Objective: To develop a nomogram-based model for predicting the time required to reestablish independent walking on level ground in stroke patients with hemiplegia admitted to a convalescent rehabilitation ward, based on available information at admission.Methods: This retrospective study included 228 patients with stroke-induced hemiplegia who were admitted to the convalescent rehabilitation ward of our hospital. The assessed outcome was the proportion of patients who achieved independent walking at 30, 60, 90, and 120 days after stroke onset. Candidate predictors at admission included age, sex, stroke type, side of paresis, number of days from onset to admission, ability to get up, lower extremity Fugl-Meyer Assessment (FMA), Berg Balance Scale (BBS) score, and total motor and cognitive Functional Independence Measure (FIM) scores. Cox proportional hazards analysis was used to identify significant predictors, and a nomogram was developed.Results: The multivariate analysis identified age, number of days from onset, ability to get up, BBS score, and total FIM motor and cognitive scores as significant predictors. The nomogram demonstrated high predictive performance (C-index: 0.858; bootstrap: 0.851) with good calibration.Conclusion: This model may assist clinicians in estimating the probability of achieving independent walking on level ground at 30, 60, 90, and 120 days after stroke onset, supporting early goal setting and individualized rehabilitation planning.