# FIGR: Few-shot Image Generation with Reptile

arXiv: https://arxiv.org/abs/1901.02199 · HTML: https://mlsanity.com/paper/1901.02199/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jan 2019.

## Built on by (most cited first, 30 of 56)

- [StarVector: Generating Scalable Vector Graphics Code from Images and Text](https://mlsanity.com/paper/2312.11556/) (2023)
- [D2C: Diffusion-Denoising Models for Few-shot Conditional Generation](https://mlsanity.com/paper/2106.06819/) (2021)
- [Meta-StyleSpeech : Multi-Speaker Adaptive Text-to-Speech Generation](https://mlsanity.com/paper/2106.03153/) (2021)
- [IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers](https://mlsanity.com/paper/2304.14400/) (2023)
- [OmniSVG: A Unified Scalable Vector Graphics Generation Model](https://mlsanity.com/paper/2504.06263/) (2025)
- [Empowering LLMs to Understand and Generate Complex Vector Graphics](https://mlsanity.com/paper/2412.11102/) (2024)
- [Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment](https://mlsanity.com/paper/2203.04121/) (2022)
- [Chat2SVG: Vector Graphics Generation with Large Language Models and Image Diffusion Models](https://mlsanity.com/paper/2411.16602/) (2024)
- [Text-to-Vector Generation with Neural Path Representation](https://mlsanity.com/paper/2405.10317/) (2024)
- [Zero-shot Generative Model Adaptation via Image-specific Prompt Learning](https://mlsanity.com/paper/2304.03119/) (2023)
- [StrokeNUWA: Tokenizing Strokes for Vector Graphic Synthesis](https://mlsanity.com/paper/2401.17093/) (2024)
- [WaveGAN: Frequency-aware GAN for High-Fidelity Few-shot Image Generation](https://mlsanity.com/paper/2207.07288/) (2022)
- [The Euclidean Space is Evil: Hyperbolic Attribute Editing for Few-shot Image Generation](https://mlsanity.com/paper/2211.12347/) (2022)
- [A Comprehensive Survey on Data-Efficient GANs in Image Generation](https://mlsanity.com/paper/2204.08329/) (2022)
- [Learning Prototype-oriented Set Representations for Meta-Learning](https://mlsanity.com/paper/2110.09140/) (2021)
- [A Survey on Generative Modeling with Limited Data, Few Shots, and Zero Shot](https://mlsanity.com/paper/2307.14397/) (2023)
- [SVGenius: Benchmarking LLMs in SVG Understanding, Editing and Generation](https://mlsanity.com/paper/2506.03139/) (2025)
- [Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2203.08422/) (2022)
- [SVGen: Interpretable Vector Graphics Generation with Large Language Models](https://mlsanity.com/paper/2508.09168/) (2025)
- [Phasic Content Fusing Diffusion Model with Directional Distribution Consistency for Few-Shot Model Adaption](https://mlsanity.com/paper/2309.03729/) (2023)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [MIGS: Meta Image Generation from Scene Graphs](https://mlsanity.com/paper/2110.11918/) (2021)
- [Few-Shot Image Generation by Conditional Relaxing Diffusion Inversion](https://mlsanity.com/paper/2407.07249/) (2024)
- [One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition](https://mlsanity.com/paper/2105.05300/) (2021)
- [Few-shot Image Generation Using Discrete Content Representation](https://mlsanity.com/paper/2207.10833/) (2022)
- [Stable Attribute Group Editing for Reliable Few-shot Image Generation](https://mlsanity.com/paper/2302.00179/) (2023)
- [VectorGym: A Multi-Task Benchmark for SVG Code Generation, Sketching and Editing](https://mlsanity.com/paper/2603.29852/) (2026)
- [HypDAE: Hyperbolic Diffusion Autoencoders for Hierarchical Few-shot Image Generation](https://mlsanity.com/paper/2411.17784/) (2024)
- [IntroSVG: Learning from Rendering Feedback for Text-to-SVG Generation via an Introspective Generator-Critic Framework](https://mlsanity.com/paper/2603.09312/) (2026)
- [VFIG: Vectorizing Complex Figures in SVG with Vision-Language Models](https://mlsanity.com/paper/2603.24575/) (2026)

## Abstract (arXiv)

Generative Adversarial Networks (GAN) boast impressive capacity to generate realistic images. However, like much of the field of deep learning, they require an inordinate amount of data to produce results, thereby limiting their usefulness in generating novelty. In the same vein, recent advances in meta-learning have opened the door to many few-shot learning applications. In the present work, we propose Few-shot Image Generation using Reptile (FIGR), a GAN meta-trained with Reptile. Our model successfully generates novel images on both MNIST and Omniglot with as little as 4 images from an unseen class. We further contribute FIGR-8, a new dataset for few-shot image generation, which contains 1,548,944 icons categorized in over 18,409 classes. Trained on FIGR-8, initial results show that our model can generalize to more advanced concepts (such as "bird" and "knife") from as few as 8 samples from a previously unseen class of images and as little as 10 training steps through those 8 images. This work demonstrates the potential of training a GAN for few-shot image generation and aims to set a new benchmark for future work in the domain.