# CountDiffusion: Text-to-Image Synthesis with Training-Free Counting-Guidance Diffusion

arXiv: https://arxiv.org/abs/2505.04347 · HTML: https://mlsanity.com/paper/2505.04347/

## Key facts

- Cited by 3 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 37 references that are in the map.
- First posted on arXiv 7 May 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)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Prompt-to-Prompt Image Editing with Cross Attention Control](https://mlsanity.com/paper/2208.01626/) (2022)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks](https://mlsanity.com/paper/2401.14159/) (2024)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2108.02938/) (2021)
- [Universal Guidance for Diffusion Models](https://mlsanity.com/paper/2302.07121/) (2023)
- [Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors](https://mlsanity.com/paper/2306.17843/) (2023)
- [Inversion-Based Style Transfer with Diffusion Models](https://mlsanity.com/paper/2211.13203/) (2022)
- [BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion](https://mlsanity.com/paper/2307.10816/) (2023)
- [Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance](https://mlsanity.com/paper/2403.14781/) (2024)
- [More Control for Free! Image Synthesis with Semantic Diffusion Guidance](https://mlsanity.com/paper/2112.05744/) (2021)
- [InstanceDiffusion: Instance-level Control for Image Generation](https://mlsanity.com/paper/2402.03290/) (2024)
- [Dense Text-to-Image Generation with Attention Modulation](https://mlsanity.com/paper/2308.12964/) (2023)
- [RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation](https://mlsanity.com/paper/2211.09869/) (2022)
- [Learning What and Where to Draw](https://mlsanity.com/paper/1610.02454/) (2016)
- [LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation](https://mlsanity.com/paper/2308.05095/) (2023)
- [Ranni: Taming Text-to-Image Diffusion for Accurate Instruction Following](https://mlsanity.com/paper/2311.17002/) (2023)
- [MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators](https://mlsanity.com/paper/2404.05014/) (2024)
- [Make It Count: Text-to-Image Generation with an Accurate Number of Objects](https://mlsanity.com/paper/2406.10210/) (2024)
- [SceneComposer: Any-Level Semantic Image Synthesis](https://mlsanity.com/paper/2211.11742/) (2022)
- [Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive](https://mlsanity.com/paper/2401.08815/) (2024)

## Built on by (most cited first, 3 of 3)

- [Transferability Between Understanding and Generation in Unified Multimodal Models](https://mlsanity.com/paper/2607.04423/) (2026)
- [LGTM: Training-Free Light-Guided Text-to-Image Diffusion Model via Initial Noise Manipulation](https://mlsanity.com/paper/2603.24086/) (2026)
- [ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models](https://mlsanity.com/paper/2603.19676/) (2026)

## Abstract (arXiv)

Stable Diffusion has advanced text-to-image synthesis, but training models to generate images with accurate object quantity is still difficult due to the high computational cost and the challenge of teaching models the abstract concept of quantity. In this paper, we propose CountDiffusion, a training-free framework aiming at generating images with correct object quantity from textual descriptions. CountDiffusion consists of two stages. In the first stage, an intermediate denoising result is generated by the diffusion model to predict the final synthesized image with one-step denoising, and a counting model is used to count the number of objects in this image. In the second stage, a correction module is used to correct the object quantity by changing the attention map of the object with universal guidance. The proposed CountDiffusion can be plugged into any diffusion-based text-to-image (T2I) generation models without further training. Experiment results demonstrate the superiority of our proposed CountDiffusion, which improves the accurate object quantity generation ability of T2I models by a large margin.