# Demystifying Numerosity in Diffusion Models -- Limitations and Remedies

arXiv: https://arxiv.org/abs/2510.11117 · HTML: https://mlsanity.com/paper/2510.11117/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models.
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 13 Oct 2025.

## Placed in

- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 30 of 31)

- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Qwen-Image Technical Report](https://mlsanity.com/paper/2508.02324/) (2025)
- [GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment](https://mlsanity.com/paper/2310.11513/) (2023)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [DeepSeek LLM: Scaling Open-Source Language Models with Longtermism](https://mlsanity.com/paper/2401.02954/) (2024)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis](https://mlsanity.com/paper/2212.05032/) (2022)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [Diffusion Self-Guidance for Controllable Image Generation](https://mlsanity.com/paper/2306.00986/) (2023)
- [Inference-Time Scaling for Diffusion Models beyond Scaling Denoising Steps](https://mlsanity.com/paper/2501.09732/) (2025)
- [InstanceDiffusion: Instance-level Control for Image Generation](https://mlsanity.com/paper/2402.03290/) (2024)
- [InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimization](https://mlsanity.com/paper/2404.04650/) (2024)
- [Self-correcting LLM-controlled Diffusion Models](https://mlsanity.com/paper/2311.16090/) (2023)
- [SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL](https://mlsanity.com/paper/2504.11455/) (2025)
- [Generating images of rare concepts using pre-trained diffusion models](https://mlsanity.com/paper/2304.14530/) (2023)
- [Guided Image Synthesis via Initial Image Editing in Diffusion Model](https://mlsanity.com/paper/2305.03382/) (2023)
- [CountGD: Multi-Modal Open-World Counting](https://mlsanity.com/paper/2407.04619/) (2024)
- [Make It Count: Text-to-Image Generation with an Accurate Number of Objects](https://mlsanity.com/paper/2406.10210/) (2024)
- [Why Do Large Language Models (LLMs) Struggle to Count Letters?](https://mlsanity.com/paper/2412.18626/) (2024)
- [All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds](https://mlsanity.com/paper/2411.18810/) (2024)
- [The Lottery Ticket Hypothesis in Denoising: Towards Semantic-Driven Initialization](https://mlsanity.com/paper/2312.08872/) (2023)
- [Towards Precise Scaling Laws for Video Diffusion Transformers](https://mlsanity.com/paper/2411.17470/) (2024)
- [The Crystal Ball Hypothesis in diffusion models: Anticipating object positions from initial noise](https://mlsanity.com/paper/2406.01970/) (2024)
- [Evaluating Numerical Reasoning in Text-to-Image Models](https://mlsanity.com/paper/2406.14774/) (2024)
- [Text-to-Image Diffusion Models Cannot Count, and Prompt Refinement Cannot Help](https://mlsanity.com/paper/2503.06884/) (2025)

## Built on by (most cited first, 2 of 2)

- [CountGD++: Generalized Prompting for Open-World Counting](https://mlsanity.com/paper/2512.23351/) (2025)
- [Advances in GRPO for Generation Models: A Survey](https://mlsanity.com/paper/2603.06623/) (2026)

## Abstract (arXiv)

Numerosity remains a challenge for state-of-the-art text-to-image generation models like FLUX and GPT-4o, which often fail to accurately follow counting instructions in text prompts. In this paper, we aim to study a fundamental yet often overlooked question: Can diffusion models inherently generate the correct number of objects specified by a textual prompt simply by scaling up the dataset and model size? To enable rigorous and reproducible evaluation, we construct a clean synthetic numerosity benchmark comprising two complementary datasets: GrayCount250 for controlled scaling studies, and NaturalCount6 featuring complex naturalistic scenes. Second, we empirically show that the scaling hypothesis does not hold: larger models and datasets alone fail to improve counting accuracy on our benchmark. Our analysis identifies a key reason: diffusion models tend to rely heavily on the noise initialization rather than the explicit numerosity specified in the prompt. We observe that noise priors exhibit biases toward specific object counts. In addition, we propose an effective strategy for controlling numerosity by injecting count-aware layout information into the noise prior. Our method achieves significant gains, improving accuracy on GrayCount250 from 20.0% to 85.3% and on NaturalCount6 from 74.8% to 86.3%, demonstrating effective generalization across settings.