Unconditional Diffusion Guidance
Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative models. Classifier guidance combines the score estimate of a diffusion model with the gradient of an image classifier and thereby requires training an image classifier separate from the diffusion model. It also raises the question of whether guidance can be performed without a classifier. We show that guidance can be indeed performed by a pure generative model without such a classifier: in what we call unconditional guidance, we jointly train a conditional and an unconditional diffusion model, and we combine the resulting conditional and unconditional score estimates to attain a trade-off between sample quality and diversity similar to that obtained using classifier guidance.
Code (0)
등록된 구현이 없습니다.
Tasks
DiversityMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Conditional Diffusion with Less Explicit Guidance via Model Predictive Control
How much explicit guidance is necessary for conditional diffusion? We consider the problem of conditional sampling using an unconditional diffusion model and limited explicit guidance (e.g., a noised classifier, or a con…
Model Predictive ControlClassifier-Free Diffusion Guidance
Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other type…
DiversityNo Training, No Problem: Rethinking Classifier-Free Guidance for Diffusion Models
Classifier-free guidance (CFG) has become the standard method for enhancing the quality of conditional diffusion models. However, employing CFG requires either training an unconditional model alongside the main diffusion…
Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models
Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching, the dominant paradigm for training-free …
Self-Rectifying Diffusion Sampling with Perturbed-Attention Guidance
Recent studies have demonstrated that diffusion models are capable of generating high-quality samples, but their quality heavily depends on sampling guidance techniques, such as classifier guidance (CG) and classifier-fr…
DeblurringDenoisingImage GenerationImage Restoration