LISA: Likelihood Score Alignment for Visual-condition Controllable Generation
Score-based generative modeling reveals that side networks contribute likelihood scores to conditional control, leading to improved training efficiency through likelihood score ali…
Hugging Face · Daily Papers
·Yanghao Wang, Hongxu Chen
·
·▲ 13 upvotes
Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.
Autores: Yanghao Wang, Hongxu Chen, Jiazhen Liu, Zhenqi He, Rui Liu, Zhen Wang
- 13 upvotes da comunidade
- Temas: score-based generative modeling, diffusion models, flow models, likelihood score, score latent space, regularization method
Resumo
Resumo original (em inglês), extraído do paper:
Score-based generative modeling reveals that side networks contribute likelihood scores to conditional control, leading to improved training efficiency through likelihood score alignment regularization.
