Multi-LoRA Composition for Image Generation
CoRR(2024)
摘要
Low-Rank Adaptation (LoRA) is extensively utilized in text-to-image models
for the accurate rendition of specific elements like distinct characters or
unique styles in generated images. Nonetheless, existing methods face
challenges in effectively composing multiple LoRAs, especially as the number of
LoRAs to be integrated grows, thus hindering the creation of complex imagery.
In this paper, we study multi-LoRA composition through a decoding-centric
perspective. We present two training-free methods: LoRA Switch, which
alternates between different LoRAs at each denoising step, and LoRA Composite,
which simultaneously incorporates all LoRAs to guide more cohesive image
synthesis. To evaluate the proposed approaches, we establish ComposLoRA, a new
comprehensive testbed as part of this research. It features a diverse range of
LoRA categories with 480 composition sets. Utilizing an evaluation framework
based on GPT-4V, our findings demonstrate a clear improvement in performance
with our methods over the prevalent baseline, particularly evident when
increasing the number of LoRAs in a composition.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要