SyncAI.news, a Varaisys broadcasting
V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization
HH

Haoran He, Runyuan Cai, Yiming Wang, Lin Yu, Xiaodong Zeng

· 1 min read

ResearcharXiv cs.AI

V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization

arXiv:2609.37198v1 Announce Type: new Abstract: Pretrained text-to-image models contain broad visual knowledge, yet they cannot reliably acquire or refine a specific visual identity from only a few references while preserving compositional control. Token-embedding methods are compact but often underfit identity, whereas adapter-based methods improve fidelity through persistent weight updates that can be costly to store and interfere when concepts are composed. We introduce V-Engram, a trigger-indexed external memory mechanism for Stable Diffusion 3.5. Each concept is assigned an explicit trigger that retrieves concept-specific memory, whose gated directions enter frozen text-encoder and MMDiT context states as relative residuals. Separating this memory from backbone adaptation enables prompt-selective and multi-concept access without merging model updates. Experiments show that V-Engram broadly matches DreamBooth-LoRA in overall subject fidelity while showing advantages in settings such as contextual subject preservation. Prompt-matched loading retrieves only matched entries, reducing most additional adaptation-state loading for a single-concept query. Qualitative results further demonstrate paired-trigger composition and same-class separation, while prompts without registered entries retain the frozen model's base behavior. Together, these results establish trigger-indexed memory as a modular interface for adding targeted visual evidence without rewriting the generator.

Original source

This story was published by arXiv cs.AI and written by Haoran He, Runyuan Cai, Yiming Wang, Lin Yu, Xiaodong Zeng. SyncAI.news shows a preview; the complete article is on the publisher's site.

Read the full story on arxiv.org

Similar News