# StyleGAN2 Distillation for Feed-forward Image Manipulation

arXiv: https://arxiv.org/abs/2003.03581 · HTML: https://mlsanity.com/paper/2003.03581/

## Key facts

- Cited by 78 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2020.

## Built on by (most cited first, 30 of 78)

- [InstructPix2Pix: Learning to Follow Image Editing Instructions](https://mlsanity.com/paper/2211.09800/) (2022)
- [GAN Inversion: A Survey](https://mlsanity.com/paper/2101.05278/) (2021)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization](https://mlsanity.com/paper/2104.05833/) (2021)
- [Only a Matter of Style: Age Transformation Using a Style-Based Regression Model](https://mlsanity.com/paper/2102.02754/) (2021)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [A Latent Transformer for Disentangled Face Editing in Images and Videos](https://mlsanity.com/paper/2106.11895/) (2021)
- [CLIP-GEN: Language-Free Training of a Text-to-Image Generator with CLIP](https://mlsanity.com/paper/2203.00386/) (2022)
- [Countering Malicious DeepFakes: Survey, Battleground, and Horizon](https://mlsanity.com/paper/2103.00218/) (2021)
- [Enjoy Your Editing: Controllable GANs for Image Editing via Latent Space Navigation](https://mlsanity.com/paper/2102.01187/) (2021)
- [Ensembling with Deep Generative Views](https://mlsanity.com/paper/2104.14551/) (2021)
- [Training on Thin Air: Improve Image Classification with Generated Data](https://mlsanity.com/paper/2305.15316/) (2023)
- [BlendGAN: Implicitly GAN Blending for Arbitrary Stylized Face Generation](https://mlsanity.com/paper/2110.11728/) (2021)
- [PVA: Pixel-aligned Volumetric Avatars](https://mlsanity.com/paper/2101.02697/) (2021)
- [EditWorld: Simulating World Dynamics for Instruction-Following Image Editing](https://mlsanity.com/paper/2405.14785/) (2024)
- [Content-Aware GAN Compression](https://mlsanity.com/paper/2104.02244/) (2021)
- [Temporally Consistent Semantic Video Editing](https://mlsanity.com/paper/2206.10590/) (2022)
- [Face Generation and Editing with StyleGAN: A Survey](https://mlsanity.com/paper/2212.09102/) (2022)
- [GLFF: Global and Local Feature Fusion for AI-synthesized Image Detection](https://mlsanity.com/paper/2211.08615/) (2022)
- [Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP](https://mlsanity.com/paper/2107.12518/) (2021)
- [Debiased Fine-Tuning for Vision-language Models by Prompt Regularization](https://mlsanity.com/paper/2301.12429/) (2023)
- [SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision](https://mlsanity.com/paper/2303.17200/) (2023)
- [AnomalyXFusion: Multi-modal Anomaly Synthesis with Diffusion](https://mlsanity.com/paper/2404.19444/) (2024)
- [Arbitrary-Scale Image Synthesis](https://mlsanity.com/paper/2204.02273/) (2022)
- [VToonify: Controllable High-Resolution Portrait Video Style Transfer](https://mlsanity.com/paper/2209.11224/) (2022)
- [Personalized Image Generation with Deep Generative Models: A Decade Survey](https://mlsanity.com/paper/2502.13081/) (2025)
- [StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces](https://mlsanity.com/paper/2303.06146/) (2023)
- [Synthetic ID Card Image Generation for Improving Presentation Attack Detection](https://mlsanity.com/paper/2211.00098/) (2022)
- [DoodleFormer: Creative Sketch Drawing with Transformers](https://mlsanity.com/paper/2112.03258/) (2021)

## Abstract (arXiv)

StyleGAN2 is a state-of-the-art network in generating realistic images. Besides, it was explicitly trained to have disentangled directions in latent space, which allows efficient image manipulation by varying latent factors. Editing existing images requires embedding a given image into the latent space of StyleGAN2. Latent code optimization via backpropagation is commonly used for qualitative embedding of real world images, although it is prohibitively slow for many applications. We propose a way to distill a particular image manipulation of StyleGAN2 into image-to-image network trained in paired way. The resulting pipeline is an alternative to existing GANs, trained on unpaired data. We provide results of human faces' transformation: gender swap, aging/rejuvenation, style transfer and image morphing. We show that the quality of generation using our method is comparable to StyleGAN2 backpropagation and current state-of-the-art methods in these particular tasks.