arXiv AI By Zhongsheng Wang, Zhedong Lin, Qian Liu, Xinyu Zhang, Jiamou Liu

SDO: Subspace Deconflicting Operator for Multi-Adapter Composition

Read the original on arXiv AI →

arXiv:2608. 13820v1 Announce Type: new Abstract: Composing independently trained adapters within a shared diffusion backbone provides a modular approach to multi-character generation, but naive joint deployment often causes identity mixing, cross-character attribute leakage, and unstable scene composition.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

Hugging Face Trending Papers
Jul 6

LILAC: Layer-Wise Independent LoRAs and Cascaded Conditioning for Multi-Concept Customization of Diffusion Models

Personalizing text-to-image diffusion models to render several specific subjects in a coherent image remains challenging: the model must preserve each subject's identity while keeping the scene spatially and visually coherent. Methods that fuse independently trained concept adapters in a shared weight space (via federated averaging, gradient fusion, or orthogonality constraints) suffer from identity confusion and style bleeding and require joint retraining.

Hugging Face Trending Papers
Aug 4

DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion Transformers

Recent advances in Diffusion Transformers (DiTs) have enabled remarkable progress in visual synthesis, benefiting from their superior scalability. To facilitate DiTs' capability of capturing meaningful internal representations, recent works such as REPA incorporate external pretrained encoders for representation alignment.

Hugging Face Trending Papers
Jul 8

Stage-Aware Adaptation and Distribution Calibration for Subject-Driven Personalized Text-to-Image Generation

Subject-driven personalized text-to-image generation requires a pretrained diffusion model to acquire a specific subject from a few reference images while preserving subject identity, following novel text prompts, and maintaining sample diversity. Existing optimization-based methods instantiate subject adaptation through full fine-tuning, textual embedding optimization, or low-rank parameter updates; PaRa further constrains personalization from the perspective of parameter rank reduction.