الملخص
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.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
He, H., Cai, R., Wang, Y., Yu, L., & Zeng, X. (2026). V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization. https://omanscience.com/ar/articles/v-engram-trigger-indexed-external-memory-for-modular-text-to-image-personalization
MLA 9
He, Haoran, et al. "V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization." https://omanscience.com/ar/articles/v-engram-trigger-indexed-external-memory-for-modular-text-to-image-personalization.
شيكاغو (المؤلف–التاريخ)
He, Haoran, Runyuan Cai, Yiming Wang, Lin Yu, and Xiaodong Zeng. 2026. "V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization." https://omanscience.com/ar/articles/v-engram-trigger-indexed-external-memory-for-modular-text-to-image-personalization.
هارفارد
He, H., Cai, R., Wang, Y., Yu, L. and Zeng, X. (2026) 'V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization', Available at: https://omanscience.com/ar/articles/v-engram-trigger-indexed-external-memory-for-modular-text-to-image-personalization.
فانكوفر
He H, Cai R, Wang Y, Yu L, Zeng X. V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization. https://omanscience.com/ar/articles/v-engram-trigger-indexed-external-memory-for-modular-text-to-image-personalization
IEEE
H. He, R. Cai, Y. Wang, L. Yu, and X. Zeng, "V-Engram: Trigger-Indexed External Memory for Modular Text-to-Image Personalization," https://omanscience.com/ar/articles/v-engram-trigger-indexed-external-memory-for-modular-text-to-image-personalization.