# Self-Distilled StyleGAN: Towards Generation from Internet Photos

arXiv: https://arxiv.org/abs/2202.12211 · HTML: https://mlsanity.com/paper/2202.12211/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 43 references that are in the map.
- First posted on arXiv 24 Feb 2022.

## Builds on (most cited first, 30 of 33)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop](https://mlsanity.com/paper/1506.03365/) (2015)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Interpreting the Latent Space of GANs for Semantic Face Editing](https://mlsanity.com/paper/1907.10786/) (2019)
- [GANSpace: Discovering Interpretable GAN Controls](https://mlsanity.com/paper/2004.02546/) (2020)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [Pivotal Tuning for Latent-based Editing of Real Images](https://mlsanity.com/paper/2106.05744/) (2021)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [StyleFlow: Attribute-conditioned Exploration of StyleGAN-Generated Images using Conditional Continuous Normalizing Flows](https://mlsanity.com/paper/2008.02401/) (2020)
- [SinGAN: Learning a Generative Model from a Single Natural Image](https://mlsanity.com/paper/1905.01164/) (2019)
- [StyleSpace Analysis: Disentangled Controls for StyleGAN Image Generation](https://mlsanity.com/paper/2011.12799/) (2020)
- [Unsupervised Discovery of Interpretable Directions in the GAN Latent Space](https://mlsanity.com/paper/2002.03754/) (2020)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators](https://mlsanity.com/paper/2108.00946/) (2021)
- [Explaining in Style: Training a GAN to explain a classifier in StyleSpace](https://mlsanity.com/paper/2104.13369/) (2021)
- [Instance-Conditioned GAN](https://mlsanity.com/paper/2109.05070/) (2021)
- [Image Counterfactual Sensitivity Analysis for Detecting Unintended Bias](https://mlsanity.com/paper/1906.06439/) (2019)
- [Diverse Image Generation via Self-Conditioned GANs](https://mlsanity.com/paper/2006.10728/) (2020)
- [High-Fidelity Image Generation With Fewer Labels](https://mlsanity.com/paper/1903.02271/) (2019)
- [Drop the GAN: In Defense of Patches Nearest Neighbors as Single Image Generative Models](https://mlsanity.com/paper/2103.15545/) (2021)
- [Pose with Style: Detail-Preserving Pose-Guided Image Synthesis with Conditional StyleGAN](https://mlsanity.com/paper/2109.06166/) (2021)
- [Inclusive GAN: Improving Data and Minority Coverage in Generative Models](https://mlsanity.com/paper/2004.03355/) (2020)
- [TryOnGAN: Body-Aware Try-On via Layered Interpolation](https://mlsanity.com/paper/2101.02285/) (2021)

## Built on by (most cited first, 30 of 37)

- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [Drag Your GAN: Interactive Point-based Manipulation on the Generative Image Manifold](https://mlsanity.com/paper/2305.10973/) (2023)
- [Orthogonal Adaptation for Modular Customization of Diffusion Models](https://mlsanity.com/paper/2312.02432/) (2023)
- [3D-aware Image Generation using 2D Diffusion Models](https://mlsanity.com/paper/2303.17905/) (2023)
- [ZONE: Zero-Shot Instruction-Guided Local Editing](https://mlsanity.com/paper/2312.16794/) (2023)
- [DeepPrivacy2: Towards Realistic Full-Body Anonymization](https://mlsanity.com/paper/2211.09454/) (2022)
- [ArtFID: Quantitative Evaluation of Neural Style Transfer](https://mlsanity.com/paper/2207.12280/) (2022)
- [3D generation on ImageNet](https://mlsanity.com/paper/2303.01416/) (2023)
- [Neural Congealing: Aligning Images to a Joint Semantic Atlas](https://mlsanity.com/paper/2302.03956/) (2023)
- [FreeDrag: Feature Dragging for Reliable Point-based Image Editing](https://mlsanity.com/paper/2307.04684/) (2023)
- [MyStyle: A Personalized Generative Prior](https://mlsanity.com/paper/2203.17272/) (2022)
- [Nested Attention: Semantic-aware Attention Values for Concept Personalization](https://mlsanity.com/paper/2501.01407/) (2025)
- [Generalized One-shot Domain Adaptation of Generative Adversarial Networks](https://mlsanity.com/paper/2209.03665/) (2022)
- [A Survey on Deep Generative 3D-aware Image Synthesis](https://mlsanity.com/paper/2210.14267/) (2022)
- [SAOR: Single-View Articulated Object Reconstruction](https://mlsanity.com/paper/2303.13514/) (2023)
- [Domain Expansion of Image Generators](https://mlsanity.com/paper/2301.05225/) (2023)
- [Does Image Anonymization Impact Computer Vision Training?](https://mlsanity.com/paper/2306.05135/) (2023)
- [TransMRSR: Transformer-based Self-Distilled Generative Prior for Brain MRI Super-Resolution](https://mlsanity.com/paper/2306.06669/) (2023)
- [WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space](https://mlsanity.com/paper/2311.13570/) (2023)
- [AdaptiveDrag: Semantic-Driven Dragging on Diffusion-Based Image Editing](https://mlsanity.com/paper/2410.12696/) (2024)
- [Content-Based Search for Deep Generative Models](https://mlsanity.com/paper/2210.03116/) (2022)
- [POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Image Generation](https://mlsanity.com/paper/2504.13392/) (2025)
- [Regularizing Neural Networks with Meta-Learning Generative Models](https://mlsanity.com/paper/2307.13899/) (2023)
- [Disentangling Structure and Appearance in ViT Feature Space](https://mlsanity.com/paper/2311.12193/) (2023)
- [G3DR: Generative 3D Reconstruction in ImageNet](https://mlsanity.com/paper/2403.00939/) (2024)
- [CustomSketching: Sketch Concept Extraction for Sketch-based Image Synthesis and Editing](https://mlsanity.com/paper/2402.17624/) (2024)
- [Learning 3D-Aware GANs from Unposed Images with Template Feature Field](https://mlsanity.com/paper/2404.05705/) (2024)
- [DISC: Latent Diffusion Models with Self-Distillation from Separated Conditions for Prostate Cancer Grading](https://mlsanity.com/paper/2404.13097/) (2024)

## Abstract (arXiv)

StyleGAN is known to produce high-fidelity images, while also offering unprecedented semantic editing. However, these fascinating abilities have been demonstrated only on a limited set of datasets, which are usually structurally aligned and well curated. In this paper, we show how StyleGAN can be adapted to work on raw uncurated images collected from the Internet. Such image collections impose two main challenges to StyleGAN: they contain many outlier images, and are characterized by a multi-modal distribution. Training StyleGAN on such raw image collections results in degraded image synthesis quality. To meet these challenges, we proposed a StyleGAN-based self-distillation approach, which consists of two main components: (i) A generative-based self-filtering of the dataset to eliminate outlier images, in order to generate an adequate training set, and (ii) Perceptual clustering of the generated images to detect the inherent data modalities, which are then employed to improve StyleGAN's "truncation trick" in the image synthesis process. The presented technique enables the generation of high-quality images, while minimizing the loss in diversity of the data. Through qualitative and quantitative evaluation, we demonstrate the power of our approach to new challenging and diverse domains collected from the Internet. New datasets and pre-trained models are available at https://self-distilled-stylegan.github.io/ .