# Analysis of Classifier-Free Guidance Weight Schedulers

arXiv: https://arxiv.org/abs/2404.13040 · HTML: https://mlsanity.com/paper/2404.13040/

## Key facts

- Cited by 68 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 36 of its 44 references that are in the map.
- First posted on arXiv 19 Apr 2024.

## Placed in

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

## Builds on (most cited first, 30 of 36)

- [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)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [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)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [LAION-5B: An open large-scale dataset for training next generation image-text models](https://mlsanity.com/paper/2210.08402/) (2022)
- [Improved Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2102.09672/) (2021)
- [Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow](https://mlsanity.com/paper/2209.03003/) (2022)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2211.01095/) (2022)
- [eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers](https://mlsanity.com/paper/2211.01324/) (2022)
- [Blended Diffusion for Text-driven Editing of Natural Images](https://mlsanity.com/paper/2111.14818/) (2021)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Muse: Text-To-Image Generation via Masked Generative Transformers](https://mlsanity.com/paper/2301.00704/) (2023)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [Scaling up GANs for Text-to-Image Synthesis](https://mlsanity.com/paper/2303.05511/) (2023)
- [VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation](https://mlsanity.com/paper/2303.08320/) (2023)
- [Your Diffusion Model is Secretly a Zero-Shot Classifier](https://mlsanity.com/paper/2303.16203/) (2023)
- [MDTv2: Masked Diffusion Transformer is a Strong Image Synthesizer](https://mlsanity.com/paper/2303.14389/) (2023)
- [Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models](https://mlsanity.com/paper/2404.07724/) (2024)

## Built on by (most cited first, 30 of 68)

- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator](https://mlsanity.com/paper/2405.07510/) (2024)
- [PixelFlow: Pixel-Space Generative Models with Flow](https://mlsanity.com/paper/2504.07963/) (2025)
- [CFG-Zero*: Improved Classifier-Free Guidance for Flow Matching Models](https://mlsanity.com/paper/2503.18886/) (2025)
- [Dynamic Negative Guidance of Diffusion Models](https://mlsanity.com/paper/2410.14398/) (2024)
- [OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers](https://mlsanity.com/paper/2505.21448/) (2025)
- [Shielded Diffusion: Generating Novel and Diverse Images using Sparse Repellency](https://mlsanity.com/paper/2410.06025/) (2024)
- [Classifier-Free Guidance inside the Attraction Basin May Cause Memorization](https://mlsanity.com/paper/2411.16738/) (2024)
- [LightningDrag: Lightning Fast and Accurate Drag-based Image Editing Emerging from Videos](https://mlsanity.com/paper/2405.13722/) (2024)
- [Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models](https://mlsanity.com/paper/2504.17789/) (2025)
- [Rectified-CFG++ for Flow Based Models](https://mlsanity.com/paper/2510.07631/) (2025)
- [Feedback Guidance of Diffusion Models](https://mlsanity.com/paper/2506.06085/) (2025)
- [Guiding a Diffusion Transformer with the Internal Dynamics of Itself](https://mlsanity.com/paper/2512.24176/) (2025)
- [Guidance in the Frequency Domain Enables High-Fidelity Sampling at Low CFG Scales](https://mlsanity.com/paper/2506.19713/) (2025)
- [The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation](https://mlsanity.com/paper/2412.05101/) (2024)
- [Learn to Guide Your Diffusion Model](https://mlsanity.com/paper/2510.00815/) (2025)
- [Effective and Efficient Masked Image Generation Models](https://mlsanity.com/paper/2503.07197/) (2025)
- [MixerMDM: Learnable Composition of Human Motion Diffusion Models](https://mlsanity.com/paper/2504.01019/) (2025)
- [Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models](https://mlsanity.com/paper/2505.21179/) (2025)
- [Dynamic Classifier-Free Diffusion Guidance via Online Feedback](https://mlsanity.com/paper/2509.16131/) (2025)
- [Entropy Rectifying Guidance for Diffusion and Flow Models](https://mlsanity.com/paper/2504.13987/) (2025)
- [Improving Classifier-Free Guidance in Masked Diffusion: Low-Dim Theoretical Insights with High-Dim Impact](https://mlsanity.com/paper/2507.08965/) (2025)
- [Gradient-Free Classifier Guidance for Diffusion Model Sampling](https://mlsanity.com/paper/2411.15393/) (2024)
- [REG: Rectified Gradient Guidance for Conditional Diffusion Models](https://mlsanity.com/paper/2501.18865/) (2025)
- [CFG-Ctrl: Control-Based Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2603.03281/) (2026)
- [C2FG: Control Classifier-Free Guidance via Score Discrepancy Analysis](https://mlsanity.com/paper/2603.08155/) (2026)
- [Efficient Distillation of Classifier-Free Guidance using Adapters](https://mlsanity.com/paper/2503.07274/) (2025)
- [Conditional Diffusion Models with Classifier-Free Gibbs-like Guidance](https://mlsanity.com/paper/2505.21101/) (2025)
- [Mitigating Diffusion Model Hallucinations with Dynamic Guidance](https://mlsanity.com/paper/2510.05356/) (2025)
- [Diffusion Reinforcement Learning via Centered Reward Distillation](https://mlsanity.com/paper/2603.14128/) (2026)

## Abstract (arXiv)

Classifier-Free Guidance (CFG) enhances the quality and condition adherence of text-to-image diffusion models. It operates by combining the conditional and unconditional predictions using a fixed weight. However, recent works vary the weights throughout the diffusion process, reporting superior results but without providing any rationale or analysis. By conducting comprehensive experiments, this paper provides insights into CFG weight schedulers. Our findings suggest that simple, monotonically increasing weight schedulers consistently lead to improved performances, requiring merely a single line of code. In addition, more complex parametrized schedulers can be optimized for further improvement, but do not generalize across different models and tasks.