Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting

• URL: http://arxiv.org/abs/2406.00773v2
• Date: Thu, 6 Jun 2024 10:08:22 GMT
• Title: Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
• Authors: Jincheng Zhong, Xingzhuo Guo, Jiaxiang Dong, Mingsheng Long,
• Abstract summary: We present Diff-Tuning, a frustratingly simple transfer approach that leverages the chain of forgetting tendency. D Diff-Tuning achieves a 26% improvement over standard fine-tuning and enhances the convergence speed of ControlNet by 24%.
• Score: 41.75432332679519
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diffusion models have significantly advanced the field of generative modeling. However, training a diffusion model is computationally expensive, creating a pressing need to adapt off-the-shelf diffusion models for downstream generation tasks. Current fine-tuning methods focus on parameter-efficient transfer learning but overlook the fundamental transfer characteristics of diffusion models. In this paper, we investigate the transferability of diffusion models and observe a monotonous chain of forgetting trend of transferability along the reverse process. Based on this observation and novel theoretical insights, we present Diff-Tuning, a frustratingly simple transfer approach that leverages the chain of forgetting tendency. Diff-Tuning encourages the fine-tuned model to retain the pre-trained knowledge at the end of the denoising chain close to the generated data while discarding the other noise side. We conduct comprehensive experiments to evaluate Diff-Tuning, including the transfer of pre-trained Diffusion Transformer models to eight downstream generations and the adaptation of Stable Diffusion to five control conditions with ControlNet. Diff-Tuning achieves a 26% improvement over standard fine-tuning and enhances the convergence speed of ControlNet by 24%. Notably, parameter-efficient transfer learning techniques for diffusion models can also benefit from Diff-Tuning.

Related papers

• Diff2Flow: Training Flow Matching Models via Diffusion Model Alignment [22.661660797545164]
  Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains.<n>This work addresses the critical challenge of efficiently transferring knowledge from pre-trained diffusion models to flow matching.<n>We propose Diff2Flow, a novel framework that systematically bridges diffusion and FM paradigms by rescaling timesteps, aligning interpolants, and deriving FM-compatible velocity fields from diffusion predictions.
  arXiv  Detail & Related papers  (2025-06-02T20:05:05Z)
• ADT: Tuning Diffusion Models with Adversarial Supervision [16.974169058917443]
  Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. We propose Adrial Diffusion Tuning (ADT) to stimulate the inference process during optimization and align the final outputs with training data. ADT features a siamese-network discriminator with a fixed pre-trained backbone and lightweight trainable parameters.
  arXiv  Detail & Related papers  (2025-04-15T17:37:50Z)
• Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control [43.87692887705523]
  We build inductive biases into the training and sampling of Diffusion Probabilistic Models (DPMs) We show that different datasets necessitate different inductive biases, and that appropriate frequency-based noise control induces increased generative performance compared to standard diffusion.
  arXiv  Detail & Related papers  (2025-02-14T15:46:37Z)
• Simple Guidance Mechanisms for Discrete Diffusion Models [44.377206440698586]
  We develop a new class of diffusion models that leverage uniform noise and that are more guidable because they can continuously edit their outputs. We improve the quality of these models with a novel continuous-time variational lower bound that yields state-of-the-art performance.
  arXiv  Detail & Related papers  (2024-12-13T15:08:30Z)
• Local Flow Matching Generative Models [19.859984725284896]
  Flow Matching (FM) is a simulation-free method for learning a continuous and invertible flow to interpolate between two distributions.<n>We introduce a stepwise FM model called Local Flow Matching (LFM), which consecutively learns a sequence of FM sub-models.<n>We empirically demonstrate improved training efficiency and competitive generative performance of LFM compared to FM.
  arXiv  Detail & Related papers  (2024-10-03T14:53:10Z)
• Improving Consistency Models with Generator-Induced Flows [16.049476783301724]
  Consistency models imitate the multi-step sampling of score-based diffusion in a single forward pass of a neural network. They can be learned in two ways: consistency distillation and consistency training. We propose a novel flow that transports noisy data towards their corresponding outputs derived from the currently trained model.
  arXiv  Detail & Related papers  (2024-06-13T20:22:38Z)
• Text-to-Image Rectified Flow as Plug-and-Play Priors [52.586838532560755]
  Rectified flow is a novel class of generative models that enforces a linear progression from the source to the target distribution. We show that rectified flow approaches surpass in terms of generation quality and efficiency, requiring fewer inference steps. Our method also displays competitive performance in image inversion and editing.
  arXiv  Detail & Related papers  (2024-06-05T14:02:31Z)
• Fair Sampling in Diffusion Models through Switching Mechanism [5.560136885815622]
  We propose a fairness-aware sampling method called textitattribute switching mechanism for diffusion models. We mathematically prove and experimentally demonstrate the effectiveness of the proposed method on two key aspects.
  arXiv  Detail & Related papers  (2024-01-06T06:55:26Z)
• Adaptive Training Meets Progressive Scaling: Elevating Efficiency in Diffusion Models [52.1809084559048]
  We propose a novel two-stage divide-and-conquer training strategy termed TDC Training. It groups timesteps based on task similarity and difficulty, assigning highly customized denoising models to each group, thereby enhancing the performance of diffusion models. While two-stage training avoids the need to train each model separately, the total training cost is even lower than training a single unified denoising model.
  arXiv  Detail & Related papers  (2023-12-20T03:32:58Z)
• Guided Diffusion from Self-Supervised Diffusion Features [49.78673164423208]
  Guidance serves as a key concept in diffusion models, yet its effectiveness is often limited by the need for extra data annotation or pretraining. We propose a framework to extract guidance from, and specifically for, diffusion models.
  arXiv  Detail & Related papers  (2023-12-14T11:19:11Z)
• Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models [77.83923746319498]
  We propose a framework called Diff-Instruct to instruct the training of arbitrary generative models. We show that Diff-Instruct results in state-of-the-art single-step diffusion-based models. Experiments on refining GAN models show that the Diff-Instruct can consistently improve the pre-trained generators of GAN models.
  arXiv  Detail & Related papers  (2023-05-29T04:22:57Z)
• Structural Pruning for Diffusion Models [65.02607075556742]
  We present Diff-Pruning, an efficient compression method tailored for learning lightweight diffusion models from pre-existing ones. Our empirical assessment, undertaken across several datasets highlights two primary benefits of our proposed method.
  arXiv  Detail & Related papers  (2023-05-18T12:38:21Z)
• Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods [27.014858633903867]
  We present a training framework for feature disentanglement of Diffusion Models (FDiff) We propose two sampling methods that can boost the realism of our Diffusion Models and also enhance the controllability.
  arXiv  Detail & Related papers  (2023-02-28T07:43:00Z)
• Diffusion Models in Vision: A Survey [80.82832715884597]
  A diffusion model is a deep generative model that is based on two stages, a forward diffusion stage and a reverse diffusion stage. Diffusion models are widely appreciated for the quality and diversity of the generated samples, despite their known computational burdens.
  arXiv  Detail & Related papers  (2022-09-10T22:00:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.