Improving GFlowNets for Text-to-Image Diffusion Alignment
This work addresses the challenge of controlling generation in diffusion models for text-to-image tasks, offering a method to enhance alignment with specified properties, though it is incremental as it builds on prior reinforcement learning approaches.
The paper tackled the problem of aligning text-to-image diffusion models with black-box reward functions for desired properties, proposing the DAG algorithm based on GFlowNets, which effectively improved alignment in experiments on Stable Diffusion with various rewards.
Diffusion models have become the de-facto approach for generating visual data, which are trained to match the distribution of the training dataset. In addition, we also want to control generation to fulfill desired properties such as alignment to a text description, which can be specified with a black-box reward function. Prior works fine-tune pretrained diffusion models to achieve this goal through reinforcement learning-based algorithms. Nonetheless, they suffer from issues including slow credit assignment as well as low quality in their generated samples. In this work, we explore techniques that do not directly maximize the reward but rather generate high-reward images with relatively high probability -- a natural scenario for the framework of generative flow networks (GFlowNets). To this end, we propose the Diffusion Alignment with GFlowNet (DAG) algorithm to post-train diffusion models with black-box property functions. Extensive experiments on Stable Diffusion and various reward specifications corroborate that our method could effectively align large-scale text-to-image diffusion models with given reward information.