# GPIC: A Giant Permissive Image Corpus for Visual Generation

arXiv: https://arxiv.org/abs/2605.30341 · HTML: https://mlsanity.com/paper/2605.30341/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 42 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 22 of 22)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Neural Discrete Representation Learning](https://mlsanity.com/paper/1711.00937/) (2017)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Taming Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2012.09841/) (2020)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction](https://mlsanity.com/paper/2404.02905/) (2024)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [Reliable Fidelity and Diversity Metrics for Generative Models](https://mlsanity.com/paper/2002.09797/) (2020)
- [Assessing Generative Models via Precision and Recall](https://mlsanity.com/paper/1806.00035/) (2018)
- [Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models](https://mlsanity.com/paper/2501.01423/) (2025)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [A Self-Supervised Descriptor for Image Copy Detection](https://mlsanity.com/paper/2202.10261/) (2022)
- [Simpler Diffusion (SiD2): 1.5 FID on ImageNet512 with pixel-space diffusion](https://mlsanity.com/paper/2410.19324/) (2024)
- [Qwen-Image-VAE-2.0 Technical Report](https://mlsanity.com/paper/2605.13565/) (2026)

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

- [GEAR: Guided End-to-End AutoRegression for Image Synthesis](https://mlsanity.com/paper/2606.32039/) (2026)
- [Scaling Muon for Diffusion Transformers](https://mlsanity.com/paper/2608.20818/) (2026)
- [There and Back Again: Bidirectional Diffusion Bridges for Multimodality Translation](https://mlsanity.com/paper/2608.27885/) (2026)
- [Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States](https://mlsanity.com/paper/2609.04196/) (2026)
- [Visualizing Distribution Coverage in Generative Diffusion Models](https://mlsanity.com/paper/2609.38853/) (2026)
- [Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces](https://mlsanity.com/paper/2609.40362/) (2026)
- [Generative Representation Learning for Scalable Latent Tokenization](https://mlsanity.com/paper/2610.20533/) (2026)

## Abstract (arXiv)

Studying scalable methods for visual generative modeling requires large, accessible, and stable datasets. We introduce GPIC, a Giant Permissive Image Corpus of approximately 28 trillion pixels. GPIC comprises diverse internet images captioned by a state-of-the-art vision-language model, including 100M training, 200K validation, and 1M test examples. Moreover, all GPIC images are permissively licensed for both research and commercial use. GPIC is safety-filtered, deduplicated, and centrally hosted on Hugging Face. We provide a benchmarking protocol for generative modeling on GPIC. Finally, we provide a reference baseline for pixel-space flow matching on GPIC. Our dataset, benchmark, and models are available at https://huggingface.co/datasets/stanford-vision-lab/gpic. Evaluation toolkit and code are available at https://gpic.stanford.edu