VAGS: Velocity Adaptive Guidance Scale for Image Editing and Generation

ArXi:2605.15661v1 Announce Type: cross Classifier-free guidance (CFG) is the primary control over how strongly text semantics move a flow-based sampler, yet standard practice holds its scale fixed across the entire ODE trajectory. This is a fundamental mismatch: early steps are noise-dominated and carry weak semantic signal, while late steps commit image structure and demand stronger directional commitment; critically, the value of any guidance strength depends on whether the guided velocity is consistent with the model's current dynamics or working against them.