LoRAShop：基於校正流變換器的免訓練多概念圖像生成與編輯

LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers

May 29, 2025

作者: Yusuf Dalva, Hidir Yesiltepe, Pinar Yanardag

cs.AI

摘要

我們推出了LoRAShop，這是首個基於LoRA模型實現多概念圖像編輯的框架。LoRAShop的構建基於對Flux風格擴散變壓器內部特徵交互模式的一個關鍵觀察：在去噪過程的早期階段，特定概念對應的變壓器特徵會激活空間上連貫的區域。我們利用這一觀察，在先前的前向傳播中為每個概念推導出解耦的潛在掩碼，並僅在待個性化概念所限定的區域內融合相應的LoRA權重。由此產生的編輯效果能將多個主題或風格無縫融入原始場景，同時保持全局上下文、光照及精細細節的完整性。實驗表明，與基準方法相比，LoRAShop在身份保持方面表現更優。通過省去重新訓練和外部約束，LoRAShop將個性化擴散模型轉變為實用的“LoRA版Photoshop”工具，為組合式視覺敘事和快速創意迭代開闢了新途徑。

English

We introduce LoRAShop, the first framework for multi-concept image editing with LoRA models. LoRAShop builds on a key observation about the feature interaction patterns inside Flux-style diffusion transformers: concept-specific transformer features activate spatially coherent regions early in the denoising process. We harness this observation to derive a disentangled latent mask for each concept in a prior forward pass and blend the corresponding LoRA weights only within regions bounding the concepts to be personalized. The resulting edits seamlessly integrate multiple subjects or styles into the original scene while preserving global context, lighting, and fine details. Our experiments demonstrate that LoRAShop delivers better identity preservation compared to baselines. By eliminating retraining and external constraints, LoRAShop turns personalized diffusion models into a practical `photoshop-with-LoRAs' tool and opens new avenues for compositional visual storytelling and rapid creative iteration.