# Not Every Image is Worth a Thousand Words: Quantifying Originality in Stable Diffusion

arXiv: https://arxiv.org/abs/2408.08184 · HTML: https://mlsanity.com/paper/2408.08184/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Robustness, privacy and adversarial aspects, one of 14 directions in Diffusion models.
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Placed in

- Diffusion models / [Robustness, privacy and adversarial aspects](https://mlsanity.com/diffusion/robustness-privacy-and-adversarial-aspects/)

## Builds on (most cited first, 24 of 24)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Extracting Training Data from Diffusion Models](https://mlsanity.com/paper/2301.13188/) (2023)
- [Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2301.13826/) (2023)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Scalable Extraction of Training Data from (Production) Language Models](https://mlsanity.com/paper/2311.17035/) (2023)
- [DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data](https://mlsanity.com/paper/2306.09344/) (2023)
- [Stronger generalization bounds for deep nets via a compression approach](https://mlsanity.com/paper/1802.05296/) (2018)
- [Information-theoretic analysis of generalization capability of learning algorithms](https://mlsanity.com/paper/1705.07809/) (2017)
- [Reconstructing Training Data from Trained Neural Networks](https://mlsanity.com/paper/2206.07758/) (2022)
- [On Provable Copyright Protection for Generative Models](https://mlsanity.com/paper/2302.10870/) (2023)
- [How much does your data exploration overfit? Controlling bias via information usage](https://mlsanity.com/paper/1511.05219/) (2015)
- [Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task](https://mlsanity.com/paper/2310.09336/) (2023)
- [Bias and Generalization in Deep Generative Models: An Empirical Study](https://mlsanity.com/paper/1811.03259/) (2018)
- [Talkin' 'Bout AI Generation: Copyright and the Generative-AI Supply Chain](https://mlsanity.com/paper/2309.08133/) (2023)
- [Can Copyright be Reduced to Privacy?](https://mlsanity.com/paper/2305.14822/) (2023)
- [Information Theoretic Lower Bounds for Information Theoretic Upper Bounds](https://mlsanity.com/paper/2302.04925/) (2023)
- [Formalizing Human Ingenuity: A Quantitative Framework for Copyright Law's Substantial Similarity](https://mlsanity.com/paper/2206.01230/) (2022)
- [Information Complexity of Stochastic Convex Optimization: Applications to Generalization and Memorization](https://mlsanity.com/paper/2402.09327/) (2024)
- [Not All Similarities Are Created Equal: Leveraging Data-Driven Biases to Inform GenAI Copyright Disputes](https://mlsanity.com/paper/2403.17691/) (2024)

## Built on by (most cited first, 4 of 4)

- [ImageRAG: Dynamic Image Retrieval for Reference-Guided Image Generation](https://mlsanity.com/paper/2502.09411/) (2025)
- [Beyond Flat Text: Dual Self-inherited Guidance for Visual Text Generation](https://mlsanity.com/paper/2501.05892/) (2025)
- [Reconstructing Template-Memorized Images from Natural Prompts](https://mlsanity.com/paper/2507.07947/) (2025)
- [We Should Separate Memorization from Copyright](https://mlsanity.com/paper/2602.08632/) (2026)

## Abstract (arXiv)

This work addresses the challenge of quantifying originality in text-to-image (T2I) generative diffusion models, with a focus on copyright originality. We begin by evaluating T2I models' ability to innovate and generalize through controlled experiments, revealing that stable diffusion models can effectively recreate unseen elements with sufficiently diverse training data. Then, our key insight is that concepts and combinations of image elements the model is familiar with, and saw more during training, are more concisly represented in the model's latent space. We hence propose a method that leverages textual inversion to measure the originality of an image based on the number of tokens required for its reconstruction by the model. Our approach is inspired by legal definitions of originality and aims to assess whether a model can produce original content without relying on specific prompts or having the training data of the model. We demonstrate our method using both a pre-trained stable diffusion model and a synthetic dataset, showing a correlation between the number of tokens and image originality. This work contributes to the understanding of originality in generative models and has implications for copyright infringement cases.