This paper investigates the capacity of general multiple-input single-output (MISO) optical intensity channels (OICs) under per-antenna peak-and averageintensity constraints. We first consider the MISO equal-cost constrained OIC (EC-OIC), where, apart from the peak-intensity constraint, average intensities of inputs are equal to arbitrarily preassigned constants. The second model of our interest is the MISO bounded-cost constrained OIC (BC-OIC), where, as compared with the EC-OIC, average intensities of inputs are no larger than arbitrarily preassigned constants. By introducing quantile functions, stop-loss transform and convex ordering of nonnegative random variables, we prove two decomposition theorems for bounded and nonnegative random variables, based on which we equivalently transform both the EC-OIC and the BC-OIC into single-input single-output channels under a peak-intensity and several stop-loss mean constraints. Lower and upper capacity bounds for both channels are established, based on which the asymptotic capacity at high and low signal-to-noise-ratio are determined.Index terms -Channel capacity, Gaussian noise, intensity-modulation and direct-detection (IM/DD), multiple-input single-output, per-antenna intensity constraint, optical wireless communication.