CVDec 29, 2025

ASemConsist: Adaptive Semantic Feature Control for Training-Free Identity-Consistent Generation

arXiv:2512.23245v2h-index: 8
Originality Incremental advance
AI Analysis

This work addresses a key problem in AI-generated content for applications like storytelling and animation, though it is incremental as it builds on existing diffusion models.

The paper tackles the challenge of generating sequences of images with consistent character identity across diverse scenes using text-to-image diffusion models, achieving state-of-the-art performance by overcoming trade-offs between identity consistency and prompt alignment.

Recent text-to-image diffusion models have significantly improved visual quality and text alignment. However, generating a sequence of images while preserving consistent character identity across diverse scene descriptions remains a challenging task. Existing methods often struggle with a trade-off between maintaining identity consistency and ensuring per-image prompt alignment. In this paper, we introduce a novel framework, ASemconsist, that addresses this challenge through selective text embedding modification, enabling explicit semantic control over character identity without sacrificing prompt alignment. Furthermore, based on our analysis of padding embeddings in FLUX, we propose a semantic control strategy that repurposes padding embeddings as semantic containers. Additionally, we introduce an adaptive feature-sharing strategy that automatically evaluates textual ambiguity and applies constraints only to the ambiguous identity prompt. Finally, we propose a unified evaluation protocol, the Consistency Quality Score (CQS), which integrates identity preservation and per-image text alignment into a single comprehensive metric, explicitly capturing performance imbalances between the two metrics. Our framework achieves state-of-the-art performance, effectively overcoming prior trade-offs. Project page: https://minjung-s.github.io/asemconsist

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes