AIbase
Product LibraryTool Navigation

SEIKO

Public

SEIKO is a novel reinforcement learning method to efficiently fine-tune diffusion models in an online setting. Our methods outperform all baselines (PPO, classifier-based guidance, direct reward backpropagation) for fine-tuning Stable Diffusion.

Creat2024-06-26T13:38:21
Update2025-03-21T22:55:32
https://arxiv.org/abs/2402.16359
21
Stars
0
Stars Increase

Related projects