AcFlow: שליטה במפענחי תמונות-לטקסט דיפוזיה-טרנספורמרים על ידי זרימה קונדיציונלית-למדות

תקציר מקורי באנגליתarXiv:2609.10723v2 Announce Type: replace-cross Abstract: Text-to-image diffusion transformers (DiTs) are powerful generators, yet direct prompting provides limited control interface for style intensity and can fail to suppress unwanted concepts. To enable these controls, we introduce AcFlow, an inference-time controller that transports intermediate layer image-token activations through a learned concept-conditioned velocity field while keeping the base DiT frozen. A textual concept description specifies the desired intervention, while the integration horizon provides a continuous control parameter. The field produces token-varying, activation-dependent updates. With parameters shared across concepts within each task family, one field covers over 15,000 style descriptions or over 1,000 sup