LoRA Scope: Semantic Change Probing for LoRA Search and Evaluation

The rapid growth of LoRA adapters for text-to-image diffusion models has made them difficult to understand, evaluate, and search beyond thumbnails and noisy metadata. We introduce LoRA Scope, a framework that represents each LoRA by what it changes: the CLIP-space difference between matched base and LoRA-adapted generations. The framework connects three complementary components through diagnostic prompts and generated images. LoUPE uses VLM-guided prompt exploration to construct adapter-specific diagnostic prompts; the LoUPE Score measures the stability, precision, and strength of the induced changes and aligns with human judgments; and LoCAL aligns LoRA weight representations with CLIP embeddings of these prompts and LoRA-generated images through learned query adapters, enabling text- and image-to-LoRA retrieval without query-time generation. On a large corpus of real-world LoRAs, LoRA Scope provides interpretable adapter characterization, human-aligned quality assessment, and scalable metadata-free retrieval directly from LoRA weights.