Research map / Image generation / Text-to-image diffusion
Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use ED-LoRA instead of standard LoRA for client tuning, with weight fusion (ablation) | Multi-concept customization · Real-Objects | image-alignment mean change: 0.115 to 0.094 identity loss | Helped |
| Replace weight fusion with gradient fusion for ED-LoRAs (ablation) | Multi-concept customization · Real-Objects | image-alignment mean change: 0.094 to 0.025 identity loss | Helped |
| Replace weight fusion with gradient fusion for ED-LoRAs (ablation) | Multi-concept customization · Human preference study | image alignment preference: 33.5% -> 66.5% | Helped |
| Replace weight fusion with gradient fusion for ED-LoRAs (ablation) | Multi-concept customization · Human preference study | text alignment preference: 47.5% -> 52.5% | Helped |
| Use regionally aware cross-attention with regional prompts and masks (ablation) | Multi-concept sampling · Qualitative attribute binding | attribute binding | Helped |
Closest papers by meaning
- Orthogonal Adaptation for Modular Customization of Diffusion Models (CVPR 2024 · similarity 0.90)
- LoRACLR: Contrastive Adaptation for Customization of Diffusion Models (CVPR 2025 · similarity 0.90)
- LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers (NeurIPS 2025 · similarity 0.88)
- Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation (ICLR 2024 · similarity 0.88)
- How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization? (NeurIPS 2024 · similarity 0.87)
- TweedieMix: Improving Multi-Concept Fusion for Diffusion-based Image/Video Generation (ICLR 2025 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.