# GANzilla: User-Driven Direction Discovery in Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2207.08320 · HTML: https://mlsanity.com/paper/2207.08320/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 31 references that are in the map.
- First posted on arXiv 17 Jul 2022.

## Builds on (most cited first, 18 of 18)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery](https://mlsanity.com/paper/2103.17249/) (2021)
- [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)
- [Closed-Form Factorization of Latent Semantics in GANs](https://mlsanity.com/paper/2007.06600/) (2020)
- [Generating Videos with Scene Dynamics](https://mlsanity.com/paper/1609.02612/) (2016)
- [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)
- [On the "steerability" of generative adversarial networks](https://mlsanity.com/paper/1907.07171/) (2019)
- [GANalyze: Toward Visual Definitions of Cognitive Image Properties](https://mlsanity.com/paper/1906.10112/) (2019)
- [Editing in Style: Uncovering the Local Semantics of GANs](https://mlsanity.com/paper/2004.14367/) (2020)
- [EditGAN: High-Precision Semantic Image Editing](https://mlsanity.com/paper/2111.03186/) (2021)
- [Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesis](https://mlsanity.com/paper/1911.09267/) (2019)
- [Controlling generative models with continuous factors of variations](https://mlsanity.com/paper/2001.10238/) (2020)
- [Sequential Attention GAN for Interactive Image Editing](https://mlsanity.com/paper/1812.08352/) (2018)
- [GANSlider: How Users Control Generative Models for Images using Multiple Sliders with and without Feedforward Information](https://mlsanity.com/paper/2202.00965/) (2022)

## Built on by (most cited first, 7 of 7)

- [Concept Induction: Analyzing Unstructured Text with High-Level Concepts Using LLooM](https://mlsanity.com/paper/2404.12259/) (2024)
- [Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models](https://mlsanity.com/paper/2304.09337/) (2023)
- [PromptCharm: Text-to-Image Generation through Multi-modal Prompting and Refinement](https://mlsanity.com/paper/2403.04014/) (2024)
- [Next Steps for Human-Centered Generative AI: A Technical Perspective](https://mlsanity.com/paper/2306.15774/) (2023)
- [Bias and Diversity in Synthetic-based Face Recognition](https://mlsanity.com/paper/2311.03970/) (2023)
- [GANravel: User-Driven Direction Disentanglement in Generative Adversarial Networks](https://mlsanity.com/paper/2302.00079/) (2023)
- [GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment Design](https://mlsanity.com/paper/2508.15227/) (2025)

## Abstract (arXiv)

Generative Adversarial Network (GAN) is widely adopted in numerous application areas, such as data preprocessing, image editing, and creativity support. However, GAN's 'black box' nature prevents non-expert users from controlling what data a model generates, spawning a plethora of prior work that focused on algorithm-driven approaches to extract editing directions to control GAN. Complementarily, we propose a GANzilla: a user-driven tool that empowers a user with the classic scatter/gather technique to iteratively discover directions to meet their editing goals. In a study with 12 participants, GANzilla users were able to discover directions that (i) edited images to match provided examples (closed-ended tasks) and that (ii) met a high-level goal, e.g., making the face happier, while showing diversity across individuals (open-ended tasks).