💻 🎬 |
↑ back to Contents
🕺 Human Pose Estimation
| Title | Venue | Year | Links |
|---|---|---|---|
| Knowledge-Guided Deep Fractal Neural Networks for Human Pose Estimation | — | 2017 | 📄 💻 |
↑ back to Contents
🧊 3D Object generation
| Title | Venue | Year | Links |
|---|---|---|---|
| 3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction | ECCV | 2016 | 📄 💻 |
↑ back to Contents
📚 GAN tutorials with easy and simple example code for starters
- 1D Generative Adversarial Network Demo
- starter from "How to Train a GAN?" at NIPS2016
- NIPS 2016 Tutorial: Generative Adversarial Networks
- OpenAI - Generative Models
↑ back to Contents
🛠 Awesome GAN GitHub Projects and Tools
Genuinely awesome, widely-used GitHub repos built on GANs — usable code and tools, not just papers. Star counts update automatically.
Real-world applications and tools
| Repo | Stars | What it does |
|---|---|---|
| TencentARC/GFPGAN | Practical real-world face restoration | |
| jantic/DeOldify | Colorize and restore old photos and video (archived) |
Foundational model code (official / canonical)
| Repo | Stars | What it does |
|---|---|---|
| junyanz/pytorch-CycleGAN-and-pix2pix | Official CycleGAN + pix2pix in PyTorch | |
| NVlabs/stylegan | Official StyleGAN | |
| NVlabs/SPADE | Semantic image synthesis, a.k.a. GauGAN | |
| NVIDIA/pix2pixHD | High-resolution image synthesis and manipulation | |
| ajbrock/BigGAN-PyTorch | The author's PyTorch BigGAN |
↑ back to Contents
🧰 Implementations of various types of GANs collection
| Repo | Stars | Framework |
|---|---|---|
| nashory/gans-collection.torch | Torch7 | |
| hwalsuklee/tensorflow-generative-model-collections | TensorFlow | |
| wiseodd/generative-models | PyTorch & TensorFlow | |
| aboev/arae-tf | TensorFlow | |
| eriklindernoren/PyTorch-GAN | PyTorch — dozens of GANs | |
| eriklindernoren/Keras-GAN | Keras — many GANs | |
| NVlabs/imaginaire | PyTorch — NVIDIA image & video synthesis GANs |
↑ back to Contents
📰 Trendy AI-application Articles
- Artificial intelligence can say yes to the dress
↑ back to Contents
Author
Minchul Shin, @nashory
Any recommendations to add to the list are welcome — see CONTRIBUTING.md and feel free to make pull requests! :)
Related repositories
Master programming by recreating your favorite technologies from scratch.
A curated meta-list of curated lists organized by technology domain. The repository acts as a directory pointing to hundreds of specialized awesome lists covering programming languages, platforms, frameworks, and tooling. All content is community-contributed under the CC0 public domain dedication.
Public APIs is a community-curated GitHub repository listing free, publicly accessible APIs across a wide range of categories, with auth type, HTTPS, and CORS noted for each entry. It's a browsable reference, not a library to install.
REA is an MCP server and CLI that gives AI coding agents the ability to reverse engineer binaries, JavaScript apps, .NET assemblies, and websites. It hooks into Hopper, Ghidra, or IDA Pro for native binary work, or runs static JavaScript analysis with just Node.js. Every investigation returns an Evidence bundle that includes what was found, what was not, and the reasoning path. Setup registers REA with supported agents and walks you through connecting an analysis engine. The CLI also works standalone for terminal-first workflows.
Quick answers
Is nashory/gans-awesome-applications open source?
Yes — nashory/gans-awesome-applications ships under the CC0-1.0 license, which makes its source code freely readable (and, depending on license terms, forkable and reusable). Source: github.com/nashory/gans-awesome-applications.
What is nashory/gans-awesome-applications?
nashory/gans-awesome-applications (nashory/gans-awesome-applications) is a multi-language project on GitHub. From the project's own README: Curated list of awesome GAN applications and demo
Where do I read more about nashory/gans-awesome-applications?
This TopGit page is a snapshot — the READ ME tab shows the project's own README content (links stripped, images preserved). The GitHub repository at github.com/nashory/gans-awesome-applications is the definitive source.
Read full README in the tab above.
Still deciding about gans-awesome-applications?
One click hands the question to an AI along with this page — see what it says about gans-awesome-applications.