Objective To explore the effects of comprehensive rehabilitation training on family function and medication adherence in patients with stable schizophrenia in the community. Methods This study was a prospective randomized controlled trail. A total of 412 patients with stable schizophrenia in the community from January 2022 to June 2023 in Jinan Jiyang Mental Health Center were selected for the study. A computer generated random number table was used to divide the patients into control group （n=206） and intervention group （n=206） in a ratio of 1∶1. Control group received conventional medication， and intervention group was treated with comprehensive rehabilitation training based on control group， including five modules of health education， medication management skills training， symptom monitoring， social skills training and vocational rehabilitation training. The Chinese version of the 8-item Morisky Medication Adherence Scale （MMAS-8）， Positive and Negative Symptom Schedule （PANSS）， Family Burden Scale of Diseases （FBSD）， Social Dysfunction Screening Scale （SDSS）， and Social Support Rating Scale （SSRS） were used to assess the medication adherence， severity of mental symptoms of patients， burden of mental disorders on the families and social function deficits in patients with mental disorders. Time trend analysis and mixed-effects model was used to assess the differences in scale scores between intervention and control groups before intervention， 3， 6， 9 and 12 months after intervention to further explore the dynamics of the intervention effect. Results There was no statistically significant difference in MMAS-8， PANSS， FBSD， SDSS and SSRS scores between the two groups before intervention （all P＞ 0.05）. At 3， 9， and 12 months of intervention， the MMAS-8 scores of intervention group were higher than those of control group， and the PANSS， FBSD， and SDSS scores were lower than those of control group， and the differences were statistically significant （all P＜ 0.05）， the differences in the SSRS scores of the two groups were not statistically significant （all P＞ 0.05）. Mixed-effects model analyses showed no statistically significant intervention fixed effects for MMAS-8， PANSS， FBSD， and SDSS scores （all P ＞ 0.05）， but the interactions between intervention and time were statistically significant （all P＜0.05）. The time trend test showed statistically significant differences in MMAS-8， PANSS， FBSD， SDSS and SSRS scores over time in both groups （P ＜ 0.05）. Conclusions Comprehensive rehabilitation training combined with medication significantly increases medication adherence and alleviate symptoms， which helps to improve long-term management and quality of life in patients.