Abstract: Carbon stock and habitat quality are two important indicators for evaluating the function of ecosystem services, which can provide a basic scientific basis for ecosystem protection and management. In this study, the PLUS model was used to predict the land use data of the Yunnan-Guizhou Plateau in 2025 and 2030, and the InVEST model was used to analyze the carbon stock and habitat quality in the region from 2000 to 2030 in a spatio-temporal manner; Explore the relationship with the results in terms of slope, elevation, four levels of zoning, and land use, respectively, and explore the drivers. The results showed that (1) the carbon stocks (×109t) from 2000 to 2030 were 7.392, 7.389, 7.403, 7.406, 7.426, 7.249, and 6.921, respectively; and the habitat quality was 0.770, 0.765, 0.760, 0.757, 0.752, 0.7301, and 0.7547, respectively; and (2) the forested land contributed to the carbon storage; forest land had the highest habitat quality, and built-up land had the lowest habitat quality; (3) the highest carbon storage over 20 years was found in the plot in the northern part of Chuxiong, east of Lijiang City; and the highest habitat quality over 20 years was found in the plot in the western part of Lijiang City-southeast of Nujiang Lisu Autonomous Prefecture; (4) the factor that had the strongest explanatory power for carbon storage was elevation, with a p-value of 0.37214, and the strongest interaction effect was land use slope orientation, whose value reached 0.8887.