Differential Vector Erasure: Unified Training-Free Concept Erasure for Flow Matching Models

2026-02-01

AI Summary

This work addresses the challenge of safely removing undesirable concepts—such as NSFW content, copyrighted styles, or specific objects—from flow-matching generative models without requiring retraining. It proposes the first training-free concept erasure framework, which analyzes the structure of the generative flow’s velocity field to construct a differential vector field that precisely captures the semantic direction corresponding to the target concept. During inference, the method removes the associated components via directional projection while preserving semantically unrelated features. Experiments on the FLUX model demonstrate that this approach significantly outperforms existing techniques, effectively suppressing unwanted content while maintaining high image quality and diversity.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Machine Learning: Deep Generative Models & Autoencoders

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Text-to-image diffusion models have demonstrated remarkable capabilities in generating high-quality images, yet their tendency to reproduce undesirable concepts, such as NSFW content, copyrighted styles, or specific objects, poses growing concerns for safe and controllable deployment. While existing concept erasure approaches primarily focus on DDPM-based diffusion models and rely on costly fine-tuning, the recent emergence of flow matching models introduces a fundamentally different generative paradigm for which prior methods are not directly applicable. In this paper, we propose Differential Vector Erasure (DVE), a training-free concept erasure method specifically designed for flow matching models. Our key insight is that semantic concepts are implicitly encoded in the directional structure of the velocity field governing the generative flow. Leveraging this observation, we construct a differential vector field that characterizes the directional discrepancy between a target concept and a carefully chosen anchor concept. During inference, DVE selectively removes concept-specific components by projecting the velocity field onto the differential direction, enabling precise concept suppression without affecting irrelevant semantics. Extensive experiments on FLUX demonstrate that DVE consistently outperforms existing baselines on a wide range of concept erasure tasks, including NSFW suppression, artistic style removal, and object erasure, while preserving image quality and diversity.

Problem

• concept erasure
• flow matching models
• text-to-image generation
• undesirable content
• training-free

Innovation

• Differential Vector Erasure
• flow matching
• concept erasure
• training-free
• velocity field