In the paper we present a model based method for generating 3D face models from multiple images by means of an energy minimization algorithm. The energy function takes into account of: i) how well the luminance profiles are transferred (through the 3D model) from one image to the others; ii) how smooth are the reconstructed surfaces; iii) how it is congruent with an adapted face template mode (Candide model). It is important to notice that with the proposed method for each considered face two different 3D models are reconstructed: one with high resolution and one with low-resolution obtained a reshaped Candide model. The first model can be used, for example, in 3D face analysis/recognition systems, while the second can be more useful for searching a specific face model in a large database.