# DogFit: Domain-guided Fine-tuning for Efficient Transfer Learning of Diffusion Models

arXiv: https://arxiv.org/abs/2508.05685 · HTML: https://mlsanity.com/paper/2508.05685/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models.
- Builds on 32 of its 56 references that are in the map.
- First posted on arXiv 5 Aug 2025.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [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)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [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)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [Imagic: Text-Based Real Image Editing with Diffusion Models](https://mlsanity.com/paper/2210.09276/) (2022)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Improved Precision and Recall Metric for Assessing Generative Models](https://mlsanity.com/paper/1904.06991/) (2019)
- [Parameter-Efficient Transfer Learning with Diff Pruning](https://mlsanity.com/paper/2012.07463/) (2020)
- [Photorealistic Video Generation with Diffusion Models](https://mlsanity.com/paper/2312.06662/) (2023)
- [Perception Prioritized Training of Diffusion Models](https://mlsanity.com/paper/2204.00227/) (2022)
- [Guiding a Diffusion Model with a Bad Version of Itself](https://mlsanity.com/paper/2406.02507/) (2024)
- [Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models](https://mlsanity.com/paper/2404.07724/) (2024)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [Score Approximation, Estimation and Distribution Recovery of Diffusion Models on Low-Dimensional Data](https://mlsanity.com/paper/2302.07194/) (2023)
- [CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling](https://mlsanity.com/paper/2310.17347/) (2023)
- [Improved Techniques for Maximum Likelihood Estimation for Diffusion ODEs](https://mlsanity.com/paper/2305.03935/) (2023)
- [Efficient Diffusion Models: A Survey](https://mlsanity.com/paper/2502.06805/) (2025)
- [Diffusion Models without Classifier-free Guidance](https://mlsanity.com/paper/2502.12154/) (2025)
- [Characteristic Guidance: Non-linear Correction for Diffusion Model at Large Guidance Scale](https://mlsanity.com/paper/2312.07586/) (2023)
- [Few-shot Image Generation with Diffusion Models](https://mlsanity.com/paper/2211.03264/) (2022)
- [Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting](https://mlsanity.com/paper/2406.00773/) (2024)
- [Expanding Expressiveness of Diffusion Models with Limited Data via Self-Distillation based Fine-Tuning](https://mlsanity.com/paper/2311.01018/) (2023)
- [Unconditional Priors Matter! Improving Conditional Generation of Fine-Tuned Diffusion Models](https://mlsanity.com/paper/2503.20240/) (2025)
- [Domain Guidance: A Simple Transfer Approach for a Pre-trained Diffusion Model](https://mlsanity.com/paper/2504.01521/) (2025)

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

- [Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching](https://mlsanity.com/paper/2601.06514/) (2026)
- [Uni-DAD: Unified Distillation and Adaptation of Diffusion Models for Few-step Few-shot Image Generation](https://mlsanity.com/paper/2511.18281/) (2025)
- [Cross-Modal Generation: From Commodity WiFi to High-Fidelity mmWave and RFID Sensing](https://mlsanity.com/paper/2604.16558/) (2026)
- [Continuous Adversarial MeanFlow Transfer](https://mlsanity.com/paper/2608.19540/) (2026)

## Abstract (arXiv)

Transfer learning of diffusion models to smaller target domains is challenging, as naively fine-tuning the model often results in poor generalization. Test-time guidance methods help mitigate this by offering controllable improvements in image fidelity through a trade-off with sample diversity. However, this benefit comes at a high computational cost, typically requiring dual forward passes during sampling. We propose the Domain-guided Fine-tuning (DogFit) method, an effective guidance mechanism for diffusion transfer learning that maintains controllability without incurring additional computational overhead. DogFit injects a domain-aware guidance offset into the training loss, effectively internalizing the guided behavior during the fine-tuning process. The domain-aware design is motivated by our observation that during fine-tuning, the unconditional source model offers a stronger marginal estimate than the target model. To support efficient controllable fidelity-diversity trade-offs at inference, we encode the guidance strength value as an additional model input through a lightweight conditioning mechanism. We further investigate the optimal placement and timing of the guidance offset during training and propose two simple scheduling strategies, i.e., late-start and cut-off, which improve generation quality and training stability. Experiments on DiT and SiT backbones across six diverse target domains show that DogFit can outperform prior guidance methods in transfer learning in terms of FID and FDDINOV2 while requiring up to 2x fewer sampling TFLOPS.