# TCFG: Tangential Damping Classifier-free Guidance

arXiv: https://arxiv.org/abs/2503.18137 · HTML: https://mlsanity.com/paper/2503.18137/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 23 of its 33 references that are in the map.
- First posted on arXiv 23 Mar 2025.

## Placed in

- Diffusion models / [Diffusion foundations and sampling](https://mlsanity.com/diffusion/diffusion-foundations-and-sampling/)

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (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)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [The Intrinsic Dimension of Images and Its Impact on Learning](https://mlsanity.com/paper/2104.08894/) (2021)
- [Diffusion Models are Minimax Optimal Distribution Estimators](https://mlsanity.com/paper/2303.01861/) (2023)
- [Improving Sample Quality of Diffusion Models Using Self-Attention Guidance](https://mlsanity.com/paper/2210.00939/) (2022)
- [CFG++: Manifold-constrained Classifier Free Guidance for Diffusion Models](https://mlsanity.com/paper/2406.08070/) (2024)
- [Score-Based Generative Models Detect Manifolds](https://mlsanity.com/paper/2206.01018/) (2022)
- [Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance](https://mlsanity.com/paper/2403.17377/) (2024)
- [No Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models](https://mlsanity.com/paper/2407.02687/) (2024)
- [Detecting Images Generated by Deep Diffusion Models using their Local Intrinsic Dimensionality](https://mlsanity.com/paper/2307.02347/) (2023)
- [A Geometric Framework for Understanding Memorization in Generative Models](https://mlsanity.com/paper/2411.00113/) (2024)
- [Losing dimensions: Geometric memorization in generative diffusion](https://mlsanity.com/paper/2410.08727/) (2024)
- [Plug-and-Play Diffusion Distillation](https://mlsanity.com/paper/2406.01954/) (2024)

## Built on by (most cited first, 15 of 15)

- [It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion Models](https://mlsanity.com/paper/2601.00090/) (2025)
- [Balanced conic rectified flow](https://mlsanity.com/paper/2510.25229/) (2025)
- [Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution](https://mlsanity.com/paper/2507.06547/) (2025)
- [Be Tangential to Manifold: Discovering Riemannian Metric for Diffusion Models](https://mlsanity.com/paper/2510.05509/) (2025)
- [Momentum Guidance: Plug-and-Play Guidance for Flow Models](https://mlsanity.com/paper/2602.20360/) (2026)
- [Noise-Level Diffusion Guidance: Well Begun is Half Done](https://mlsanity.com/paper/2509.13936/) (2025)
- [Controllable Stylistic Text Generation with Train-Time Attribute-Regularized Diffusion](https://mlsanity.com/paper/2510.06386/) (2025)
- [Spectral Prior for Reducing Exposure Bias in Diffusion Models](https://mlsanity.com/paper/2607.22091/) (2026)
- [TAG: Tangential Amplifying Guidance for Hallucination-Resistant Sampling](https://mlsanity.com/paper/2510.04533/) (2025)
- [Guiding Diffusion Models with Semantically Degraded Conditions](https://mlsanity.com/paper/2603.10780/) (2026)
- [GeoEdit: Local Frames for Fast, Training-Free On-Manifold Editing in Diffusion Models](https://mlsanity.com/paper/2604.24238/) (2026)
- [Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models](https://mlsanity.com/paper/2608.16786/) (2026)
- [Correcting Guided Diffusion Trajectories with Spectral Alignment](https://mlsanity.com/paper/2610.02753/) (2026)
- [Geometry-Aware Preference Optimization for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2610.04980/) (2026)
- [TrajCFG: Token-Wise Classifier-Free Guidance via Denoising Trajectory Feedback](https://mlsanity.com/paper/2610.14153/) (2026)

## Abstract (arXiv)

Diffusion models have achieved remarkable success in text-to-image synthesis, largely attributed to the use of classifier-free guidance (CFG), which enables high-quality, condition-aligned image generation. CFG combines the conditional score (e.g., text-conditioned) with the unconditional score to control the output. However, the unconditional score is in charge of estimating the transition between manifolds of adjacent timesteps from xt to xt-1, which may inadvertently interfere with the trajectory toward the specific condition. In this work, we introduce a novel approach that leverages a geometric perspective on the unconditional score to enhance CFG performance when conditional scores are available. Specifically, we propose a method that filters the singular vectors of both conditional and unconditional scores using singular value decomposition. This filtering process aligns the unconditional score with the conditional score, thereby refining the sampling trajectory to stay closer to the manifold. Our approach improves image quality with negligible additional computation. We provide deeper insights into the score function behavior in diffusion models and present a practical technique for achieving more accurate and contextually coherent image synthesis.