[Submitted on 24 Oct 2026 (v1), last revised 27 Oct 2026 (this version, v2)]
Abstract:Affect-controlled image generation should change how a scene feels while preserving what the prompt specifies. We study the temporal allocation of stochastic exploration and policy optimization in flow-matching models as a means of controlling this balance. During RL training, our semantic-first schedule uses deterministic ordinary differential equation (ODE) sampling during the high-noise phase and confines stochastic differential equation (SDE) exploration and group relative policy optimization (GRPO) to a late window. Controlled experiments separate exploration location, optimization location, and terminal-step sampling, showing distinct semantic benefits from late exploration and late updates. On FLUX.1-dev, semantic-first improves prompt faithfulness, independently evaluated affect accuracy, and human-rated semantic preservation and overall preference. The expanded semantic audit records 2.7% subject drift, while GRPO training time decreases by 41.1% relative to original full-path Flow-GRPO. Window-width experiments characterize the affect-semantic and computational trade-offs, and replication on SD3.5-Medium reproduces the scheduling advantage. These results establish denoising time as a practical control dimension for reliable emotional image generation.
Submission history
From: Zhenxuan Wang [view email]
[v1] Sat, 24 Oct 2026 05:32:15 UTC (1,088 KB)
[v2] Tue, 27 Oct 2026 15:07:17 UTC (15,051 KB)
