# Slimmable Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2012.05660 · HTML: https://mlsanity.com/paper/2012.05660/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Dec 2020.

## Built on by (most cited first, 27 of 27)

- [Anycost GANs for Interactive Image Synthesis and Editing](https://mlsanity.com/paper/2103.03243/) (2021)
- [Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models](https://mlsanity.com/paper/2211.02048/) (2022)
- [Online Multi-Granularity Distillation for GAN Compression](https://mlsanity.com/paper/2108.06908/) (2021)
- [Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme](https://mlsanity.com/paper/2110.14439/) (2021)
- [Conditional GANs with Auxiliary Discriminative Classifier](https://mlsanity.com/paper/2107.10060/) (2021)
- [SlimmeRF: Slimmable Radiance Fields](https://mlsanity.com/paper/2312.10034/) (2023)
- [FlexGaussian: Flexible and Cost-Effective Training-Free Compression for 3D Gaussian Splatting](https://mlsanity.com/paper/2507.06671/) (2025)
- [Mind the Gap in Distilling StyleGANs](https://mlsanity.com/paper/2208.08840/) (2022)
- [Self-Supervised GANs with Label Augmentation](https://mlsanity.com/paper/2106.08601/) (2021)
- [Balanced Training for Sparse GANs](https://mlsanity.com/paper/2302.14670/) (2023)
- [Augmentation-Aware Self-Supervision for Data-Efficient GAN Training](https://mlsanity.com/paper/2205.15677/) (2022)
- [Efficient Controllable Multi-Task Architectures](https://mlsanity.com/paper/2308.11744/) (2023)
- [Generative Optimization Networks for Memory Efficient Data Generation](https://mlsanity.com/paper/2110.02912/) (2021)
- [Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs](https://mlsanity.com/paper/2206.14658/) (2022)
- [SlimSeg: Slimmable Semantic Segmentation with Boundary Supervision](https://mlsanity.com/paper/2207.06242/) (2022)
- [Can We Find Strong Lottery Tickets in Generative Models?](https://mlsanity.com/paper/2212.08311/) (2022)
- [Discriminator-Cooperated Feature Map Distillation for GAN Compression](https://mlsanity.com/paper/2212.14169/) (2022)
- [Head3D: Complete 3D Head Generation via Tri-plane Feature Distillation](https://mlsanity.com/paper/2303.15892/) (2023)
- [UGC: Unified GAN Compression for Efficient Image-to-Image Translation](https://mlsanity.com/paper/2309.09310/) (2023)
- [Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold](https://mlsanity.com/paper/2312.14776/) (2023)
- [CoroNetGAN: Controlled Pruning of GANs via Hypernetworks](https://mlsanity.com/paper/2403.08261/) (2024)
- [Nickel and Diming Your GAN: A Dual-Method Approach to Enhancing GAN Efficiency via Knowledge Distillation](https://mlsanity.com/paper/2405.11614/) (2024)
- [Exploring Content Relationships for Distilling Efficient GANs](https://mlsanity.com/paper/2212.11091/) (2022)
- [DGL-GAN: Discriminator Guided Learning for GAN Compression](https://mlsanity.com/paper/2112.06502/) (2021)
- [Towards Device Efficient Conditional Image Generation](https://mlsanity.com/paper/2203.10363/) (2022)
- [Hybrid Data-Free Knowledge Distillation](https://mlsanity.com/paper/2412.13525/) (2024)
- [OFA-Diffusion Compression: Compressing Diffusion Model in One-Shot Manner](https://mlsanity.com/paper/2604.12668/) (2026)

## Abstract (arXiv)

Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models makes them challenging to deploy widely in practical applications. In particular, for real-time generation tasks, different devices require generators of different sizes due to varying computing power. In this paper, we introduce slimmable GANs (SlimGANs), which can flexibly switch the width of the generator to accommodate various quality-efficiency trade-offs at runtime. Specifically, we leverage multiple discriminators that share partial parameters to train the slimmable generator. To facilitate the textitconsistency between generators of different widths, we present a stepwise inplace distillation technique that encourages narrow generators to learn from wide ones. As for class-conditional generation, we propose a sliceable conditional batch normalization that incorporates the label information into different widths. Our methods are validated, both quantitatively and qualitatively, by extensive experiments and a detailed ablation study.