SFDDM: Single-fold Distillation for Diffusion models
While diffusion models effectively generate remarkable synthetic images, a key limitation is the inference inefficiency, requiring numerous sampling steps. To accelerate inference and maintain high-quality synthesis, teacher-student distillation is applied to compress the diffusion models in a progressive and binary manner by retraining, e.g., reducing the 1024-step model to a 128-step model in 3 folds. In this paper, we propose a single-fold distillation algorithm, SFDDM, which can flexibly compress the teacher diffusion model into a student model of any desired step, based on reparameterization of the intermediate inputs from the teacher model. To train the student diffusion, we minimize not only the output distance but also the distribution of the hidden variables between the teacher and student model. Extensive experiments on four datasets demonstrate that our student model trained by the proposed SFDDM is able to sample high-quality data with steps reduced to as little as approximately 1%, thus, trading off inference time. Our remarkable performance highlights that SFDDM effectively transfers knowledge in single-fold distillation, achieving semantic consistency and meaningful image interpolation.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ManifoldGD: Training-Free Hierarchical Manifold Guidance for Diffusion-Based Dataset Distillation
In recent times, large datasets hinder efficient model training while also containing redundant concepts. Dataset distillation aims to synthesize compact datasets that preserve the knowledge of large-scale training sets …
Amortized Posterior Sampling with Diffusion Prior Distillation
We propose a variational inference approach to sample from the posterior distribution for solving inverse problems. From a pre-trained diffusion model, our approach trains a conditional flow model to minimize the diverge…
Variational InferenceMasked Auto-Regressive Variational Acceleration: Fast Inference Makes Practical Reinforcement Learning
Masked auto-regressive diffusion models (MAR) benefit from the expressive modeling ability of diffusion models and the flexibility of masked auto-regressive ordering. However, vanilla MAR suffers from slow inference due …
Reinforcement LearningInference-Time Diffusion Model Distillation
Diffusion distillation models effectively accelerate reverse sampling by compressing the process into fewer steps. However, these models still exhibit a performance gap compared to their pre-trained diffusion model count…
DenoisingmodelVariance Reduction on the Camera Axis: Multi-View Score Distillation for 3D
Score distillation turns a pretrained 2D diffusion model into a 3D generator, but the per-step gradient is estimated from a single randomly chosen view: it is high-variance and blind to global shape consistency. Prior wo…