Beyond Fine-Tuning: A Systematic Study of Sampling Techniques in Personalized Image Generation
This work addresses a key problem in personalized image generation for users needing tailored outputs, but it is incremental as it builds on existing sampling strategies.
The paper tackles the challenge of balancing concept fidelity and contextual generation in personalized text-to-image generation by systematically analyzing sampling techniques beyond fine-tuning, proposing a decision framework that optimizes concept preservation, prompt adherence, and resource efficiency.
Personalized text-to-image generation aims to create images tailored to user-defined concepts and textual descriptions. Balancing the fidelity of the learned concept with its ability for generation in various contexts presents a significant challenge. Existing methods often address this through diverse fine-tuning parameterizations and improved sampling strategies that integrate superclass trajectories during the diffusion process. While improved sampling offers a cost-effective, training-free solution for enhancing fine-tuned models, systematic analyses of these methods remain limited. Current approaches typically tie sampling strategies with fixed fine-tuning configurations, making it difficult to isolate their impact on generation outcomes. To address this issue, we systematically analyze sampling strategies beyond fine-tuning, exploring the impact of concept and superclass trajectories on the results. Building on this analysis, we propose a decision framework evaluating text alignment, computational constraints, and fidelity objectives to guide strategy selection. It integrates with diverse architectures and training approaches, systematically optimizing concept preservation, prompt adherence, and resource efficiency. The source code can be found at https://github.com/ControlGenAI/PersonGenSampler.