In recent years, diffusion models trained on equilibrium molecular distributions have proven effective for sampling biomolecules. Beyond direct sampling, the score of such a model can also be used to derive the forces that act on molecular systems. However, while classical diffusion sampling usually recovers the training distribution, forces extracted from the score reveal inconsistencies and lead to incorrect dynamics, even for low-dimensional toy systems. In this talk, we will discuss why these inconsistencies happen, how the Fokker-Planck equation can be used to facilitate this problem and demonstrate diffusion models capable of both: sampling and simulation for biomolecules such as alanine dipeptide or BBA.