English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Public large-scale text-to-image diffusion models, such as Stable Diffusion,have gained significant attention from the community. These models can beeasily customized for new concepts using low-rank adaptations (LoRAs). However,the utilization of multiple concept LoRAs to jointly support multiplecustomized concepts presents a challenge. We refer to this scenario asdecentralized multi-concept customization, which involves single-client concepttuning and center-node concept fusion. In this paper, we propose a newframework called Mix-of-Show that addresses the challenges of decentralizedmulti-concept customization, including concept conflicts resulting fromexisting single-client LoRA tuning and identity loss during model fusion.Mix-of-Show adopts an embedding-decomposed LoRA (ED-LoRA) for single-clienttuning and gradient fusion for the center node to preserve the in-domainessence of single concepts and support theoretically limitless concept fusion.Additionally, we introduce regionally controllable sampling, which extendsspatially controllable sampling (e.g., ControlNet and T2I-Adaptor) to addressattribute binding and missing object problems in multi-concept sampling.Extensive experiments demonstrate that Mix-of-Show is capable of composingmultiple customized concepts with high fidelity, including characters, objects,and scenes.

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models