The long short-term memory (LSTM) model requires continuous input data in time series. Choosing appropriate input factors and input methods is of great significance for improving the performance of LSTM in flood forecasting. In this study, three input methods were set to consider the discontinuous temporal characteristics of flood events including a fixed time step. Input method 1 concatenates flood events was a dynamic time step. Input method 2 considers floods separately, and input method 3 combines fixed and dynamic time steps by separating treatment of flood events. Seven input schemes were designed by considering the above input methods with rainfall, streamflow, and both rainfall and streamflow as input factors respectively. The performance of LSTM model with different input schemes was compared in the Jianyang River Basin, Fujian. Results show that: (1) The LSTM model with rainfall and streamflow as input factors (schemes 3, 6, 7) yields better flood calculation results than those with only rainfall (schemes 2, 5) or only streamflow (schemes 1, 4) as input factors. (2) When the lead times are 1-2 hours, there is no significant difference in the prediction results of schemes 3, 6,7. When the lead times are 3-5 hours, the scheme 7 that combines fixed step size and dynamic step size settings has the best performance. (3) The scheme 7 uses multiple models with the lead times of 1-3 hours and a single model with the lead time of 1 hour for rolling forecasting. The multi model approach has higher accuracy in predicting flood peaks within the lead time of 3 hours. This research provides reference for the selection of input factors and time step setting of LSTM flood forecasting model, combining the setting of fixed time step and dynamic time step, can improve the accuracy of flood forecasting under longer lead times.