A General Framework for Inference-time Scaling and Steering of Diffusion
Models
A General Framework for Inference-time Scaling and Steering of Diffusion
Models
Diffusion models produce impressive results in modalities ranging from images and video to protein design and text. However, generating samples with user-specified properties remains a challenge. Recent research proposes fine-tuning models to maximize rewards that capture desired properties, but these methods require expensive training and are prone to mode collapse. …