This work proposes the use of conditional flow‐based generative models to learn an approximationof the distribution of the critical points of a cost function. This approximation is used to incrementallyidentify all critical points, in the feasible domain of said function, by iteratively alternating thesampling of the distribution and the retraining of the model with the newly discovered points. Thispaper will focus, in particular, on the identification and conditional generation of all local minimain the case in which the value of the cost function is subject to some uncertain parameters. Thetarget application is the study of complex dynamical systems. It will be shown that when the costfunction represents the potential of a dynamical system, the proposed flow‐based model can beused to generate minima conditional to their degree of stability or metastability.In dynamical systems subject to uncertainty in the dynamics, the existence of the minima and theirstability characteristics are a function of the uncertain parameters. Thus, the proposed model architectureincorporates a conditional variable that can be the value of the uncertain parameters ora label indicating a characteristic of the critical points. The proposed conditional flow‐model allowsthe generation of points with the desired characteristics. This is of extreme importance in the analysisof equilibrium states and possible transitions, controlled or uncontrolled, to other equilibriumstates.Some illustrative examples of functions with hundreds of local minima are used to test the potentialitiesof the proposed approach. It will be shown that the use of a generative approachis advantageous to explore more complex landscapes compared to a basic random local searchalgorithm. When applied to the analysis of the uncertain five body problem, the proposed generativemodel is shown to successfully identify all dynamical equilibrium solutions under uncertainty.Finally when trained on the dynamical stability properties of the critical points, the model can successfullydifferentiate between stable and metastable solutions. These results show that, for certaintypes of system, the flow‐based model can be trained to find equilibrium points more efficientlythan a simple random search. Moreover, we demonstrate that conditional flow‐based models arecapable of one‐shot sampling for specific values of uncertain parameters or characteristics of theequilibrium points.