We present FlowFixer, a refinement framework for subject-driven generation (SDG) that restores fine details lost during generation caused by changes in scale and perspective of a subject. FlowFixer proposes direct image-to-image translation from visual references, avoiding ambiguities in language prompts. To enable image-to-image training, we introduce a one-step denoising scheme to generate self-supervised training data, which automatically removes high-frequency details while preserving global structure, effectively simulating real-world SDG errors. We further propose a keypoint matching-based metric to properly assess fidelity in details beyond semantic similarities usually measured by CLIP or DINO. Experimental results demonstrate that FlowFixer outperforms state-of-the-art SDG methods in both qualitative and quantitative evaluations, setting a new benchmark for high-fidelity subject-driven generation.
@article{arxiv.2602.21402,
title = {FlowFixer: Towards Detail-Preserving Subject-Driven Generation},
author = {Jinyoung Jun and Won-Dong Jang and Wenbin Ouyang and Raghudeep Gadde and Jungbeom Lee},
journal= {arXiv preprint arXiv:2602.21402},
year = {2026}
}